Skip to content

Automate browser based workflows with AI

SKY-10580: rebrand Workflows → Agents in the public docs (with redirects) (#6384)

Suchintanc847199fa8b7
diff --git a/docs/changelog.mdx b/docs/changelog.mdx
index 01e4c1408..9d79e18f1 100644
--- a/docs/changelog.mdx
+++ b/docs/changelog.mdx
@@ -43,10 +43,12 @@ keywords:
<p className="cl-subtitle">New features, improvements, and fixes in Skyvern</p>
<a id="week-jun-1-2026"></a>
-<Update label="Week of June 1, 2026" description="Feature preview, tag filters, OSS schedules, captcha improvements, bug fixes">
+<Update label="Week of June 1, 2026" description="Workflows are now Agents, feature preview, tag filters, OSS schedules, captcha improvements">
## New features
+- **Workflows are now Agents** — We've renamed "Workflows" to "Agents" across the product, public API, and docs. The API is now served under `/agents` (e.g. `POST /v1/run/agents`) and accepts an `agent_id` alias for `workflow_id` (same `wpid_` value), with `agent_id` echoed in responses. Fully backwards-compatible: existing `workflow_id` inputs, `/workflows` endpoints, SDK methods, and bookmarked doc URLs all keep working.
+
- **Feature Preview Section in Settings** — A new "Feature Preview" panel in account settings lets you opt into upcoming features before they are fully released. ([#6318](https://github.com/Skyvern-AI/skyvern/pull/6318))
- **Filter Workflows by Tags** — The `GET /workflows` API now accepts a `?tags=` query parameter to filter results by tag. ([#6334](https://github.com/Skyvern-AI/skyvern/pull/6334))
- **Workflow Schedules in Open Source** — Self-hosted Skyvern deployments now support workflow schedules, previously a cloud-only feature. ([#6344](https://github.com/Skyvern-AI/skyvern/pull/6344))
diff --git a/docs/cloud/account-settings/api-keys.mdx b/docs/cloud/account-settings/api-keys.mdx
index 9a81bcb3a..9fa63b6e3 100644
--- a/docs/cloud/account-settings/api-keys.mdx
+++ b/docs/cloud/account-settings/api-keys.mdx
@@ -21,7 +21,7 @@ Open **Settings** in the sidebar. Your API key is shown in a masked field. Click
<img src="/images/cloud/settings-api-key.png" alt="API key display with reveal and copy buttons" />
<Warning>
-Treat your API key like a password. Anyone with this key can create runs, read results, and manage workflows on behalf of your organization.
+Treat your API key like a password. Anyone with this key can create runs, read results, and manage agents on behalf of your organization.
</Warning>
## Using your key
diff --git a/docs/cloud/account-settings/billing-usage.mdx b/docs/cloud/account-settings/billing-usage.mdx
index 085b3578b..af2009e0b 100644
--- a/docs/cloud/account-settings/billing-usage.mdx
+++ b/docs/cloud/account-settings/billing-usage.mdx
@@ -15,7 +15,7 @@ keywords:
- usage
---
-Skyvern bills per **credit**: each browser action the AI takes during a run consumes credits. You pay for real work, not for workflows created or credentials stored.
+Skyvern bills per **credit**: each browser action the AI takes during a run consumes credits. You pay for real work, not for agents created or credentials stored.
## Plans
@@ -88,7 +88,7 @@ Everything in Pro, plus:
- Azure Key Vault integration
- Bitwarden integration
- Custom code blocks
-- Human-in-the-loop workflows
+- Human-in-the-loop agents
[Contact sales](https://skyvern.com/contact) to discuss Enterprise.
</Accordion>
diff --git a/docs/cloud/account-settings/organization-settings.mdx b/docs/cloud/account-settings/organization-settings.mdx
index 048b53256..f216b9477 100644
--- a/docs/cloud/account-settings/organization-settings.mdx
+++ b/docs/cloud/account-settings/organization-settings.mdx
@@ -12,7 +12,7 @@ keywords:
- permissions
---
-Everything in Skyvern (workflows, credentials, runs, API keys) belongs to an **organization**. One is created automatically when you sign up.
+Everything in Skyvern (agents, credentials, runs, API keys) belongs to an **organization**. One is created automatically when you sign up.
## Organization details
@@ -26,7 +26,7 @@ Plans that support multiple users (Pro and Enterprise) show a **Members** sectio
### Inviting members
-Click **Invite Member**, enter their email address, and send the invitation. They'll receive an email with a link to join your organization. Once they accept, they appear in the members list with full access to workflows, runs, credentials, and API keys.
+Click **Invite Member**, enter their email address, and send the invitation. They'll receive an email with a link to join your organization. Once they accept, they appear in the members list with full access to agents, runs, credentials, and API keys.
### Removing members
diff --git a/docs/cloud/browser-management/browser-profiles.mdx b/docs/cloud/browser-management/browser-profiles.mdx
index c1ffb0fe0..d5a920950 100644
--- a/docs/cloud/browser-management/browser-profiles.mdx
+++ b/docs/cloud/browser-management/browser-profiles.mdx
@@ -18,7 +18,7 @@ Profiles are ideal when you:
- Run the same automation repeatedly with the same account (daily reports, scheduled data extraction)
- Want to skip login steps that consume credits and time
-- Need multiple workflows to share the same authenticated state
+- Need multiple agents to share the same authenticated state
<Note>
Looking to manage profiles from code? See the [API & SDK guide](/developers/optimization/browser-profiles) instead.
@@ -56,7 +56,7 @@ Browser profiles are created automatically when you test a password credential w
</Steps>
<Tip>
-The **Save browser session** flow is the easiest way to create a profile. It handles the full lifecycle: open browser, log in, save state. No workflows or API calls required.
+The **Save browser session** flow is the easiest way to create a profile. It handles the full lifecycle: open browser, log in, save state. No agents or API calls required.
</Tip>
---
@@ -87,7 +87,7 @@ For sites with short-lived sessions (banks, healthcare portals), refresh profile
| **Lifetime** | Minutes to hours | Days to months |
| **State** | Current page, cookies, open connections | Cookies, localStorage, session files |
| **Billing** | Charged while open | No cost when not in use |
-| **Best for** | Back-to-back tasks, human-in-the-loop | Repeated logins, scheduled workflows |
+| **Best for** | Back-to-back tasks, human-in-the-loop | Repeated logins, scheduled agents |
---
diff --git a/docs/cloud/browser-management/browser-sessions.mdx b/docs/cloud/browser-management/browser-sessions.mdx
index a8556944b..95bec6f99 100644
--- a/docs/cloud/browser-management/browser-sessions.mdx
+++ b/docs/cloud/browser-management/browser-sessions.mdx
@@ -1,7 +1,7 @@
---
title: Browser Sessions
subtitle: Keep a browser open across multiple tasks
-description: Create and manage persistent browser sessions in the Skyvern Cloud UI to preserve cookies, login state, and page context across multiple tasks and workflows.
+description: Create and manage persistent browser sessions in the Skyvern Cloud UI to preserve cookies, login state, and page context across multiple tasks and agents.
slug: cloud/browser-management/browser-sessions
keywords:
- persistent browser
@@ -32,7 +32,7 @@ Each row shows:
|--------|--------------|
| **ID** | Session identifier (starts with `pbs_`) |
| **Open** | Whether the browser is currently running |
-| **Occupied** | Whether a task or workflow is actively using the session |
+| **Occupied** | Whether a task or agent is actively using the session |
| **Started** | When the session launched |
| **Timeout** | How long the session stays open before auto-closing |
| **CDP URL** | Chrome DevTools Protocol address for direct connection |
@@ -77,7 +77,7 @@ Click on <kbd>Take Control</kbd> to interact with the browser yourself. Use this
### Recordings
-Video recordings of activity in the session. Each recording captures what happened during a task or workflow that ran inside this session.
+Video recordings of activity in the session. Each recording captures what happened during a task or agent that ran inside this session.
### Downloads
@@ -103,19 +103,19 @@ The task executes inside your existing session. Cookies, login state, and page c
---
-## Using a session with a workflow
+## Using a session with an agent
-You can also run workflows inside an existing session:
+You can also run agents inside an existing session:
1. Copy the session ID from the Browsers page
-2. Go to **Workflows** and click **Run** on your workflow
+2. Go to **Agents** and click **Run** on your agent
3. On the parameters page, scroll to **Run Settings**
4. Paste the ID into the **Browser Session ID** field
-5. Click **Run Workflow**
+5. Click **Run Agent**
-The workflow picks up where the browser left off: same page, same cookies, same form data.
+The agent picks up where the browser left off: same page, same cookies, same form data.
-<img src="/images/cloud/workflow-run-session-id-field.png" alt="Workflow run settings panel with a pbs_ session ID entered in the Browser Session ID field" />
+<img src="/images/cloud/workflow-run-session-id-field.png" alt="Agent run settings panel with a pbs_ session ID entered in the Browser Session ID field" />
---
@@ -133,15 +133,15 @@ Closed sessions cannot be reopened. If you need the same login state later, crea
---
-## When to use sessions vs workflows
+## When to use sessions vs agents
-If your steps run back-to-back with no pauses between them, a [workflow](/cloud/building-workflows/build-a-workflow) is more efficient. Workflow blocks share one browser instance with no inter-step startup cost.
+If your steps run back-to-back with no pauses between them, an [agent](/cloud/building-agents/build-an-agent) is more efficient. Agent blocks share one browser instance with no inter-step startup cost.
Sessions are the right choice when you need:
- **Pauses between steps**: review results, get approval, or wait for external input before continuing
- **Human-in-the-loop**: interact with the browser yourself between automated steps
-- **Ad-hoc sequences**: run different tasks one after another without pre-building a workflow
+- **Ad-hoc sequences**: run different tasks one after another without pre-building an agent
---
@@ -153,7 +153,7 @@ Sessions are the right choice when you need:
| **Lifetime** | Minutes to hours | Days to months |
| **State** | Current page, cookies, open connections | Cookies, localStorage, session files |
| **Billing** | Charged while open | No cost when not in use |
-| **Best for** | Back-to-back tasks, human-in-the-loop | Repeated logins, scheduled workflows |
+| **Best for** | Back-to-back tasks, human-in-the-loop | Repeated logins, scheduled agents |
<Tip>
Use a session when you need a live browser right now. Use a [profile](/cloud/browser-management/browser-profiles) when you want to save login state and reuse it later.
diff --git a/docs/cloud/building-workflows/add-parameters.mdx b/docs/cloud/building-agents/add-parameters.mdx
similarity index 78%
rename from docs/cloud/building-workflows/add-parameters.mdx
rename to docs/cloud/building-agents/add-parameters.mdx
index 7dcd9b79c..3d874de35 100644
--- a/docs/cloud/building-workflows/add-parameters.mdx
+++ b/docs/cloud/building-agents/add-parameters.mdx
@@ -1,7 +1,7 @@
---
-title: Workflow Parameters
-subtitle: Pass dynamic values into your workflows at runtime
-description: Define input and credential parameters in the Skyvern Cloud UI workflow editor to pass dynamic values like URLs, JSON data, and vault credentials into workflows at runtime.
+title: Agent Parameters
+subtitle: Pass dynamic values into your agents at runtime
+description: Define input and credential parameters in the Skyvern Cloud UI agent editor to pass dynamic values like URLs, JSON data, and vault credentials into agents at runtime.
slug: cloud/add-parameters
keywords:
- input parameter
@@ -13,15 +13,15 @@ keywords:
- JSON
---
-Parameters let you create reusable workflows that accept different input values each time they run. Instead of hardcoding a URL or search term into a block, you reference a parameter and fill in the value when you run the workflow.
+Parameters let you create reusable agents that accept different input values each time they run. Instead of hardcoding a URL or search term into a block, you reference a parameter and fill in the value when you run the agent.
-This page covers parameters in the Cloud UI workflow editor. If you're building automations in code, parameters are just function arguments. See [Browser Automation](/developers/browser-automations/overview) for the code-first approach.
+This page covers parameters in the Cloud UI agent editor. If you're building automations in code, parameters are just function arguments. See [Browser Automation](/developers/browser-automations/overview) for the code-first approach.
---
## Opening the parameters panel
-In the [workflow editor](/cloud/building-workflows/build-a-workflow), click the **Parameters** button in the header bar. A panel appears below the header showing all defined parameters and controls to add new ones.
+In the [agent editor](/cloud/building-agents/build-an-agent), click the **Parameters** button in the header bar. A panel appears below the header showing all defined parameters and controls to add new ones.
<img src="/images/cloud/parameters-panel-open.png" alt="Parameters panel" />
@@ -33,7 +33,7 @@ Click **Add Parameter** in the panel. Two types are available:
| Type | Use for |
|------|---------|
-| **Input Parameter** | Values the user provides when running the workflow (text, numbers, JSON, etc.) |
+| **Input Parameter** | Values the user provides when running the agent (text, numbers, JSON, etc.) |
| **Credential Parameter** | Securely inject login credentials from a vault (Bitwarden, 1Password, Azure, AWS, or Skyvern) |
Each parameter requires a unique **key**. This is the name you use to reference it in blocks. Keys cannot contain spaces and cannot use [reserved names](#reserved-variables).
@@ -101,7 +101,7 @@ Credential parameters securely inject login credentials into blocks without expo
| **AWS Secret** | Secrets stored in AWS Secrets Manager |
| **Azure Secret** | Secrets stored in Azure Secret |
-When you add a credential parameter, you configure the source and connection details (collection ID, vault ID, etc.). At runtime, Skyvern fetches the real credentials from the vault and injects them into the workflow. Credential values are masked in logs and outputs.
+When you add a credential parameter, you configure the source and connection details (collection ID, vault ID, etc.). At runtime, Skyvern fetches the real credentials from the vault and injects them into the agent. Credential values are masked in logs and outputs.
---
@@ -150,15 +150,15 @@ Process item {{ current_index }}: {{ current_value.name }}
<Card
title="Block Reference"
icon="cube"
- href="/cloud/building-workflows/configure-blocks"
+ href="/cloud/building-agents/configure-blocks"
>
Configuration fields for every block type
</Card>
<Card
- title="Run Your Workflow"
+ title="Run Your Agent"
icon="play"
- href="/cloud/building-workflows/run-a-workflow"
+ href="/cloud/building-agents/run-an-agent"
>
- Execute workflows and fill in parameter values
+ Execute agents and fill in parameter values
</Card>
</CardGroup>
diff --git a/docs/cloud/building-workflows/build-a-workflow.mdx b/docs/cloud/building-agents/build-an-agent.mdx
similarity index 72%
rename from docs/cloud/building-workflows/build-a-workflow.mdx
rename to docs/cloud/building-agents/build-an-agent.mdx
index e52633ce9..6f4829552 100644
--- a/docs/cloud/building-workflows/build-a-workflow.mdx
+++ b/docs/cloud/building-agents/build-an-agent.mdx
@@ -1,10 +1,10 @@
---
-title: Build a Workflow
-subtitle: Create multi-step automations with the visual workflow editor
-description: Create multi-step browser automations in the Skyvern Cloud UI using the visual workflow editor with blocks for navigation, extraction, loops, conditionals, and email.
+title: Build an Agent
+subtitle: Create multi-step automations with the visual agent editor
+description: Create multi-step browser automations in the Skyvern Cloud UI using the visual agent editor with blocks for navigation, extraction, loops, conditionals, and email.
slug: cloud/build-a-workflow
keywords:
- - workflow editor
+ - agent editor
- drag and drop
- navigation block
- extract block
@@ -14,19 +14,19 @@ keywords:
- visual builder
---
-Workflows are multi-step automations built visually in the Cloud UI. You drag blocks onto a canvas, wire them together, configure each one, and run the whole sequence with a click. No code required. Workflows can be versioned, shared across your team, scheduled on a cron, and run with different parameters each time.
+Agents are multi-step automations built visually in the Cloud UI. You drag blocks onto a canvas, wire them together, configure each one, and run the whole sequence with a click. No code required. Agents can be versioned, shared across your team, scheduled on a cron, and run with different parameters each time.
-If you prefer writing automation code in Python or TypeScript, see [Browser Automation](/developers/browser-automations/overview) in the developer docs. Both approaches handle multi-step work across pages. Workflows are the visual path, browser automations are the code path.
+If you prefer writing automation code in Python or TypeScript, see [Browser Automation](/developers/browser-automations/overview) in the developer docs. Both approaches handle multi-step work across pages. Agents are the visual path, browser automations are the code path.
<Info>
-**Workflows vs. Browser Automation:** Workflows are defined in this visual editor and run from the Cloud UI (or [triggered from code](/cloud/building-workflows/run-from-code)). Browser automations are written in Python/TypeScript using Page, Agent, and Browser. Choose based on whether your team prefers a visual editor or a code editor.
+**Agents vs. Browser Automation:** Agents are defined in this visual editor and run from the Cloud UI (or [triggered from code](/cloud/building-agents/run-from-code)). Browser automations are written in Python/TypeScript using Page, Agent, and Browser. Choose based on whether your team prefers a visual editor or a code editor.
</Info>
-This page explains how workflows work, walks you through building one from scratch, and covers the editor's features.
+This page explains how agents work, walks you through building one from scratch, and covers the editor's features.
-## How workflows work
+## How agents work
-A workflow is a sequence of **blocks** that run one after another. Each block does one thing: navigate to a page, extract data, send an email, run custom code, loop, or branch. You connect blocks on a visual canvas, pass data between them, and run the whole chain with one click.
+An agent is a sequence of **blocks** that run one after another. Each block does one thing: navigate to a page, extract data, send an email, run custom code, loop, or branch. You connect blocks on a visual canvas, pass data between them, and run the whole chain with one click.
```
[Browser Task] → [Extraction] → [Loop] → [Send Email]
@@ -51,7 +51,7 @@ For example, an Extraction block labeled `scrape_listings` produces output that
| **Files** | Download and upload files | File Download, Cloud Storage Upload |
| **Communication** | Send data to external services or humans | Send Email, HTTP Request, Human Interaction |
-See [Block Reference](/cloud/building-workflows/configure-blocks) for every block type and its configuration fields.
+See [Block Reference](/cloud/building-agents/configure-blocks) for every block type and its configuration fields.
<Tip>
If your block needs a browser, pick a browser automation block. If it just needs to process data, use Text Prompt or Code. If you need to repeat or branch, use control flow.
@@ -61,18 +61,18 @@ If your block needs a browser, pick a browser automation block. If it just needs
## Tutorial: Build a job listing tracker
-Let's build a real workflow. You'll create an automation that finds the top 5 job listings from Hacker News's monthly "Who is Hiring" thread, summarizes each one, and emails you a digest.
+Let's build a real agent. You'll create an automation that finds the top 5 job listings from Hacker News's monthly "Who is Hiring" thread, summarizes each one, and emails you a digest.
This uses 5 blocks across 3 categories: browser automation, data and extraction, and communication.
<Steps>
- <Step title="Create a new workflow">
+ <Step title="Create a new agent">
- Go to **Workflows** in the left sidebar and click **Create → Blank Workflow**.
+ Go to **Agents** in the left sidebar and click **Create → Blank Agent**.
- <img src="/images/cloud/create-workflow-dropdown.png" alt="Create workflow dropdown showing Blank Workflow and From Template options" />
+ <img src="/images/cloud/create-workflow-dropdown.png" alt="Create agent dropdown showing Blank Agent and From Template options" />
- The editor opens with an empty canvas showing a single start node. Click the workflow title at the top left and rename it to **HN Job Tracker**.
+ The editor opens with an empty canvas showing a single start node. Click the agent title at the top left and rename it to **HN Job Tracker**.
</Step>
@@ -206,10 +206,10 @@ This uses 5 blocks across 3 categories: browser automation, data and extraction,
<Step title="Save and run">
<Warning>
- Workflows are **not** auto-saved. Click the **Save** button (disk icon) in the header bar before navigating away or you'll lose your work.
+ Agents are **not** auto-saved. Click the **Save** button (disk icon) in the header bar before navigating away or you'll lose your work.
</Warning>
- Click **Save**, then click **Run** in the top right. A parameters page opens where you can review and confirm the workflow's settings. Click **Run Workflow** to start execution.
+ Click **Save**, then click **Run** in the top right. A parameters page opens where you can review and confirm the agent's settings. Click **Run Agent** to start execution.
The [live execution view](/cloud/getting-started/monitor-a-run) opens. Watch as Skyvern navigates Hacker News, extracts listings, summarizes each one, and sends your email.
@@ -226,7 +226,7 @@ flowchart LR
D --> E["send_digest<br/>Send Email"]
```
-Five blocks, three categories, zero code. You can now re-run this workflow anytime, tweak the extraction schema to pull different fields, swap the email for an HTTP Request to post to Slack, or add a Conditional block to only email when listings match certain criteria.
+Five blocks, three categories, zero code. You can now re-run this agent anytime, tweak the extraction schema to pull different fields, swap the email for an HTTP Request to post to Slack, or add a Conditional block to only email when listings match certain criteria.
---
@@ -234,11 +234,11 @@ Five blocks, three categories, zero code. You can now re-run this workflow anyti
### Layout
-<img src="/images/cloud/workflow-editor-overview.png" alt="Workflow editor overview" />
+<img src="/images/cloud/workflow-editor-overview.png" alt="Agent editor overview" />
| Area | What it shows |
|------|---------------|
-| **Header bar** (top) | Workflow title (click to rename), Parameters button, Save button, Template toggle, History button, Run button |
+| **Header bar** (top) | Agent title (click to rename), Parameters button, Save button, Template toggle, History button, Run button |
| **Canvas** (center) | Visual graph of blocks connected in sequence. Zoom with the scroll wheel, pan by dragging the background. |
| **Configuration panel** (right) | Opens when you click a block. Shows that block's settings form. |
@@ -246,9 +246,9 @@ Five blocks, three categories, zero code. You can now re-run this workflow anyti
Hover over the **+** button on any edge (the connecting line between blocks) to reveal the menu. Select **Add Block** to open the block library, a searchable list of all available block types. Click a block to insert it at that position.
-The menu also offers **Record Browser** (record actions in a live browser to generate blocks) and **Upload SOP** (upload a PDF procedure to auto-generate a workflow).
+The menu also offers **Record Browser** (record actions in a live browser to generate blocks) and **Upload SOP** (upload a PDF procedure to auto-generate an agent).
-When you create a blank workflow, hover over the **+** on the start edge to add your first block.
+When you create a blank agent, hover over the **+** on the start edge to add your first block.
<img src="/images/cloud/add-block-panel.png" alt="Add block panel" />
@@ -256,7 +256,7 @@ When you create a blank workflow, hover over the **+** on the start edge to add
Click any block on the canvas to open its configuration panel on the right. Each block has a **Label** field (which determines its output variable name) and block-specific settings. Browser-based blocks share additional fields like URL, Engine, and Max Retries.
-See [Block Reference](/cloud/building-workflows/configure-blocks) for the full list of fields on each block type.
+See [Block Reference](/cloud/building-agents/configure-blocks) for the full list of fields on each block type.
### Connecting and reordering blocks
@@ -275,7 +275,7 @@ Click the **three-dot menu** on a block's header and select **Delete Block**. Do
### Saving
<Warning>
-Workflows are **not** auto-saved. Click the **Save** button (disk icon) in the header bar to persist your changes. The editor warns you if you try to navigate away with unsaved work.
+Agents are **not** auto-saved. Click the **Save** button (disk icon) in the header bar to persist your changes. The editor warns you if you try to navigate away with unsaved work.
</Warning>
The **Run** button also saves before starting execution.
@@ -284,12 +284,12 @@ The **Run** button also saves before starting execution.
| Button | Description |
|--------|-------------|
-| **Save** (disk icon) | Save the current workflow definition |
-| **Template** (bookmark icon) | Toggle whether this workflow is saved as an organization template |
-| **History** (clock icon) | View past runs of this workflow |
-| **Schedule** (clock icon) | Create or manage recurring schedules for this workflow (see [Create a Schedule](/cloud/building-workflows/scheduling)) |
-| **Parameters** | Open the parameters panel (see [Workflow Parameters](/cloud/building-workflows/add-parameters)) |
-| **Run** (play icon) | Save and start a new execution (see [Running Workflows](/cloud/building-workflows/run-a-workflow)) |
+| **Save** (disk icon) | Save the current agent definition |
+| **Template** (bookmark icon) | Toggle whether this agent is saved as an organization template |
+| **History** (clock icon) | View past runs of this agent |
+| **Schedule** (clock icon) | Create or manage recurring schedules for this agent (see [Create a Schedule](/cloud/building-agents/scheduling)) |
+| **Parameters** | Open the parameters panel (see [Agent Parameters](/cloud/building-agents/add-parameters)) |
+| **Run** (play icon) | Save and start a new execution (see [Running Agents](/cloud/building-agents/run-an-agent)) |
---
@@ -299,28 +299,28 @@ The **Run** button also saves before starting execution.
<Card
title="Block Reference"
icon="cube"
- href="/cloud/building-workflows/configure-blocks"
+ href="/cloud/building-agents/configure-blocks"
>
Configuration fields for every block type
</Card>
<Card
title="Add Parameters"
icon="sliders"
- href="/cloud/building-workflows/add-parameters"
+ href="/cloud/building-agents/add-parameters"
>
- Pass dynamic values into your workflows
+ Pass dynamic values into your agents
</Card>
<Card
- title="Run Your Workflow"
+ title="Run Your Agent"
icon="play"
- href="/cloud/building-workflows/run-a-workflow"
+ href="/cloud/building-agents/run-an-agent"
>
- Execute workflows and track results
+ Execute agents and track results
</Card>
<Card
- title="Schedule This Workflow"
+ title="Schedule This Agent"
icon="calendar"
- href="/cloud/building-workflows/scheduling"
+ href="/cloud/building-agents/scheduling"
>
Set up recurring cron-based execution
</Card>
diff --git a/docs/cloud/building-workflows/configure-blocks.mdx b/docs/cloud/building-agents/configure-blocks.mdx
similarity index 89%
rename from docs/cloud/building-workflows/configure-blocks.mdx
rename to docs/cloud/building-agents/configure-blocks.mdx
index 50629dea6..6e4ad8c5a 100644
--- a/docs/cloud/building-workflows/configure-blocks.mdx
+++ b/docs/cloud/building-agents/configure-blocks.mdx
@@ -1,7 +1,7 @@
---
title: Block Types and Configuration
-subtitle: Reference for every block available in the workflow editor
-description: Reference guide for every workflow block type in the Skyvern Cloud UI, including Browser Task, Extraction, Login, Loop, While Loop, Conditional, Code, HTTP Request, and more.
+subtitle: Reference for every block available in the agent editor
+description: Reference guide for every agent block type in the Skyvern Cloud UI, including Browser Task, Extraction, Login, Loop, While Loop, Conditional, Code, HTTP Request, and more.
slug: cloud/configure-blocks
keywords:
- navigation block
@@ -18,12 +18,12 @@ keywords:
- conditional block
---
-Workflows are built from blocks. Each block performs one specific operation: navigating a page, extracting data, making an API call, or branching logic. This page covers every block type available in the Cloud UI [workflow editor](/cloud/building-workflows/build-a-workflow), grouped by category.
+Agents are built from blocks. Each block performs one specific operation: navigating a page, extracting data, making an API call, or branching logic. This page covers every block type available in the Cloud UI [agent editor](/cloud/building-agents/build-an-agent), grouped by category.
If you're writing automations in code instead, the equivalent operations are Page and Agent methods. See the [Actions Reference](/developers/browser-automations/actions-reference) for the code-first counterparts to these blocks.
-<Frame caption="To add a block in your workflow, click the **+** button, click on Add block, then select the block type from the menu.">
-<img src="/images/cloud/add-block-ui.png" alt="how to add a block to a workflow in Skyvern" />
+<Frame caption="To add a block in your agent, click the **+** button, click on Add block, then select the block type from the menu.">
+<img src="/images/cloud/add-block-ui.png" alt="how to add a block to an agent in Skyvern" />
</Frame>
## Quick reference
@@ -45,7 +45,7 @@ These fields appear on most blocks:
| Field | Description |
|-------|-------------|
| **Label** | Display name on the canvas. Also determines how downstream blocks reference this block's output (`{{ label_output }}`). |
-| **Continue on Failure** | Allow the workflow to continue if this block fails |
+| **Continue on Failure** | Allow the agent to continue if this block fails |
| **Next Loop on Failure** | Only inside loops. Skip to the next iteration on failure. |
| **Model** | Override the default LLM model for this block (Advanced Settings on most blocks) |
@@ -69,7 +69,7 @@ Browser-based blocks (Browser Task, Browser Action, Extraction, Login, File Down
The primary block for browser automation. Accepts a natural-language prompt and autonomously navigates the browser to accomplish the goal.
-The block uses Skyvern 1.0 by default. Existing workflows that already contain V2 browser blocks remain editable and may show a reduced field set.
+The block uses Skyvern 1.0 by default. Existing agents that already contain V2 browser blocks remain editable and may show a reduced field set.
**Skyvern 1.0:**
@@ -167,7 +167,7 @@ Navigate the browser directly to a specific URL without AI interaction.
| Field | Type | Description |
|-------|------|-------------|
-| **URL** | text | **(Required)** The URL to navigate to. Supports [parameter references](/cloud/building-workflows/add-parameters#referencing-parameters-in-blocks). |
+| **URL** | text | **(Required)** The URL to navigate to. Supports [parameter references](/cloud/building-agents/add-parameters#referencing-parameters-in-blocks). |
<Frame>
<img width="400" src="/images/cloud/url_block.png" alt="Go to URL block configuration with URL field" />
@@ -239,7 +239,7 @@ Repeat a sequence of blocks for each item in a list. Child blocks are placed ins
| **Loop Value** | text | The list to iterate over. Use a parameter reference (e.g., `{{ my_list }}`) or a natural language description (e.g., "Extract links of the top 5 posts") which triggers automatic extraction. |
| **Continue if Empty** | boolean | Mark the loop as complete if the list is empty |
-Inside loop blocks, use these [reserved variables](/cloud/building-workflows/add-parameters#reserved-variables):
+Inside loop blocks, use these [reserved variables](/cloud/building-agents/add-parameters#reserved-variables):
- `{{ current_value }}`: the current item
- `{{ current_index }}`: the iteration number (0-based)
@@ -247,7 +247,7 @@ Inside loop blocks, use these [reserved variables](/cloud/building-workflows/add
<img width="400" src="/images/cloud/block-loop-config.png" alt="Loop block configuration" />
</Frame>
-Use Loop when the item list is already known before the loop starts, such as rows extracted from a table, files uploaded by a user, or URLs passed as workflow parameters.
+Use Loop when the item list is already known before the loop starts, such as rows extracted from a table, files uploaded by a user, or URLs passed as agent parameters.
### While Loop
@@ -257,14 +257,14 @@ Repeat a sequence of blocks while a condition remains true. Child blocks are pla
|-------|------|-------------|
| **Condition** | expression | Jinja2 template or natural-language prompt evaluated before each iteration |
-Inside while-loop blocks, use these [reserved variables](/cloud/building-workflows/add-parameters#reserved-variables):
+Inside while-loop blocks, use these [reserved variables](/cloud/building-agents/add-parameters#reserved-variables):
- `{{ current_index }}`: the iteration number (0-based)
Use While Loop for flows where the number of iterations is discovered during the run, such as pagination, polling, or retrying until a recoverable page state clears. For pagination, a common pattern is to extract a `has_next_page` boolean inside the loop, click Next, and let the next condition check decide whether to continue.
### Conditional
-Branch the workflow based on conditions. The UI shows branches as tabs (A, B, C, etc.). Each branch has an expression that determines when it executes. Expressions can be Jinja2 templates or natural language prompts.
+Branch the agent based on conditions. The UI shows branches as tabs (A, B, C, etc.). Each branch has an expression that determines when it executes. Expressions can be Jinja2 templates or natural language prompts.
| Field | Type | Description |
|-------|------|-------------|
@@ -282,7 +282,7 @@ Branch the workflow based on conditions. The UI shows branches as tabs (A, B, C,
### AI Validation
-Assert conditions using AI and halt the workflow on failure. Useful for checking that a previous block produced expected results before continuing.
+Assert conditions using AI and halt the agent on failure. Useful for checking that a previous block produced expected results before continuing.
| Field | Type | Description |
|-------|------|-------------|
@@ -315,7 +315,7 @@ Execute custom Python code. Input parameters are available as global variables.
### Wait
-Pause workflow execution for a specified duration.
+Pause agent execution for a specified duration.
| Field | Type | Description |
|-------|------|-------------|
@@ -397,7 +397,7 @@ Send an email notification, optionally with file attachments from previous block
|-------|------|-------------|
| **Recipients** | text | Comma-separated email addresses |
| **Subject** | text | Email subject line |
-| **Body** | text | Email body. Supports [parameter references](/cloud/building-workflows/add-parameters#referencing-parameters-in-blocks). |
+| **Body** | text | Email body. Supports [parameter references](/cloud/building-agents/add-parameters#referencing-parameters-in-blocks). |
| **File Attachments** | text | Path to files to attach |
<Frame>
@@ -422,7 +422,7 @@ Additional fields in **Advanced Settings:**
|-------|------|-------------|
| **Timeout** | number | Request timeout in seconds (1–300, default: 30) |
| **Follow Redirects** | boolean | Automatically follow HTTP redirects (default: true) |
-| **Continue on Failure** | boolean | Continue workflow if the request fails |
+| **Continue on Failure** | boolean | Continue agent if the request fails |
| **Save Response as File** | boolean | Save the response body as a downloadable file |
| **Download Filename** | text | Filename for the saved response (shown when Save Response as File is enabled) |
@@ -432,7 +432,7 @@ Additional fields in **Advanced Settings:**
### Human Interaction
-Pause the workflow and request human input. Optionally sends an email notification to reviewers.
+Pause the agent and request human input. Optionally sends an email notification to reviewers.
| Field | Type | Description |
|-------|------|-------------|
diff --git a/docs/cloud/building-agents/manage-agents.mdx b/docs/cloud/building-agents/manage-agents.mdx
new file mode 100644
index 000000000..5df0b4354
--- /dev/null
+++ b/docs/cloud/building-agents/manage-agents.mdx
@@ -0,0 +1,117 @@
+---
+title: Managing Agents
+subtitle: Create, organize, clone, import, and export reusable automations
+description: Organize, clone, import, export, and delete agents in the Skyvern Cloud UI, including folder management and template sharing across your organization.
+slug: cloud/manage-workflows
+keywords:
+ - clone
+ - import
+ - export
+ - delete
+ - folder
+ - template
+ - organize
+---
+
+Agents are multi-step automations built visually in the Cloud UI. Once you've [built an agent](/cloud/building-agents/build-an-agent), the **Agents** page is where you organize, share, and manage them. Each agent is a reusable sequence of blocks that you can run with different inputs each time.
+
+If you're building automations in code instead, see the [Browser Automation](/developers/browser-automations/overview) developer docs.
+
+Click **Agents** in the left sidebar to open it.
+
+<img src="/images/cloud/workflows-page-overview.png" alt="Agents page overview" />
+
+---
+
+## The agents table
+
+The table lists all agents in your organization with the following columns:
+
+| Column | Description |
+|--------|-------------|
+| **ID** | Unique agent identifier |
+| **Title** | Display name (click to open in the editor) |
+| **Folder** | Folder assignment, if any |
+| **Created At** | When the agent was created |
+| **Actions** | Inline buttons and three-dot menu |
+
+Each row also has inline action buttons: folder assignment, parameter toggle, open in editor (pencil icon), run (play icon), and a three-dot menu for additional actions.
+
+---
+
+## Organizing with folders
+
+The top of the page shows your recent folders as cards. Use folders to group related agents.
+
+- Click **+ New folder** to create one
+- Click a folder card to filter the table to that folder's agents
+- Assign an agent to a folder using the folder icon in the table row
+- Click **View all** to see all folders when you have more than five
+
+<img src="/images/cloud/workflow-folders.png" alt="Agent folders" />
+
+---
+
+## Searching and filtering
+
+Use the search bar above the table to filter agents by title or parameter. The results highlight matching text and auto-expand parameter rows when a parameter matches.
+
+The items-per-page selector at the bottom lets you choose 5, 10, 20, or 50 rows per page.
+
+---
+
+## Agent actions
+
+Click the **three-dot menu** on any agent row to access these actions:
+
+| Action | What it does |
+|--------|-------------|
+| **Clone Agent** | Creates a copy named "Copy of ..." with the original title |
+| **Save as Template** | Makes this agent available in the organization template gallery. A bookmark icon appears next to the title. |
+| **Remove from Templates** | Removes the agent from the template gallery (appears instead of "Save as Template" for templates) |
+| **Export as... > YAML** | Downloads the agent definition as a `.yaml` file |
+| **Export as... > JSON** | Downloads the agent definition as a `.json` file |
+| **Delete Agent** | Opens a confirmation dialog, then permanently deletes the agent |
+
+<img src="/images/cloud/workflow-actions-menu.png" alt="Agent actions menu" />
+
+<Warning>
+Deleting an agent is permanent. Clone it first if you want to keep a backup.
+</Warning>
+
+---
+
+## Importing agents
+
+Click the **Import** button to upload agent files.
+
+| Format | Behavior |
+|--------|----------|
+| `.yaml` / `.yml` | Parsed and created as a new agent |
+| `.json` | Converted to YAML internally, then created |
+| `.pdf` | Sent to the AI to generate an agent from a Standard Operating Procedure document |
+
+<Tip>
+Upload a PDF of your Standard Operating Procedure and Skyvern generates an agent from it automatically.
+</Tip>
+
+---
+
+## What's next
+
+<CardGroup cols={2}>
+ <Card
+ title="Open the Editor"
+ icon="pen-to-square"
+ href="/cloud/building-agents/build-an-agent"
+ >
+ Build automations visually with the agent editor
+ </Card>
+ <Card
+ title="Add Parameters"
+ icon="sliders"
+ href="/cloud/building-agents/add-parameters"
+ >
+ Make agents reusable with dynamic input values
+ </Card>
+</CardGroup>
diff --git a/docs/cloud/building-workflows/run-a-workflow.mdx b/docs/cloud/building-agents/run-an-agent.mdx
similarity index 58%
rename from docs/cloud/building-workflows/run-a-workflow.mdx
rename to docs/cloud/building-agents/run-an-agent.mdx
index 1e8dd4b50..8343100bd 100644
--- a/docs/cloud/building-workflows/run-a-workflow.mdx
+++ b/docs/cloud/building-agents/run-an-agent.mdx
@@ -1,7 +1,7 @@
---
-title: Running Workflows
-subtitle: Execute workflows, fill parameters, and track status
-description: Execute workflows from the Skyvern Cloud UI editor or workflows list, fill in runtime parameters, configure run settings like proxy and webhook, and monitor live execution.
+title: Running Agents
+subtitle: Execute agents, fill parameters, and track status
+description: Execute agents from the Skyvern Cloud UI editor or agents list, fill in runtime parameters, configure run settings like proxy and webhook, and monitor live execution.
slug: cloud/run-a-workflow
keywords:
- execute
@@ -14,30 +14,30 @@ keywords:
- live execution
---
-Once you've built and saved a workflow in the Cloud UI, you can run it from the editor or the workflows list. Each run creates an independent execution with its own status, logs, and output.
+Once you've built and saved an agent in the Cloud UI, you can run it from the editor or the agents list. Each run creates an independent execution with its own status, logs, and output.
-You can also trigger workflows programmatically from your code. See [Run from Code](/cloud/building-workflows/run-from-code) for the SDK and API approach.
+You can also trigger agents programmatically from your code. See [Run from Code](/cloud/building-agents/run-from-code) for the SDK and API approach.
## Starting a run
Two ways to start:
-1. **From the editor**: Click the **Run** button (play icon) in the header bar. The editor saves your workflow first.
+1. **From the editor**: Click the **Run** button (play icon) in the header bar. The editor saves your agent first.
-<img src="/images/cloud/run-wf-1.png" alt="Workflow editor with the Run button highlighted in the header bar" />
+<img src="/images/cloud/run-wf-1.png" alt="Agent editor with the Run button highlighted in the header bar" />
-2. **From the workflows list**: Click the **play icon** on the workflow's row.
+2. **From the agents list**: Click the **play icon** on the agent's row.
-<img src="/images/cloud/run-wf-2.png" alt="Workflows list page with play icon to start a run from the list" />
+<img src="/images/cloud/run-wf-2.png" alt="Agents list page with play icon to start a run from the list" />
Both take you to the parameters page where you fill in runtime values before the run starts.
## Filling in parameters
-The parameters page shows all [workflow parameters](/cloud/building-workflows/add-parameters) defined in the editor. Fill in a value for each one, or leave them at their defaults. Parameters without defaults must be filled in before running.
+The parameters page shows all [agent parameters](/cloud/building-agents/add-parameters) defined in the editor. Fill in a value for each one, or leave them at their defaults. Parameters without defaults must be filled in before running.
-<img src="/images/cloud/run-wf-3.png" alt="Parameters page showing input fields and settings before starting a workflow run" />
+<img src="/images/cloud/run-wf-3.png" alt="Parameters page showing input fields and settings before starting an agent run" />
## Run settings
@@ -64,9 +64,9 @@ Below the parameters, you can configure settings for this specific run:
After clicking **Run**, you're taken to the live execution view, the same interface described in [Watching Live Execution](/cloud/getting-started/monitor-a-run).
-For workflows, the left panel also shows a **block timeline**: a list of all blocks in the workflow. Completed blocks show a checkmark. The currently executing block is highlighted.
+For agents, the left panel also shows a **block timeline**: a list of all blocks in the agent. Completed blocks show a checkmark. The currently executing block is highlighted.
-<img src="/images/cloud/workflow-run-timeline.png" alt="Workflow run block timeline" />
+<img src="/images/cloud/workflow-run-timeline.png" alt="Agent run block timeline" />
---
@@ -78,7 +78,7 @@ For workflows, the left panel also shows a **block timeline**: a list of all blo
| `queued` | Waiting for an available browser |
| `running` | Blocks are executing |
| `completed` | All blocks finished successfully |
-| `failed` | A block failed and the workflow stopped |
+| `failed` | A block failed and the agent stopped |
| `canceled` | You canceled the run |
| `timed_out` | The run exceeded its time limit |
| `terminated` | The run was terminated by the system |
@@ -93,7 +93,7 @@ After a run completes, open it from **Runs** in the sidebar. The run detail page
- **Recording**: Full video replay of the browser session
- **Parameters**: The values you submitted for this run
-<img src="/images/cloud/run-wf-8.png" alt="Completed workflow run showing extracted data, output tabs, and block timeline" />
+<img src="/images/cloud/run-wf-8.png" alt="Completed agent run showing extracted data, output tabs, and block timeline" />
See [Reviewing results](/cloud/getting-started/monitor-a-run#reviewing-results) for details on the Actions, Recording, Parameters, and Diagnostics tabs.
@@ -109,10 +109,10 @@ Click the **Cancel** button during execution. A confirmation dialog appears. The
Access past runs from two places:
-1. **Runs** in the left sidebar: shows all runs across all workflows
+1. **Runs** in the left sidebar: shows all runs across all agents
<img src="/images/cloud/run-wf-4.png" alt="Run History page in the sidebar showing all past runs with status and duration" />
-2. Go to the **History** button (clock icon) in the workflow editor: shows runs for this specific workflow
-<img src="/images/cloud/run-wf-5.png" alt="Past Runs view for a specific workflow showing run statuses and timestamps" />
+2. Go to the **History** button (clock icon) in the agent editor: shows runs for this specific agent
+<img src="/images/cloud/run-wf-5.png" alt="Past Runs view for a specific agent showing run statuses and timestamps" />
---
@@ -121,16 +121,16 @@ Access past runs from two places:
<CardGroup cols={2}>
<Card
- title="Build a Workflow"
+ title="Build an Agent"
icon="pen-to-square"
- href="/cloud/building-workflows/build-a-workflow"
+ href="/cloud/building-agents/build-an-agent"
>
- Create and edit workflows in the visual editor
+ Create and edit agents in the visual editor
</Card>
<Card
title="Block Reference"
icon="cube"
- href="/cloud/building-workflows/configure-blocks"
+ href="/cloud/building-agents/configure-blocks"
>
Configuration fields for every block type
</Card>
diff --git a/docs/cloud/building-workflows/run-from-code.mdx b/docs/cloud/building-agents/run-from-code.mdx
similarity index 84%
rename from docs/cloud/building-workflows/run-from-code.mdx
rename to docs/cloud/building-agents/run-from-code.mdx
index 301bd529f..6197ea00c 100644
--- a/docs/cloud/building-workflows/run-from-code.mdx
+++ b/docs/cloud/building-agents/run-from-code.mdx
@@ -1,8 +1,8 @@
---
title: Run from Code
-subtitle: Execute and schedule workflows via the API or SDK
-description: Run workflows programmatically, pass parameters, poll for results, and create recurring schedules using the Python SDK, TypeScript SDK, or REST API.
-slug: cloud/building-workflows/run-from-code
+subtitle: Execute and schedule agents via the API or SDK
+description: Run agents programmatically, pass parameters, poll for results, and create recurring schedules using the Python SDK, TypeScript SDK, or REST API.
+slug: cloud/building-agents/run-from-code
keywords:
- run_workflow
- get_run
@@ -15,15 +15,15 @@ keywords:
- API
---
-If you've built a workflow in the Cloud UI and want to trigger it from your codebase, this page shows how. You can run workflows on demand, poll for results, and set up recurring schedules using the Python SDK, TypeScript SDK, or REST API.
+If you've built an agent in the Cloud UI and want to trigger it from your codebase, this page shows how. You can run agents on demand, poll for results, and set up recurring schedules using the Python SDK, TypeScript SDK, or REST API.
-This is for workflows defined in the visual editor. If you're writing your entire automation in code (no workflow editor involved), see [Browser Automation](/developers/browser-automations/overview) instead.
+This is for agents defined in the visual editor. If you're writing your entire automation in code (no agent editor involved), see [Browser Automation](/developers/browser-automations/overview) instead.
---
-## Run a workflow
+## Run an agent
-Pass values for the workflow's input parameters. The call returns immediately with a `run_id` -- the workflow runs asynchronously in the background.
+Pass values for the agent's input parameters. The call returns immediately with a `run_id` -- the agent runs asynchronously in the background.
<CodeGroup>
```python Python
@@ -98,11 +98,11 @@ curl -X POST "https://api.skyvern.com/v1/run/workflows" \
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
-| `workflow_id` | string | Yes | The `workflow_permanent_id` returned when creating the workflow |
-| `parameters` | object | No | Values for the workflow's input parameters. Keys must match the `key` field in the workflow's parameter definitions |
+| `workflow_id` | string | Yes | The `workflow_permanent_id` returned when creating the agent |
+| `parameters` | object | No | Values for the agent's input parameters. Keys must match the `key` field in the agent's parameter definitions |
| `title` | string | No | Display name for this specific run |
-| `proxy_location` | string or object | No | Override the workflow's default proxy location |
-| `webhook_url` | string | No | URL to receive a POST request when the workflow completes |
+| `proxy_location` | string or object | No | Override the agent's default proxy location |
+| `webhook_url` | string | No | URL to receive a POST request when the agent completes |
| `browser_session_id` | string | No | Reuse a persistent browser session (prefix `pbs_`) |
| `browser_profile_id` | string | No | Reuse a browser profile with saved cookies and storage (prefix `bp_`) |
@@ -110,7 +110,7 @@ curl -X POST "https://api.skyvern.com/v1/run/workflows" \
## Get results
-Workflows run asynchronously, so you need to check back for results. You have two options: poll the API, or receive a webhook when the workflow completes.
+Agents run asynchronously, so you need to check back for results. You have two options: poll the API, or receive a webhook when the agent completes.
### Option 1: Polling
@@ -171,7 +171,7 @@ done
### Option 2: Webhooks
-Pass a `webhook_url` when running the workflow. Skyvern sends a POST request to your URL when the workflow reaches a terminal state.
+Pass a `webhook_url` when running the agent. Skyvern sends a POST request to your URL when the agent reaches a terminal state.
<CodeGroup>
```python Python
@@ -262,9 +262,9 @@ The webhook payload contains the same data as the polling response. See [Webhook
---
-## Schedule a workflow
+## Schedule an agent
-Schedules let you run any workflow automatically on a recurring basis. Define a cron expression and timezone, and Skyvern triggers the workflow at each interval.
+Schedules let you run any agent automatically on a recurring basis. Define a cron expression and timezone, and Skyvern triggers the agent at each interval.
### Create a schedule
@@ -319,7 +319,7 @@ curl -X POST "https://api.skyvern.com/api/v1/workflows/wpid_123456789/schedules"
| `timezone` | string | Yes | IANA timezone identifier (e.g., `America/New_York`) |
| `name` | string | No | Human-readable name for the schedule |
| `description` | string | No | Description of what this schedule does |
-| `parameters` | object | No | Workflow parameters to pass on each run |
+| `parameters` | object | No | Agent parameters to pass on each run |
| `enabled` | boolean | No | Whether the schedule is active. Defaults to `true` |
### Enable and disable a schedule
@@ -370,9 +370,9 @@ curl -X DELETE "https://api.skyvern.com/api/v1/workflows/wpid_123456789/schedule
---
-## List workflows
+## List agents
-Retrieve all workflows in your organization.
+Retrieve all agents in your organization.
<CodeGroup>
```python Python
diff --git a/docs/cloud/building-workflows/scheduling.mdx b/docs/cloud/building-agents/scheduling.mdx
similarity index 65%
rename from docs/cloud/building-workflows/scheduling.mdx
rename to docs/cloud/building-agents/scheduling.mdx
index c0b8bf9b2..5dbf38a21 100644
--- a/docs/cloud/building-workflows/scheduling.mdx
+++ b/docs/cloud/building-agents/scheduling.mdx
@@ -1,7 +1,7 @@
---
-title: Schedule a Workflow
+title: Schedule an Agent
subtitle: Set up recurring cron-based execution from the UI
-description: Set up recurring cron-based workflow schedules in the Skyvern Cloud UI, including creating, editing, pausing, and deleting schedules with timezone support.
+description: Set up recurring cron-based agent schedules in the Skyvern Cloud UI, including creating, editing, pausing, and deleting schedules with timezone support.
slug: cloud/scheduling
keywords:
- schedule
@@ -14,16 +14,16 @@ keywords:
- disable
---
-You can schedule any workflow built in the Cloud UI to run automatically on a recurring basis. Schedules are configured with a cron expression and timezone, and Skyvern triggers the workflow at each interval.
+You can schedule any agent built in the Cloud UI to run automatically on a recurring basis. Schedules are configured with a cron expression and timezone, and Skyvern triggers the agent at each interval.
-This page covers scheduling through the Cloud UI. You can also create schedules programmatically via the SDK or API. See [Run from Code](/cloud/building-workflows/run-from-code) for the code approach.
+This page covers scheduling through the Cloud UI. You can also create schedules programmatically via the SDK or API. See [Run from Code](/cloud/building-agents/run-from-code) for the code approach.
Schedules are created as **active** by default: they start triggering runs immediately after creation.
When creating a schedule you'll fill in these fields:
-- **Workflow** (required): The workflow to run. When creating from the workflow editor this is pre-selected.
-- **Cron Expression** (required): A standard 5-field cron expression that defines how often the workflow runs (e.g., `0 9 * * 1-5` for every weekday at 9 AM). The UI validates the expression in real time and shows a human-readable translation. Quick presets are available for common patterns like hourly, daily, and weekly.
+- **Agent** (required): The agent to run. When creating from the agent editor this is pre-selected.
+- **Cron Expression** (required): A standard 5-field cron expression that defines how often the agent runs (e.g., `0 9 * * 1-5` for every weekday at 9 AM). The UI validates the expression in real time and shows a human-readable translation. Quick presets are available for common patterns like hourly, daily, and weekly.
- **Timezone** (required): The IANA timezone the cron expression is evaluated in (e.g., `America/New_York`). Defaults to your browser's local timezone. The dropdown is searchable by city name.
- **Name**: A human-readable label to identify this schedule in the table and run history.
- **Description**: Optional notes about what this schedule does or why it exists.
@@ -46,10 +46,10 @@ The minimum interval between runs is **5 minutes**. Expressions that resolve to
Click <kbd>Create Schedule</kbd> in the top right corner.
<img src="/images/cloud/create-schedule-button.png" alt="Schedules page with Create Schedule button in the top right corner" />
</Step>
- <Step title="Select a workflow and configure the schedule">
- Choose the workflow you want to schedule from the dropdown. Only saved workflows appear in this list. Then fill in the cron expression, timezone, and optionally a name and description. Check the **Next Scheduled Runs** preview to verify the upcoming execution times match your expectations.
+ <Step title="Select an agent and configure the schedule">
+ Choose the agent you want to schedule from the dropdown. Only saved agents appear in this list. Then fill in the cron expression, timezone, and optionally a name and description. Check the **Next Scheduled Runs** preview to verify the upcoming execution times match your expectations.
<Frame>
- <img src="/images/cloud/create-sched-form.png" alt="Schedule creation form with workflow dropdown, cron expression, timezone, name, and description fields" width="300" />
+ <img src="/images/cloud/create-sched-form.png" alt="Schedule creation form with agent dropdown, cron expression, timezone, name, and description fields" width="300" />
</Frame>
</Step>
<Step title="Create">
@@ -57,17 +57,17 @@ The minimum interval between runs is **5 minutes**. Expressions that resolve to
</Step>
</Steps>
</Tab>
- <Tab title="From the workflow editor">
+ <Tab title="From the agent editor">
<Steps>
- <Step title="Open the workflow">
- Navigate to [**Workflows**](https://app.skyvern.com/workflows/) in the sidebar and click the workflow you want to schedule.
+ <Step title="Open the agent">
+ Navigate to [**Agents**](https://app.skyvern.com/workflows/) in the sidebar and click the agent you want to schedule.
</Step>
<Step title="Click the Schedule button">
In the editor header bar, click the <kbd>Schedule</kbd> button (clock icon).
- <img src="/images/cloud/wf-page-sched.png" alt="Workflow editor page with Schedule button (clock icon) in the header bar" />
+ <img src="/images/cloud/wf-page-sched.png" alt="Agent editor page with Schedule button (clock icon) in the header bar" />
</Step>
<Step title="Click Add and configure the schedule">
- A panel opens showing any existing schedules for this workflow. Click <kbd>Add</kbd> to create a new one. Fill in the cron expression, timezone, and optionally a name and description. The workflow is already selected.
+ A panel opens showing any existing schedules for this agent. Click <kbd>Add</kbd> to create a new one. Fill in the cron expression, timezone, and optionally a name and description. The agent is already selected.
<Frame>
<img src="/images/cloud/create-sched-form.png" alt="Schedule creation form with cron expression, timezone, name, and description fields" width="300" />
</Frame>
@@ -83,19 +83,19 @@ The minimum interval between runs is **5 minutes**. Expressions that resolve to
## The Schedules page
-Click **Schedules** in the left sidebar to see every schedule across all workflows.
+Click **Schedules** in the left sidebar to see every schedule across all agents.
Each row shows:
| Column | What it shows |
|--------|--------------|
-| **Workflow** | The workflow this schedule triggers |
+| **Agent** | The agent this schedule triggers |
| **Name** | Schedule name |
| **Schedule** | Human-readable cron description (e.g., "Every weekday at 9:00 AM") |
| **Next Run** | Next execution time in your local timezone |
| **Status** | **Active** (green) or **Paused** (gray) |
-Use the search bar to filter by schedule name or workflow title. The status filter narrows to Active or Paused schedules.
+Use the search bar to filter by schedule name or agent title. The status filter narrows to Active or Paused schedules.
---
@@ -114,7 +114,7 @@ On this page, you can:
- **Delete the schedule**: Use the delete button (trash icon) in the header. Deletion is permanent. Runs already triggered by the schedule are not affected.
<Info>
-To change which workflow a schedule runs, delete the schedule and create a new one for the target workflow.
+To change which agent a schedule runs, delete the schedule and create a new one for the target agent.
</Info>
---
@@ -125,7 +125,7 @@ To change which workflow a schedule runs, delete the schedule and create a new o
<Card
title="Scheduling API"
icon="code"
- href="/cloud/building-workflows/run-from-code#create-a-schedule"
+ href="/cloud/building-agents/run-from-code#create-a-schedule"
>
Create and manage schedules programmatically
</Card>
diff --git a/docs/cloud/building-workflows/manage-workflows.mdx b/docs/cloud/building-workflows/manage-workflows.mdx
deleted file mode 100644
index fce56ae1a..000000000
--- a/docs/cloud/building-workflows/manage-workflows.mdx
+++ /dev/null
@@ -1,117 +0,0 @@
----
-title: Managing Workflows
-subtitle: Create, organize, clone, import, and export reusable automations
-description: Organize, clone, import, export, and delete workflows in the Skyvern Cloud UI, including folder management and template sharing across your organization.
-slug: cloud/manage-workflows
-keywords:
- - clone
- - import
- - export
- - delete
- - folder
- - template
- - organize
----
-
-Workflows are multi-step automations built visually in the Cloud UI. Once you've [built a workflow](/cloud/building-workflows/build-a-workflow), the **Workflows** page is where you organize, share, and manage them. Each workflow is a reusable sequence of blocks that you can run with different inputs each time.
-
-If you're building automations in code instead, see the [Browser Automation](/developers/browser-automations/overview) developer docs.
-
-Click **Workflows** in the left sidebar to open it.
-
-<img src="/images/cloud/workflows-page-overview.png" alt="Workflows page overview" />
-
----
-
-## The workflows table
-
-The table lists all workflows in your organization with the following columns:
-
-| Column | Description |
-|--------|-------------|
-| **ID** | Unique workflow identifier |
-| **Title** | Display name (click to open in the editor) |
-| **Folder** | Folder assignment, if any |
-| **Created At** | When the workflow was created |
-| **Actions** | Inline buttons and three-dot menu |
-
-Each row also has inline action buttons: folder assignment, parameter toggle, open in editor (pencil icon), run (play icon), and a three-dot menu for additional actions.
-
----
-
-## Organizing with folders
-
-The top of the page shows your recent folders as cards. Use folders to group related workflows.
-
-- Click **+ New folder** to create one
-- Click a folder card to filter the table to that folder's workflows
-- Assign a workflow to a folder using the folder icon in the table row
-- Click **View all** to see all folders when you have more than five
-
-<img src="/images/cloud/workflow-folders.png" alt="Workflow folders" />
-
----
-
-## Searching and filtering
-
-Use the search bar above the table to filter workflows by title or parameter. The results highlight matching text and auto-expand parameter rows when a parameter matches.
-
-The items-per-page selector at the bottom lets you choose 5, 10, 20, or 50 rows per page.
-
----
-
-## Workflow actions
-
-Click the **three-dot menu** on any workflow row to access these actions:
-
-| Action | What it does |
-|--------|-------------|
-| **Clone Workflow** | Creates a copy named "Copy of ..." with the original title |
-| **Save as Template** | Makes this workflow available in the organization template gallery. A bookmark icon appears next to the title. |
-| **Remove from Templates** | Removes the workflow from the template gallery (appears instead of "Save as Template" for templates) |
-| **Export as... > YAML** | Downloads the workflow definition as a `.yaml` file |
-| **Export as... > JSON** | Downloads the workflow definition as a `.json` file |
-| **Delete Workflow** | Opens a confirmation dialog, then permanently deletes the workflow |
-
-<img src="/images/cloud/workflow-actions-menu.png" alt="Workflow actions menu" />
-
-<Warning>
-Deleting a workflow is permanent. Clone it first if you want to keep a backup.
-</Warning>
-
----
-
-## Importing workflows
-
-Click the **Import** button to upload workflow files.
-
-| Format | Behavior |
-|--------|----------|
-| `.yaml` / `.yml` | Parsed and created as a new workflow |
-| `.json` | Converted to YAML internally, then created |
-| `.pdf` | Sent to the AI to generate a workflow from a Standard Operating Procedure document |
-
-<Tip>
-Upload a PDF of your Standard Operating Procedure and Skyvern generates a workflow from it automatically.
-</Tip>
-
----
-
-## What's next
-
-<CardGroup cols={2}>
- <Card
- title="Open the Editor"
- icon="pen-to-square"
- href="/cloud/building-workflows/build-a-workflow"
- >
- Build automations visually with the workflow editor
- </Card>
- <Card
- title="Add Parameters"
- icon="sliders"
- href="/cloud/building-workflows/add-parameters"
- >
- Make workflows reusable with dynamic input values
- </Card>
-</CardGroup>
diff --git a/docs/cloud/getting-started/core-concepts.mdx b/docs/cloud/getting-started/core-concepts.mdx
index e88937849..d673bd27e 100644
--- a/docs/cloud/getting-started/core-concepts.mdx
+++ b/docs/cloud/getting-started/core-concepts.mdx
@@ -1,11 +1,11 @@
---
title: Core Concepts
subtitle: The building blocks of every automation in the Skyvern dashboard
-description: Understand tasks, workflows, blocks, runs, browser sessions, browser profiles, and credentials in the Skyvern Cloud UI — what each is, where to find it, and how it fits together.
+description: Understand tasks, agents, blocks, runs, browser sessions, browser profiles, and credentials in the Skyvern Cloud UI — what each is, where to find it, and how it fits together.
slug: cloud/getting-started/core-concepts
keywords:
- task
- - workflow
+ - agent
- block
- browser session
- browser profile
@@ -29,9 +29,9 @@ You create tasks from the **Discover** page. Type your prompt and target URL int
<img src="/images/cloud/discover-page-overview.png" alt="Discover page where you create one-off tasks" />
-Tasks are the right starting point for one-off automations, ad-hoc data extraction, or quickly testing whether an idea is feasible before turning it into a workflow.
+Tasks are the right starting point for one-off automations, ad-hoc data extraction, or quickly testing whether an idea is feasible before turning it into an agent.
-When you outgrow a single task — you need parameters, branching, loops, or to run the same flow on a schedule — graduate to a Workflow.
+When you outgrow a single task — you need parameters, branching, loops, or to run the same flow on a schedule — graduate to an Agent.
<Card title="Run a task →" icon="play" href="/cloud/getting-started/run-a-task">
Walkthrough of every option on the Discover page.
@@ -39,22 +39,22 @@ When you outgrow a single task — you need parameters, branching, loops, or to
---
-## Workflows
+## Agents
-A **Workflow** is a reusable automation built by chaining blocks together on a visual canvas. Workflows are versioned, parameterized, and shareable across your team.
+An **Agent** is a reusable automation built by chaining blocks together on a visual canvas. Agents are versioned, parameterized, and shareable across your team.
-You build them on the **Workflows** page. Click any workflow to open the editor, where blocks appear as connected nodes you can drag and configure.
+You build them on the **Agents** page. Click any agent to open the editor, where blocks appear as connected nodes you can drag and configure.
-<img src="/images/cloud/workflow-editor-overview.png" alt="Workflow editor with blocks chained together" />
+<img src="/images/cloud/workflow-editor-overview.png" alt="Agent editor with blocks chained together" />
-Use a workflow when:
+Use an agent when:
- The same flow needs to run repeatedly with different inputs
- You need to loop over a list, branch on a condition, or pass data between steps
- You want to schedule the automation to run on a cadence
- You want a teammate to be able to re-run it without re-deriving the logic
-<Card title="Build a workflow →" icon="diagram-project" href="/cloud/building-workflows/build-a-workflow">
+<Card title="Build an agent →" icon="diagram-project" href="/cloud/building-agents/build-an-agent">
Tutorial covering blocks, parameters, branching, and execution.
</Card>
@@ -62,9 +62,9 @@ Use a workflow when:
## Blocks
-**Blocks** are the units a workflow is built from. Each block performs one thing — navigate, log in, extract data, branch on a condition, send an email — and passes its output to the next block.
+**Blocks** are the units an agent is built from. Each block performs one thing — navigate, log in, extract data, branch on a condition, send an email — and passes its output to the next block.
-In the workflow editor, click the **+** button on any node to insert a new block. The picker groups every available block by category.
+In the agent editor, click the **+** button on any node to insert a new block. The picker groups every available block by category.
<img src="/images/cloud/add-block-panel.png" alt="Block picker with categories and block types" />
@@ -76,13 +76,13 @@ There are 20+ block types organized into:
- **Files** — File Download, Cloud Storage Upload
- **Communication** — Send Email, HTTP Request, Human Interaction
-Each block has its own configuration panel. The full reference, with every field for every block, lives at [Workflow Blocks](/cloud/building-workflows/configure-blocks).
+Each block has its own configuration panel. The full reference, with every field for every block, lives at [Agent Blocks](/cloud/building-agents/configure-blocks).
---
## Runs
-Every time a task or workflow executes, Skyvern creates a **Run** — a record of what happened, with a video, screenshots, action log, and any extracted data.
+Every time a task or agent executes, Skyvern creates a **Run** — a record of what happened, with a video, screenshots, action log, and any extracted data.
The **Runs** page is your history. Filter by status, search by run ID, click any row to drill in.
@@ -168,9 +168,9 @@ You can also sync credentials from **Bitwarden**, **1Password**, or **Azure Key
## Schedules
-A **schedule** runs a workflow automatically on a recurring cadence. You set a cron expression and timezone, and Skyvern fires the workflow at every interval — no manual trigger needed.
+A **schedule** runs an agent automatically on a recurring cadence. You set a cron expression and timezone, and Skyvern fires the agent at every interval — no manual trigger needed.
-Schedules are configured per workflow. Open any workflow's actions menu and choose **Schedule**.
+Schedules are configured per agent. Open any agent's actions menu and choose **Schedule**.
<Frame>
<img src="/images/cloud/create-sched-form.png" alt="Schedule form with cron expression and timezone" width="300" />
@@ -178,7 +178,7 @@ Schedules are configured per workflow. Open any workflow's actions menu and choo
Use schedules for daily reports, hourly monitoring, periodic data syncs, or anything that should "just keep running" without you remembering to click Run.
-<Card title="Scheduling →" icon="calendar" href="/cloud/building-workflows/scheduling">
+<Card title="Scheduling →" icon="calendar" href="/cloud/building-agents/scheduling">
Cron syntax, timezones, and managing scheduled runs.
</Card>
@@ -188,17 +188,17 @@ Use schedules for daily reports, hourly monitoring, periodic data syncs, or anyt
An **engine** is the AI model Skyvern uses to drive the browser. Different engines have different strengths — speed, accuracy on complex pages, cost — and you can pick one per task or per block.
-The engine picker appears in API/SDK task requests and on supported browser-driven blocks in the workflow editor.
+The engine picker appears in API/SDK task requests and on supported browser-driven blocks in the agent editor.
| Engine | When to use |
|--------|-------------|
| **Skyvern 1.0** | Default for new tasks. Lighter and faster for simple, single-page interactions. |
-| **Skyvern 2.0** | Available for existing V2 workflows and explicitly requested V2 task runs. |
+| **Skyvern 2.0** | Available for existing V2 agents and explicitly requested V2 task runs. |
| **OpenAI CUA** | OpenAI's Computer Use Agent. Good for visual reasoning. |
| **Anthropic CUA** | Anthropic's Claude Computer Use. Strong at multi-step planning. |
| **UI-TARS** | Lightweight CUA model option. |
-If you're not sure, use the default. Move repeated automations into workflows when you need scheduling, reusable parameters, or cached code replays.
+If you're not sure, use the default. Move repeated automations into agents when you need scheduling, reusable parameters, or cached code replays.
---
@@ -221,7 +221,7 @@ flowchart LR
A typical day in the dashboard:
1. **Prototype** with a Task on the Discover page. Iterate on the prompt until it works.
-2. **Productionize** by turning the prompt into a Workflow with Blocks, Parameters, and a Schedule.
+2. **Productionize** by turning the prompt into an Agent with Blocks, Parameters, and a Schedule.
3. **Persist state** by saving a Browser Profile after the first authenticated run, so future runs skip login.
4. **Audit** every execution on the Runs page — recording, actions, output, downloaded files.
@@ -238,9 +238,9 @@ A typical day in the dashboard:
Hands-on tutorial — go from prompt to extracted data in a few minutes.
</Card>
<Card
- title="Build a Workflow"
+ title="Build an Agent"
icon="diagram-project"
- href="/cloud/building-workflows/build-a-workflow"
+ href="/cloud/building-agents/build-an-agent"
>
Wire blocks together into a reusable, parameterized automation.
</Card>
diff --git a/docs/cloud/getting-started/overview.mdx b/docs/cloud/getting-started/overview.mdx
index 93e73d12b..b0c2aac72 100644
--- a/docs/cloud/getting-started/overview.mdx
+++ b/docs/cloud/getting-started/overview.mdx
@@ -9,7 +9,7 @@ keywords:
- sidebar
- settings
- runs page
- - workflows page
+ - agents page
- run
---
@@ -38,8 +38,8 @@ Where you create and monitor automations.
| Page | Purpose |
|------|---------|
| **Discover** | Run one-off tasks. Type your instructions and target URL into a single prompt, pick an engine, and hit send. |
-| **Workflows** | Build multi-step automations with the visual workflow editor. Add loops, conditionals, and data passing between steps. |
-| **Runs** | Execution history for every task and workflow. Filter by status, drill into any run to see actions, recordings, and extracted data. |
+| **Agents** | Build multi-step automations with the visual agent editor. Add loops, conditionals, and data passing between steps. |
+| **Runs** | Execution history for every task and agent. Filter by status, drill into any run to see actions, recordings, and extracted data. |
| **Browsers** | Active [browser sessions](/cloud/browser-management/browser-sessions). Keep a browser open across multiple tasks to preserve login state, cookies, and page context. Load a [browser profile](/cloud/browser-management/browser-profiles) to restore previously saved state. |
### Agents
@@ -51,7 +51,7 @@ Ready-made automation templates. Each agent is preconfigured with a prompt, targ
| Page | Purpose |
|------|---------|
| **Billing** | Usage, remaining credits, and plan management. |
-| **Credentials** | Store website logins, credit card details, and secret values securely. Skyvern uses these to authenticate automatically, fill payment forms, and inject secrets into workflows. |
+| **Credentials** | Store website logins, credit card details, and secret values securely. Skyvern uses these to authenticate automatically, fill payment forms, and inject secrets into agents. |
| **Settings** | API key, account preferences, and organization management. |
## How it works
@@ -89,6 +89,6 @@ That's it. The next guide walks you through this flow with a real example.
icon="book"
href="/developers/getting-started/core-concepts"
>
- Understand tasks, workflows, and other foundational concepts
+ Understand tasks, agents, and other foundational concepts
</Card>
</CardGroup>
diff --git a/docs/cloud/getting-started/run-a-task.mdx b/docs/cloud/getting-started/run-a-task.mdx
index a6c45e58d..405abfe80 100644
--- a/docs/cloud/getting-started/run-a-task.mdx
+++ b/docs/cloud/getting-started/run-a-task.mdx
@@ -48,7 +48,7 @@ New tasks created from the Discover page use the default Skyvern 1.0 task engine
| **Anthropic CUA** | Computer-use tasks powered by Anthropic's Claude model |
<Tip>
-Start with the default. Move repeated automations into workflows when you need scheduling, reusable parameters, or cached code replays.
+Start with the default. Move repeated automations into agents when you need scheduling, reusable parameters, or cached code replays.
</Tip>
---
@@ -67,7 +67,7 @@ Click the **gear icon** next to the prompt box to expand the settings panel.
| **CDP Address** | Connect to your own browser via Chrome DevTools Protocol (e.g., `http://127.0.0.1:9222`). For local development. |
| **2FA Identifier** | Links your TOTP credentials to this task. Skyvern uses it to retrieve the correct code when a 2FA prompt appears. |
| **Extra HTTP Headers** | Custom headers sent with every browser request, as JSON (e.g., `{"Authorization": "Bearer token"}`). |
-| **Publish Workflow** | Save a reusable workflow alongside the task run. Re-run the same automation later from the Workflows page. |
+| **Publish Agent** | Save a reusable agent alongside the task run. Re-run the same automation later from the Agents page. |
| **Max Steps Override** | Cap the number of AI reasoning steps. Each step = one screenshot-analyze-act cycle. Useful for controlling cost during development. |
| **Max Screenshot Scrolls** | Number of scrolls for post-action screenshots. Increase for pages with lazy-loaded content. `0` = viewport only. |
@@ -135,11 +135,11 @@ Use the `description` field on each property to guide the AI on what to extract.
---
-## Workflow templates
+## Agent templates
-Below the prompt box, the Discover page shows a gallery of **workflow templates**: pre-built automations for common use cases.
+Below the prompt box, the Discover page shows a gallery of **agent templates**: pre-built automations for common use cases.
-<img src="/images/cloud/workflow-templates.png" alt="Workflow template gallery" />
+<img src="/images/cloud/workflow-templates.png" alt="Agent template gallery" />
Click any template to launch it with pre-filled configuration, or use it as a starting point and customize.
@@ -186,10 +186,10 @@ Click any template to launch it with pre-filled configuration, or use it as a st
Monitor runs, take control of the browser, and review results
</Card>
<Card
- title="Build a Workflow"
+ title="Build an Agent"
icon="diagram-project"
- href="/cloud/building-workflows/build-a-workflow"
+ href="/cloud/building-agents/build-an-agent"
>
- Turn a successful task into a reusable multi-step workflow
+ Turn a successful task into a reusable multi-step agent
</Card>
</CardGroup>
diff --git a/docs/cloud/getting-started/run-your-first-task.mdx b/docs/cloud/getting-started/run-your-first-task.mdx
index 4644a580b..fb530d5a8 100644
--- a/docs/cloud/getting-started/run-your-first-task.mdx
+++ b/docs/cloud/getting-started/run-your-first-task.mdx
@@ -34,9 +34,9 @@ Below the input, you'll see quick-action chips like "Add a product to cart" and
The more specific your prompt, the better. "Get the title of the #1 post" works much better than "get some data." Include the exact fields you want, what success looks like, and any constraints.
</Tip>
-## Step 2: Create and run the workflow
+## Step 2: Create and run the agent
-Click the **send button** (arrow icon to the right of the input). Skyvern generates a workflow from your prompt using the default Skyvern 1.0 task engine and opens it in the workflow editor. Click **Run** in the top right, confirm the parameters, then click **Run workflow** to start execution.
+Click the **send button** (arrow icon to the right of the input). Skyvern generates an agent from your prompt using the default Skyvern 1.0 task engine and opens it in the agent editor. Click **Run** in the top right, confirm the parameters, then click **Run agent** to start execution.
<Accordion title="Optional: Advanced settings">
Click the **gear icon** next to send to configure additional options before running:
@@ -50,7 +50,7 @@ Click the **gear icon** next to send to configure additional options before runn
| **2FA Identifier** | Identifier for a 2FA code to handle two-factor auth automatically |
| **Extra HTTP Headers** | Custom HTTP request headers (dict format) |
| **Generate Script** | Auto-generate reusable scripts from a successful run |
-| **Publish Workflow** | Create a workflow alongside this task run |
+| **Publish Agent** | Create an agent alongside this task run |
| **Max Steps Override** | Cap the number of steps the AI can take |
| **Data Schema** | Define structured JSON output format |
| **Max Screenshot Scrolls** | Limit scrolls for post-action screenshots (default: 3) |
@@ -106,7 +106,7 @@ Now that you've seen the basic flow, here are a few ideas to try next:
- **Fill a form**: Point Skyvern at a contact form and tell it what to enter in each field
- **Compare prices**: Extract product names and prices from an e-commerce page using a data schema
-- **Navigate a flow**: Build a workflow to walk through a multi-page checkout or signup process
+- **Navigate a flow**: Build an agent to walk through a multi-page checkout or signup process
- **Use an Agent template**: Check the **Agents** section in the sidebar for pre-built automations you can run instantly
---
@@ -126,6 +126,6 @@ Now that you've seen the basic flow, here are a few ideas to try next:
icon="book"
href="/developers/getting-started/core-concepts"
>
- Understand tasks, workflows, and other building blocks
+ Understand tasks, agents, and other building blocks
</Card>
</CardGroup>
diff --git a/docs/cloud/managing-credentials/credentials-overview.mdx b/docs/cloud/managing-credentials/credentials-overview.mdx
index ca761b373..22c266d3c 100644
--- a/docs/cloud/managing-credentials/credentials-overview.mdx
+++ b/docs/cloud/managing-credentials/credentials-overview.mdx
@@ -14,7 +14,7 @@ keywords:
- Azure Key Vault
---
-The **Credentials** page stores sensitive values (passwords, payment cards, and secrets) so your workflows can use them without embedding secrets in prompts or parameters. Skyvern stores credentials by default with no external service required.
+The **Credentials** page stores sensitive values (passwords, payment cards, and secrets) so your agents can use them without embedding secrets in prompts or parameters. Skyvern stores credentials by default with no external service required.
<img src="/images/cloud/credentials-overview.png" alt="Credentials page overview" />
@@ -27,7 +27,7 @@ Sensitive credential data never reaches the LLM, logs, or API responses.
When you save a credential, the sensitive data (passwords, card numbers, CVVs, and TOTP secrets) is sent to a secure vault that provides encryption at rest. Skyvern supports multiple vault backends: Bitwarden, 1Password, Azure Key Vault, and custom webhook providers. Skyvern's own database stores only non-sensitive metadata: credential name, username, card last four digits, card brand, TOTP method, and similar identifiers. Passwords, full card numbers, CVVs, and TOTP secrets are stored exclusively in the vault.
</Step>
<Step title="Placeholders during execution">
- When a workflow runs, the LLM receives only placeholder IDs like `placeholder_Xk9m_password`. The AI decides *where* to type on the page, but never sees the real values. No third party, including the LLM provider, ever accesses your actual credentials.
+ When an agent runs, the LLM receives only placeholder IDs like `placeholder_Xk9m_password`. The AI decides *where* to type on the page, but never sees the real values. No third party, including the LLM provider, ever accesses your actual credentials.
</Step>
<Step title="Just-in-time injection">
At the browser level, the automation layer resolves placeholders to real values and types them directly into the page. After execution, credential values that appear in HTTP Request block responses, block context snapshots, and conditional evaluation outputs are automatically masked before storage.
@@ -48,7 +48,7 @@ Sensitive credential data never reaches the LLM, logs, or API responses.
<img src="/images/cloud/credentials-add-dropdown.png" alt="Add dropdown showing Password, Credit Card, and Secret options" />
</Step>
<Step title="Fill in the details and save">
- Enter the required fields and click **Save**. The credential is immediately available for use in workflows.
+ Enter the required fields and click **Save**. The credential is immediately available for use in agents.
</Step>
</Steps>
@@ -69,7 +69,7 @@ Sensitive credential data never reaches the LLM, logs, or API responses.
icon="credit-card"
href="/cloud/managing-credentials/credit-card-credentials"
>
- Payment card details for purchase and checkout workflows
+ Payment card details for purchase and checkout agents
</Card>
<Card
title="Secret Credentials"
@@ -90,21 +90,21 @@ Secrets store a single sensitive value (an API key, bearer token, or similar). C
{{ parameter_key.secret_value }}
```
-Replace `parameter_key` with the **key** assigned to the credential parameter in the workflow editor (e.g., `credentials`, `credentials_1`).
+Replace `parameter_key` with the **key** assigned to the credential parameter in the agent editor (e.g., `credentials`, `credentials_1`).
---
-## Using credentials in workflows
+## Using credentials in agents
-The most common pattern is a **Login block**. A Login block is a workflow step that signs into a website using stored credentials. Select a credential from the dropdown, and Skyvern fills in the username, password, and 2FA code (if configured) automatically. See [Block Reference](/cloud/building-workflows/configure-blocks) for details.
+The most common pattern is a **Login block**. A Login block is an agent step that signs into a website using stored credentials. Select a credential from the dropdown, and Skyvern fills in the username, password, and 2FA code (if configured) automatically. See [Block Reference](/cloud/building-agents/configure-blocks) for details.
-For workflows that need different credentials at runtime, add a **Credential parameter** (type: `credential_id`). When someone runs the workflow, they pick which credential to use from a dropdown. See [Workflow Parameters](/cloud/building-workflows/add-parameters) for setup.
+For agents that need different credentials at runtime, add a **Credential parameter** (type: `credential_id`). When someone runs the agent, they pick which credential to use from a dropdown. See [Agent Parameters](/cloud/building-agents/add-parameters) for setup.
---
## Deleting credentials
-Click the **trash icon** on any credential row. Deletion is permanent and cannot be undone. If a workflow references a deleted credential, the run will fail during initialization until you assign a replacement.
+Click the **trash icon** on any credential row. Deletion is permanent and cannot be undone. If an agent references a deleted credential, the run will fail during initialization until you assign a replacement.
<CardGroup cols={2}>
<Card
@@ -119,7 +119,7 @@ Click the **trash icon** on any credential row. Deletion is permanent and cannot
icon="credit-card"
href="/cloud/managing-credentials/credit-card-credentials"
>
- Store payment details for checkout workflows
+ Store payment details for checkout agents
</Card>
<Card
title="2FA / TOTP Setup"
diff --git a/docs/cloud/managing-credentials/credit-card-credentials.mdx b/docs/cloud/managing-credentials/credit-card-credentials.mdx
index adbc15e2b..d1ce2ca38 100644
--- a/docs/cloud/managing-credentials/credit-card-credentials.mdx
+++ b/docs/cloud/managing-credentials/credit-card-credentials.mdx
@@ -1,7 +1,7 @@
---
title: Credit Card Credentials
-subtitle: Store payment details for purchase and checkout workflows
-description: Store credit card details securely in the Skyvern Cloud UI for automated checkout and purchase workflows, with encrypted storage and browser-level injection.
+subtitle: Store payment details for purchase and checkout agents
+description: Store credit card details securely in the Skyvern Cloud UI for automated checkout and purchase agents, with encrypted storage and browser-level injection.
slug: cloud/managing-credentials/credit-card-credentials
keywords:
- credit card
@@ -41,11 +41,11 @@ Credit card credentials store payment details so the AI can fill checkout forms
<img src="/images/cloud/credentials-credit-card-detail.png" alt="Saved credit card credential showing masked card number" />
-## Using credit cards in workflows
+## Using credit cards in agents
-Credit cards work with [**Browser Task** and **Browser Action**](/cloud/building-workflows/configure-blocks) blocks that interact with checkout pages. The AI automatically recognizes standard checkout forms and fills card number, name, expiration, and CVV fields with the stored details. No field mapping is required.
+Credit cards work with [**Browser Task** and **Browser Action**](/cloud/building-agents/configure-blocks) blocks that interact with checkout pages. The AI automatically recognizes standard checkout forms and fills card number, name, expiration, and CVV fields with the stored details. No field mapping is required.
-For workflows that need different cards at runtime, add a **Credential parameter** (type: `credential_id`) in the [workflow editor](/cloud/building-workflows/add-parameters). When someone runs the workflow, they select which card to use from a dropdown. This lets the same checkout workflow work with different payment methods.
+For agents that need different cards at runtime, add a **Credential parameter** (type: `credential_id`) in the [agent editor](/cloud/building-agents/add-parameters). When someone runs the agent, they select which card to use from a dropdown. This lets the same checkout agent work with different payment methods.
<Note>
If you use 1Password as a credential provider, credit cards require a custom text field named **"Expire Date"**, **"Expiry Date"**, or **"Expiration Date"** in `MM/YYYY` or `MM/YY` format. 1Password does not expose the native expiration field through its API, so Skyvern reads this custom text field instead. See [External Providers](/cloud/managing-credentials/external-providers#1password) for full setup details.
diff --git a/docs/cloud/managing-credentials/external-providers.mdx b/docs/cloud/managing-credentials/external-providers.mdx
index 8d6852f17..d568ef68f 100644
--- a/docs/cloud/managing-credentials/external-providers.mdx
+++ b/docs/cloud/managing-credentials/external-providers.mdx
@@ -1,7 +1,7 @@
---
title: External Credential Providers
subtitle: Connect Bitwarden, 1Password, Azure Key Vault, or your own vault API
-description: Connect external credential vaults like Bitwarden, 1Password, Azure Key Vault, or a custom webhook API to the Skyvern Cloud UI so workflows can pull secrets at runtime.
+description: Connect external credential vaults like Bitwarden, 1Password, Azure Key Vault, or a custom webhook API to the Skyvern Cloud UI so agents can pull secrets at runtime.
slug: cloud/managing-credentials/external-providers
keywords:
- Bitwarden
@@ -13,10 +13,10 @@ keywords:
- runtime secrets
---
-Instead of copying secrets into Skyvern, you can point Skyvern at your existing vault and it pulls credentials at runtime. If your organization already manages secrets in a dedicated vault, connect it as a credential source and reference items directly from workflow parameters.
+Instead of copying secrets into Skyvern, you can point Skyvern at your existing vault and it pulls credentials at runtime. If your organization already manages secrets in a dedicated vault, connect it as a credential source and reference items directly from agent parameters.
<Note>
-External providers are configured per-organization. Once connected, any workflow in the organization can reference credentials from that provider.
+External providers are configured per-organization. Once connected, any agent in the organization can reference credentials from that provider.
</Note>
## Choosing a provider
@@ -29,7 +29,7 @@ External providers are configured per-organization. Once connected, any workflow
| **Azure Key Vault** | Password (with optional TOTP) | Settings page setup | Enterprise Azure environments |
| **Webhook (Custom API)** | Password, Credit Card | Settings page setup | Organizations with custom vaults |
-You can mix sources within the same workflow. For example, one Login block can use Skyvern-stored credentials while another uses Azure Key Vault.
+You can mix sources within the same agent. For example, one Login block can use Skyvern-stored credentials while another uses Azure Key Vault.
---
@@ -60,8 +60,8 @@ Make sure your Bitwarden account is on `bitwarden.com`, not `bitwarden.eu`. The
<Step title="Grab your Collection ID">
Click into the collection and find the collection UUID in the URL bar.
</Step>
- <Step title="Add to a workflow">
- In the Skyvern workflow editor, click **Parameters → Add Parameter → Credential Parameter** and select the **Bitwarden** tab. Enter your **Collection ID** and optionally an **Item ID** to target a specific vault item.
+ <Step title="Add to an agent">
+ In the Skyvern agent editor, click **Parameters → Add Parameter → Credential Parameter** and select the **Bitwarden** tab. Enter your **Collection ID** and optionally an **Item ID** to target a specific vault item.
</Step>
</Steps>
@@ -71,7 +71,7 @@ Make sure your Bitwarden account is on `bitwarden.com`, not `bitwarden.eu`. The
|-------|------------|
| **Collection ID** | The UUID of your Bitwarden collection (found in the URL when viewing the collection) |
| **Item ID** | Target a specific vault item. Leave blank to use URL matching instead. |
-| **URL Parameter Key** | Match credentials by the target URL. Useful when the same workflow runs against different sites. |
+| **URL Parameter Key** | Match credentials by the target URL. Useful when the same agent runs against different sites. |
### Identity data
@@ -144,9 +144,9 @@ Connects via a [service account token](https://developer.1password.com/docs/serv
If the status does not turn Active, verify that your service account token has access to the target vault and has not expired.
</Tip>
-### Using in a workflow
+### Using in an agent
-In the workflow editor, add a **Credential Parameter** and select **1Password** as the source. Provide the **Vault ID** and **Item ID**. You can find both IDs in the URL when viewing an item in the 1Password web app.
+In the agent editor, add a **Credential Parameter** and select **1Password** as the source. Provide the **Vault ID** and **Item ID**. You can find both IDs in the URL when viewing an item in the 1Password web app.
<Warning>
Credit cards from 1Password need a custom text field named **"Expire Date"**, **"Expiry Date"**, or **"Expiration Date"** in `MM/YYYY` or `MM/YY` format. 1Password does not expose the native expiration field through its API, so Skyvern reads this custom text field instead.
@@ -172,9 +172,9 @@ Pulls credentials stored as Azure secrets. Supports passwords with optional TOTP
</Step>
</Steps>
-### Using in a workflow
+### Using in an agent
-In the workflow editor, add a **Credential Parameter** and select **Azure Key Vault** as the source. Provide the vault name and the **secret names** that store the username, password, and optionally a TOTP secret. Enter the secret names, not the values themselves.
+In the agent editor, add a **Credential Parameter** and select **Azure Key Vault** as the source. Provide the vault name and the **secret names** that store the username, password, and optionally a TOTP secret. Enter the secret names, not the values themselves.
For example, if your vault stores secrets named `salesforce-username`, `salesforce-password`, and `salesforce-totp`, enter those three names in the corresponding fields.
@@ -383,10 +383,10 @@ Restart Skyvern after setting these variables.
Store login details with optional 2FA
</Card>
<Card
- title="Workflow Parameters"
+ title="Agent Parameters"
icon="sliders"
- href="/cloud/building-workflows/add-parameters"
+ href="/cloud/building-agents/add-parameters"
>
- Configure credential parameters in the workflow editor
+ Configure credential parameters in the agent editor
</Card>
</CardGroup>
diff --git a/docs/cloud/managing-credentials/password-credentials.mdx b/docs/cloud/managing-credentials/password-credentials.mdx
index c1e83ac21..0ef1047ce 100644
--- a/docs/cloud/managing-credentials/password-credentials.mdx
+++ b/docs/cloud/managing-credentials/password-credentials.mdx
@@ -1,7 +1,7 @@
---
title: Password Credentials
subtitle: Store login details and use them in automated sign-in flows
-description: Create and manage password credentials in the Skyvern Cloud UI with optional two-factor authentication via TOTP, email, or SMS for automated login workflows.
+description: Create and manage password credentials in the Skyvern Cloud UI with optional two-factor authentication via TOTP, email, or SMS for automated login agents.
slug: cloud/managing-credentials/password-credentials
keywords:
- username
@@ -12,7 +12,7 @@ keywords:
- automated sign-in
---
-Password credentials store a username, password, and optional 2FA configuration. Reference them from [Login blocks](/cloud/building-workflows/configure-blocks) in your workflows, and Skyvern handles the entire sign-in flow, including entering 2FA codes.
+Password credentials store a username, password, and optional 2FA configuration. Reference them from [Login blocks](/cloud/building-agents/configure-blocks) in your agents, and Skyvern handles the entire sign-in flow, including entering 2FA codes.
## Creating a password credential
@@ -27,7 +27,7 @@ Password credentials store a username, password, and optional 2FA configuration.
Expand the **Two-Factor Authentication** accordion to set up automated 2FA handling. See [below](#adding-two-factor-authentication) for details.
</Step>
<Step title="Save">
- Click **Save**. The credential is immediately available for use in workflows.
+ Click **Save**. The credential is immediately available for use in agents.
</Step>
</Steps>
@@ -60,7 +60,7 @@ The secret key is the base32-encoded string behind the QR code you'd scan in an
If you only have a QR code, decode it to extract the `secret=` parameter from the `otpauth://totp/...?secret=BASE32KEY` URI.
</Accordion>
-## Using credentials in a workflow
+## Using credentials in an agent
In the Login block configuration, select a stored credential from the dropdown. Skyvern fills in the username and password automatically, and handles 2FA if configured.
@@ -83,7 +83,7 @@ To edit a credential, click the **pencil icon** on its row. For security, saved
<Card
title="Block Reference"
icon="cube"
- href="/cloud/building-workflows/configure-blocks"
+ href="/cloud/building-agents/configure-blocks"
>
Configure Login blocks and other blocks that use credentials
</Card>
diff --git a/docs/cloud/managing-credentials/totp-setup.mdx b/docs/cloud/managing-credentials/totp-setup.mdx
index 8a2ecb947..b57f691eb 100644
--- a/docs/cloud/managing-credentials/totp-setup.mdx
+++ b/docs/cloud/managing-credentials/totp-setup.mdx
@@ -92,7 +92,7 @@ When a site sends 2FA codes via email or SMS, someone (or something) needs to de
## Pushing codes to Skyvern
-Once a workflow is running and waiting for a 2FA code, you need to deliver it. There are two ways.
+Once an agent is running and waiting for a 2FA code, you need to deliver it. There are two ways.
### Via the UI
@@ -106,7 +106,7 @@ Open the **2FA** tab on the Credentials page. The **Push a 2FA Code** form has t
<img src="/images/cloud/credentials-2fa-push-form.png" alt="2FA tab showing the Push a 2FA Code form and code history table" />
<Tip>
-If multiple workflows are running simultaneously, click **Add optional metadata** to link the code to a specific run using the workflow run ID, workflow ID, or task ID.
+If multiple agents are running simultaneously, click **Add optional metadata** to link the code to a specific run using the workflow run ID, workflow ID, or task ID.
</Tip>
### Via the API
@@ -171,7 +171,7 @@ This turns email-based 2FA into something nearly as automated as an authenticato
## Server-fetched codes (totp_url)
-Instead of pushing codes to Skyvern, you can have Skyvern pull them from your server. Pass `totp_url` when running a [task](/cloud/getting-started/run-from-code) or [workflow](/cloud/building-workflows/build-a-workflow), and Skyvern will call your endpoint when it needs a verification code.
+Instead of pushing codes to Skyvern, you can have Skyvern pull them from your server. Pass `totp_url` when running a [task](/cloud/getting-started/run-from-code) or [agent](/cloud/building-agents/build-an-agent), and Skyvern will call your endpoint when it needs a verification code.
Your endpoint must accept a POST request with `task_id`, `workflow_run_id`, and `workflow_permanent_id` in the body, and return:
diff --git a/docs/cloud/viewing-results/downloading-artifacts.mdx b/docs/cloud/viewing-results/downloading-artifacts.mdx
index 4a29ebbe8..d441f160e 100644
--- a/docs/cloud/viewing-results/downloading-artifacts.mdx
+++ b/docs/cloud/viewing-results/downloading-artifacts.mdx
@@ -22,7 +22,7 @@ Every run generates artifacts: video recordings, screenshots at each decision po
| **Recordings** | Recording tab → right-click the video → **Save video as...** |
| **Screenshots** | Overview tab → click a timeline item → right-click the image → **Save image as...** |
| **Extracted data** | Output tab → select the JSON text and copy |
-| **Downloaded files** | Output tab → **Workflow Run Downloaded Files** → click any link |
+| **Downloaded files** | Output tab → **Agent Run Downloaded Files** → click any link |
| **Generated code** | Code tab → **Copy** button in the top right |
## From the API
diff --git a/docs/cloud/viewing-results/run-details.mdx b/docs/cloud/viewing-results/run-details.mdx
index 31a225b83..d7d410bf1 100644
--- a/docs/cloud/viewing-results/run-details.mdx
+++ b/docs/cloud/viewing-results/run-details.mdx
@@ -1,7 +1,7 @@
---
title: Run Details
subtitle: Inspect actions, outputs, recordings, and parameters for any run
-description: Inspect the details of any task or workflow run in the Skyvern Cloud UI, including AI reasoning timelines, extracted data, recordings, screenshots, and parameters.
+description: Inspect the details of any task or agent run in the Skyvern Cloud UI, including AI reasoning timelines, extracted data, recordings, screenshots, and parameters.
slug: cloud/viewing-results/run-details
keywords:
- step timeline
@@ -15,25 +15,25 @@ keywords:
Every run has a detail page showing what the AI saw, what it decided, what it extracted, and whether anything went wrong. Click any run in [Run History](/cloud/viewing-results/run-history) to get here.
-<img src="/images/cloud/task-run-details.png" alt="Run details page showing a completed workflow run" />
+<img src="/images/cloud/task-run-details.png" alt="Run details page showing a completed agent run" />
## The header
-The top of the page shows the workflow title, a color-coded status badge, and the run ID. Three buttons on the right:
+The top of the page shows the agent title, a color-coded status badge, and the run ID. Three buttons on the right:
- **API & Webhooks**: the exact API request that would reproduce this run, including endpoint, headers, and payload
-- **Edit**: jump to the workflow editor
+- **Edit**: jump to the agent editor
- **Rerun**: start a new run pre-filled with the same parameters (appears after the run finishes)
While a run is in progress, a **Cancel** button appears instead of Rerun.
-<img src="/images/cloud/workflow-run-timeline.png" alt="A running workflow with live browser view and timeline" />
+<img src="/images/cloud/workflow-run-timeline.png" alt="A running agent with live browser view and timeline" />
## Extracted information
On success, the **Extracted Information** section appears above the tabs, showing the structured data you asked for, displayed as JSON.
-<img src="/images/cloud/task-run-results.png" alt="Workflow Run Outputs showing extracted JSON data" />
+<img src="/images/cloud/task-run-results.png" alt="Agent Run Outputs showing extracted JSON data" />
The output includes a `summary` (natural language description of what was accomplished), `extracted_information` (structured data matching your schema), and a `failure_reason` field that's `null` on success. On failure, a **Failure Reason** section appears instead with error details in a red box.
@@ -50,7 +50,7 @@ The timeline is a chronological feed of three card types:
| Card | What it shows |
|------|--------------|
| **Thought** | The AI's internal reasoning: what it sees, what it plans to do, and why. Tagged with "Decision." |
-| **Block** | When a workflow block starts or finishes (e.g., "Extraction"). Green checkmark = success. |
+| **Block** | When an agent block starts or finishes (e.g., "Extraction"). Green checkmark = success. |
| **Action** | Individual browser operations (e.g., "#1 Extract Data") with a description of what was done. |
Click any timeline item to see its corresponding screenshot in the left panel. The **Actions** and **Steps** counters at the top give you a quick sense of how much work the run involved.
@@ -61,11 +61,11 @@ When a run produces wrong results, start with the Thought cards. Read the AI's r
### Output
-All output data in one place. **Workflow Run Outputs** shows the complete JSON with line numbers and syntax highlighting. **Workflow Run Downloaded Files** lists any files the workflow downloaded; click to download directly.
+All output data in one place. **Agent Run Outputs** shows the complete JSON with line numbers and syntax highlighting. **Agent Run Downloaded Files** lists any files the agent downloaded; click to download directly.
### Parameters
-The configuration that produced this run: workflow input parameters (key-value pairs), webhook URL, proxy location, and HTTP headers. Use this to verify a run received the right inputs or to recreate a past result.
+The configuration that produced this run: agent input parameters (key-value pairs), webhook URL, proxy location, and HTTP headers. Use this to verify a run received the right inputs or to recreate a past result.
When you select a block in the Overview timeline, this tab also shows that block's configuration: prompt, URL, schema, and other settings.
@@ -83,7 +83,7 @@ Python code generated from the run. This tab appears when code generation is ena
<img src="/images/cloud/workflow-run-code-tab.png" alt="Code tab showing generated Python code with syntax highlighting" />
-If the workflow uses cached code, a **Cache Key selector** lets you switch between versions.
+If the agent uses cached code, a **Cache Key selector** lets you switch between versions.
## Debugging failed runs
diff --git a/docs/cloud/viewing-results/run-history.mdx b/docs/cloud/viewing-results/run-history.mdx
index fd367feba..ca8bf0fd9 100644
--- a/docs/cloud/viewing-results/run-history.mdx
+++ b/docs/cloud/viewing-results/run-history.mdx
@@ -1,7 +1,7 @@
---
title: Run History
-subtitle: Find, filter, and inspect past task and workflow executions
-description: Search, filter, and inspect past task and workflow runs in the Skyvern Cloud UI Runs page, including filtering by status, trigger type, and run parameters.
+subtitle: Find, filter, and inspect past task and agent executions
+description: Search, filter, and inspect past task and agent runs in the Skyvern Cloud UI Runs page, including filtering by status, trigger type, and run parameters.
slug: cloud/viewing-results/run-history
keywords:
- filter
@@ -12,13 +12,13 @@ keywords:
- past runs
---
-The **Runs** page shows every task and workflow execution, sorted newest-first. Use it to check on past runs, find failures, or verify that a scheduled workflow completed.
+The **Runs** page shows every task and agent execution, sorted newest-first. Use it to check on past runs, find failures, or verify that a scheduled agent completed.
<img src="/images/cloud/run-history-overview.png" alt="Run History page overview" />
## Finding a specific run
-**Search** narrows the list by run ID or workflow parameter value. Type part of an ID (e.g., `wr_49338`) or a parameter you passed (like a URL), and matching results appear as you type.
+**Search** narrows the list by run ID or agent parameter value. Type part of an ID (e.g., `wr_49338`) or a parameter you passed (like a URL), and matching results appear as you type.
<img src="/images/cloud/run-history-search.png" alt="Searching for a run by ID" />
@@ -32,13 +32,13 @@ Each row is one run. The columns:
| Column | What it shows |
|--------|--------------|
-| **Run ID** | Workflow run (`wr_...`) or task (`tsk_...`) identifier. Hover for the full ID. |
-| **Detail** | Workflow title or task description. A lightning bolt icon means code generation was used. |
+| **Run ID** | Agent run (`wr_...`) or task (`tsk_...`) identifier. Hover for the full ID. |
+| **Detail** | Agent title or task description. A lightning bolt icon means code generation was used. |
| **Status** | Color-coded badge: green (completed), yellow (running/queued/created), red (failed/timed_out), orange (terminated/canceled). |
| **Trigger** | How the run was started: **Manual**, **API**, or **Scheduled** (calendar icon). |
| **Created At** | Start time in your local timezone. Hover for UTC. |
-Workflow runs have a **settings icon** in the last column. Click it to expand the row and see the parameters passed to that run. If your search matches something inside the parameters, the row auto-expands so you can see the match in context.
+Agent runs have a **settings icon** in the last column. Click it to expand the row and see the parameters passed to that run. If your search matches something inside the parameters, the row auto-expands so you can see the match in context.
## Trigger type
@@ -48,7 +48,7 @@ Every run has a trigger type that indicates how it was started:
|-------------|-------------|
| **Manual** | Started by clicking **Run** in the Cloud UI |
| **API** | Started via the REST API or SDK |
-| **Scheduled** | Started automatically by a [schedule](/cloud/building-workflows/scheduling) |
+| **Scheduled** | Started automatically by a [schedule](/cloud/building-agents/scheduling) |
Scheduled runs display a **calendar icon badge** next to the run ID. Click the run to see the schedule name and cron expression in the run details.
diff --git a/docs/cookbooks/bulk-invoice-downloader.mdx b/docs/cookbooks/bulk-invoice-downloader.mdx
index d4f0c6978..5a6eb23e0 100644
--- a/docs/cookbooks/bulk-invoice-downloader.mdx
+++ b/docs/cookbooks/bulk-invoice-downloader.mdx
@@ -1,7 +1,7 @@
---
title: Bulk Invoice Downloader
subtitle: Automate invoice collection from any vendor portal
-description: Build a workflow that logs into vendor portals, finds order history, filters by date, and downloads invoices as PDFs.
+description: Build an agent that logs into vendor portals, finds order history, filters by date, and downloads invoices as PDFs.
slug: cookbooks/bulk-invoice-downloader
keywords:
- invoice
@@ -15,13 +15,13 @@ keywords:
Automate invoice collection from any vendor portal.
-This cookbook creates a workflow that takes in a vendor portal URL, logs in using saved credentials, finds order history, filters by date and finally downloads and emails the invoices as PDFs.
+This cookbook creates an agent that takes in a vendor portal URL, logs in using saved credentials, finds order history, filters by date and finally downloads and emails the invoices as PDFs.
---
## What you'll build
-A workflow that:
+An agent that:
1. Logs into a customer account portal
2. Navigates to order history and filters by date
@@ -72,7 +72,7 @@ Change `portal_url` to use your vendor's portal URL.
## Step 1: Store credentials
-Before defining the workflow, store the login email and password Skyvern will use. This keeps secrets out of your workflow definition and away from LLMs.
+Before defining the agent, store the login email and password Skyvern will use. This keeps secrets out of your agent definition and away from LLMs.
<Tabs>
<Tab title="Cloud UI">
@@ -86,7 +86,7 @@ Before defining the workflow, store the login email and password Skyvern will us
<img src="/images/cookbooks/er-creds.png" alt="Fill username and password to add a credential to Skyvern" />
</Step>
<Step title="Copy the credential ID">
- Copy the credential ID (here: `cred_504291305450505900`). You'll use this when configuring the workflow.
+ Copy the credential ID (here: `cred_504291305450505900`). You'll use this when configuring the agent.
<img src="/images/cookbooks/creds-id-copy.png" alt="Fill username and password to add a credential to Skyvern" />
</Step>
</Steps>
@@ -154,14 +154,14 @@ Before defining the workflow, store the login email and password Skyvern will us
---
-## Step 2: Create a new workflow
+## Step 2: Create a new agent
<Tabs>
<Tab title="Cloud UI">
<Steps>
- <Step title="Create the workflow">
- Go to **Workflows** → **Create Workflow**. Name it "Bulk Invoice Downloader".
- <img src="/images/cookbooks/create-workflow.png" alt="Create a new workflow from Skyvern Dashboard" />
+ <Step title="Create the agent">
+ Go to **Agents** → **Create Agent**. Name it "Bulk Invoice Downloader".
+ <img src="/images/cookbooks/create-workflow.png" alt="Create a new agent from Skyvern Dashboard" />
</Step>
<Step title="Configure the Start node">
Click the **Start** node. Set **Proxy Location** to **Residential**.
@@ -169,7 +169,7 @@ Before defining the workflow, store the login email and password Skyvern will us
</Steps>
</Tab>
<Tab title="API / SDK">
- A **workflow definition** is a JSON or YAML file that describes your entire workflow: its metadata, parameters, and blocks.
+ An **agent definition** is a JSON or YAML file that describes your entire agent: its metadata, parameters, and blocks.
This definition file contains no sensitive information (like credentials or input values) and can be shared publicly. Once we make this, it can either be uploaded via the Cloud UI or sent as an input parameter to `create_workflow()`. We'll do this in Step 4.
@@ -202,7 +202,7 @@ Before defining the workflow, store the login email and password Skyvern will us
### Set parameters
-Parameters are the inputs your workflow accepts. Defining them upfront lets you reuse the same workflow against different portals, date ranges, or recipients.
+Parameters are the inputs your agent accepts. Defining them upfront lets you reuse the same agent against different portals, date ranges, or recipients.
<Tabs>
<Tab title="Cloud UI">
@@ -216,7 +216,7 @@ Parameters are the inputs your workflow accepts. Defining them upfront lets you
| `recipient_email` | String | Email recipient for the summary |
| `credentials` | Credential ID | Select the credential you created in Step 1 |
- <img src="/images/cookbooks/add-params.png" alt="Setting input parameters in a workflow in Skyvern" />
+ <img src="/images/cookbooks/add-params.png" alt="Setting input parameters in an agent in Skyvern" />
<Note>
SMTP parameters are configured automatically by Skyvern Cloud. For self-hosted deployments, add them as AWS Secret parameters.
@@ -282,9 +282,9 @@ Parameters are the inputs your workflow accepts. Defining them upfront lets you
---
-## Step 3: Add workflow blocks
+## Step 3: Add agent blocks
-The workflow chains together several blocks to automate the full invoice collection process:
+The agent chains together several blocks to automate the full invoice collection process:
1. **Login block**: Authenticates to the vendor portal using stored credentials
2. **Navigation block**: Navigates to order history and applies date filters
@@ -293,7 +293,7 @@ The workflow chains together several blocks to automate the full invoice collect
5. **For loop + File parser**: Parses each downloaded PDF to extract structured data
6. **Send email**: Sends a summary with PDFs attached to the recipient
-In the Cloud UI, click the **+** button after the Start node to add blocks sequentially. For SDK users, add each block to the `blocks` array in your workflow definition file.
+In the Cloud UI, click the **+** button after the Start node to add blocks sequentially. For SDK users, add each block to the `blocks` array in your agent definition file.
### Login block
@@ -310,7 +310,7 @@ The `login` block authenticates using stored credentials. Skyvern injects the us
- `INVALID_CREDENTIALS`: "Login failed - incorrect email or password"
- `ACCOUNT_LOCKED`: "Account has been locked or suspended"
- <img src="/images/cookbooks/add-block.png" alt="Adding a block in a workflow in Skyvern" />
+ <img src="/images/cookbooks/add-block.png" alt="Adding a block in an agent in Skyvern" />
</Tab>
<Tab title="API / SDK">
@@ -353,7 +353,7 @@ The `login` block authenticates using stored credentials. Skyvern injects the us
</Tab>
</Tabs>
-**Why `error_code_mapping`?** It surfaces specific failures in your workflow output, so you can handle "wrong password" differently from "account locked."
+**Why `error_code_mapping`?** It surfaces specific failures in your agent output, so you can handle "wrong password" differently from "account locked."
### Navigation block
@@ -514,7 +514,7 @@ The output is accessible as `data_extraction_block_output.orders` in subsequent
### Download invoices block
-Iterate over each order and click its "Download Invoice" button. `continue_on_failure: true` ensures one failed download doesn't stop the entire workflow.
+Iterate over each order and click its "Download Invoice" button. `continue_on_failure: true` ensures one failed download doesn't stop the entire agent.
<Tabs>
<Tab title="Cloud UI">
@@ -732,15 +732,15 @@ Send a summary email with PDFs attached.
---
-## Complete workflow
+## Complete agent
<Tabs>
<Tab title="Cloud UI">
- Here's a summary of the complete workflow you've built in the visual editor:
+ Here's a summary of the complete agent you've built in the visual editor:
<Steps>
- <Step title="Create the workflow">
- Go to **Workflows** and click **Create Workflow**. Name it "Bulk Invoice Downloader." On the **Start** node, set **Proxy Location** to **Residential** and add the parameters: `portal_url`, `start_date`, `end_date`, `recipient_email`, and `credentials`.
+ <Step title="Create the agent">
+ Go to **Agents** and click **Create Agent**. Name it "Bulk Invoice Downloader." On the **Start** node, set **Proxy Location** to **Residential** and add the parameters: `portal_url`, `start_date`, `end_date`, `recipient_email`, and `credentials`.
</Step>
<Step title="Block 1: Login">
Add a **Login** block. Set **URL** to the `portal_url` parameter. Select the `credentials` parameter. Set the goal: "Log in using the provided credentials. Handle any cookie consent popups. COMPLETE when on the account dashboard or orders page." In **Advanced Settings**, add error messages for `INVALID_CREDENTIALS` and `ACCOUNT_LOCKED`.
@@ -1067,13 +1067,13 @@ workflow_definition:
## Step 4: Run and monitor
-Create the workflow from your definition file and execute it.
+Create the agent from your definition file and execute it.
<Tabs>
<Tab title="Cloud UI">
<Steps>
- <Step title="Run the workflow">
- Click **Run** in the workflow editor. Fill in the parameters:
+ <Step title="Run the agent">
+ Click **Run** in the agent editor. Fill in the parameters:
- **portal_url**: `https://ember--roasters.vercel.app/`
- **start_date**: `2025-01-01`
@@ -1230,14 +1230,14 @@ Create the workflow from your definition file and execute it.
## Resources
<CardGroup cols={2}>
- <Card title="Workflow Blocks Reference" icon="cube" href="/cloud/building-workflows/configure-blocks">
+ <Card title="Agent Blocks Reference" icon="cube" href="/cloud/building-agents/configure-blocks">
Complete parameter reference for all block types
</Card>
<Card title="Credential Management" icon="key" href="/sdk-reference/credentials/create-credential">
Securely store and use login credentials
</Card>
- <Card title="File Operations" icon="file" href="/cloud/building-workflows/configure-blocks">
- Download, parse, and upload files in workflows
+ <Card title="File Operations" icon="file" href="/cloud/building-agents/configure-blocks">
+ Download, parse, and upload files in agents
</Card>
<Card title="Error Handling" icon="triangle-exclamation" href="/developers/going-to-production/error-handling">
Handle failures and retries in production
diff --git a/docs/cookbooks/healthcare-portal-data.mdx b/docs/cookbooks/healthcare-portal-data.mdx
index cf41aca04..974e419ec 100644
--- a/docs/cookbooks/healthcare-portal-data.mdx
+++ b/docs/cookbooks/healthcare-portal-data.mdx
@@ -1,7 +1,7 @@
---
title: Healthcare Portal Data Extraction
subtitle: Extract patient demographics and billing data from OpenEMR
-description: Extract patient demographics and billing data from OpenEMR using Skyvern workflows with residential proxies, browser profiles, and loop blocks for multi-page pagination.
+description: Extract patient demographics and billing data from OpenEMR using Skyvern agents with residential proxies, browser profiles, and loop blocks for multi-page pagination.
slug: cookbooks/healthcare-portal-data
keywords:
- healthcare
@@ -114,8 +114,8 @@ Log in once, save the browser state as a profile, and skip login on future runs.
<Tabs>
<Tab title="Cloud UI">
<Steps>
- <Step title="Create a login workflow">
- Go to **Workflows** in the sidebar and create a new workflow. Add a **Navigation** block with URL `https://demo.openemr.io/openemr/index.php` and goal: "Log in with username 'admin' and password 'pass'. Confirm the Calendar page loads."
+ <Step title="Create a login agent">
+ Go to **Agents** in the sidebar and create a new agent. Add a **Navigation** block with URL `https://demo.openemr.io/openemr/index.php` and goal: "Log in with username 'admin' and password 'pass'. Confirm the Calendar page loads."
On the **Start** node, expand the settings and enable **Save & Reuse Session**. Set **Proxy Location** to a country (e.g., **United States**).
@@ -129,11 +129,11 @@ Log in once, save the browser state as a profile, and skip login on future runs.
></video>
</Frame>
</Step>
- <Step title="Run the workflow">
- Run the workflow and wait for it to complete.
+ <Step title="Run the agent">
+ Run the agent and wait for it to complete.
</Step>
<Step title="Create a profile via API">
- Browser profile creation is done via the API. Use the `create_browser_profile` call from the API/SDK tab with the completed workflow run ID. Name it `openemr-demo-admin`.
+ Browser profile creation is done via the API. Use the `create_browser_profile` call from the API/SDK tab with the completed agent run ID. Name it `openemr-demo-admin`.
</Step>
</Steps>
</Tab>
@@ -263,7 +263,7 @@ Log in once, save the browser state as a profile, and skip login on future runs.
</Tabs>
<Note>
-`persist_browser_session` is a workflow definition property. Set it when creating the workflow, not when running it. See [Browser Profiles](/developers/optimization/browser-profiles) for the full lifecycle.
+`persist_browser_session` is an agent definition property. Set it when creating the agent, not when running it. See [Browser Profiles](/developers/optimization/browser-profiles) for the full lifecycle.
</Note>
---
@@ -274,12 +274,12 @@ Navigate to **Patient/Client > Finder** and extract the results table.
<Tabs>
<Tab title="Cloud UI">
- Create a workflow with two blocks:
+ Create an agent with two blocks:
1. **Navigation** block, URL: `https://demo.openemr.io/openemr/index.php`. Goal: "Click Patient/Client in the top menu, then click Finder. Click Search to display all patients."
2. **Extraction** block, Goal: "Extract all patient rows from the Patient Finder results table." Paste the patient schema into **Data Schema**.
- On the **Start** node, set **Proxy Location** to a country (e.g., **United States**). Run the workflow.
+ On the **Start** node, set **Proxy Location** to a country (e.g., **United States**). Run the agent.
</Tab>
<Tab title="API / SDK">
<CodeGroup>
@@ -408,12 +408,12 @@ Navigate to **Reports > Visits > Superbill**, set a date range, and extract the
<Tabs>
<Tab title="Cloud UI">
- Create a workflow with two blocks:
+ Create an agent with two blocks:
1. **Navigation** block, Goal: "Click Reports in the top menu, then Visits, then Superbill. Set the From date to 2020-01-01 and the To date to today. Click Submit."
2. **Extraction** block, Goal: "Extract all encounter rows from the Superbill report." Paste the encounter schema into **Data Schema**.
- On the **Start** node, set **Proxy Location** to a country (e.g., **United States**). Run the workflow.
+ On the **Start** node, set **Proxy Location** to a country (e.g., **United States**). Run the agent.
</Tab>
<Tab title="API / SDK">
<CodeGroup>
@@ -705,7 +705,7 @@ You cannot use `browser_profile_id` and `browser_session_id` in the same request
## Error handling
-OpenEMR can timeout or show session-expired pages. Use `error_code_mapping` on workflow blocks to classify failures, and `max_retries` to retry automatically.
+OpenEMR can timeout or show session-expired pages. Use `error_code_mapping` on agent blocks to classify failures, and `max_retries` to retry automatically.
<Tabs>
<Tab title="Cloud UI">
@@ -730,7 +730,7 @@ OpenEMR can timeout or show session-expired pages. Use `error_code_mapping` on w
</Note>
</Tab>
<Tab title="API / SDK">
- Set `error_code_mapping` and `max_retries` directly on workflow blocks:
+ Set `error_code_mapping` and `max_retries` directly on agent blocks:
```json
{
@@ -790,15 +790,15 @@ See [Error Handling](/developers/going-to-production/error-handling) and [CAPTCH
---
-## Complete workflow
+## Complete agent
-This workflow combines everything: navigate to the Patient Finder, extract demographics, navigate to Superbill, and extract billing data, with error recovery and residential proxy.
+This agent combines everything: navigate to the Patient Finder, extract demographics, navigate to Superbill, and extract billing data, with error recovery and residential proxy.
<Tabs>
<Tab title="Cloud UI">
<Steps>
- <Step title="Create the workflow">
- Go to **Workflows** and create a new workflow named "OpenEMR Daily Extract." On the **Start** node, enable **Save & Reuse Session** and set **Proxy Location** to a country (e.g., **United States**).
+ <Step title="Create the agent">
+ Go to **Agents** and create a new agent named "OpenEMR Daily Extract." On the **Start** node, enable **Save & Reuse Session** and set **Proxy Location** to a country (e.g., **United States**).
</Step>
<Step title="Block 1: Navigation (open Patient Finder)">
Add a **Navigation** block. Set URL to `https://demo.openemr.io/openemr/index.php` and goal: "Click Patient/Client > Finder. Click Search to display all patients. If a login page appears, log in with 'admin'/'pass'." In **Advanced Settings**, enable **Error Messages** and add `{"session_expired": "Session expired, login required, or access denied page"}`.
@@ -813,7 +813,7 @@ This workflow combines everything: navigate to the Patient Finder, extract demog
Add another **Extraction** block. Set goal: "Extract all encounter rows from the Superbill report." Paste the encounter schema into **Data Schema**.
</Step>
<Step title="Run">
- Click **Run**. The workflow navigates to the Patient Finder, extracts demographics, then navigates to Superbill and extracts billing data.
+ Click **Run**. The agent navigates to the Patient Finder, extracts demographics, then navigates to Superbill and extracts billing data.
</Step>
</Steps>
@@ -1062,7 +1062,7 @@ This workflow combines everything: navigate to the Patient Finder, extract demog
| Error mapping + retries | Recover from session timeouts |
<Tip>
-The OpenEMR demo resets daily at 8:00 AM UTC, so profiles expire every day. In production, re-run your login workflow weekly or whenever extractions fail with auth errors. See [Browser Profiles](/developers/optimization/browser-profiles) for the refresh pattern.
+The OpenEMR demo resets daily at 8:00 AM UTC, so profiles expire every day. In production, re-run your login agent weekly or whenever extractions fail with auth errors. See [Browser Profiles](/developers/optimization/browser-profiles) for the refresh pattern.
</Tip>
---
diff --git a/docs/cookbooks/job-application-filler.mdx b/docs/cookbooks/job-application-filler.mdx
index 0a779162f..bfedf6a91 100644
--- a/docs/cookbooks/job-application-filler.mdx
+++ b/docs/cookbooks/job-application-filler.mdx
@@ -1,7 +1,7 @@
---
title: Job Applications Pipeline
subtitle: Search for jobs and automatically apply using your resume
-description: Build a workflow that parses your resume, searches job portals, extracts listings, generates tailored answers with AI, and submits applications automatically.
+description: Build an agent that parses your resume, searches job portals, extracts listings, generates tailored answers with AI, and submits applications automatically.
slug: cookbooks/job-application-filler
keywords:
- job application
@@ -15,13 +15,13 @@ keywords:
Automate job applications across multiple postings on any job portal.
-This cookbook creates a workflow that logs into a job portal, searches for relevant positions based on your resume, extracts job listings, and applies to each one with AI-generated responses tailored to the role.
+This cookbook creates an agent that logs into a job portal, searches for relevant positions based on your resume, extracts job listings, and applies to each one with AI-generated responses tailored to the role.
---
## What you'll build
-A workflow that:
+An agent that:
1. Parses your resume PDF to extract structured information
2. Logs into a job portal using saved credentials
@@ -71,9 +71,9 @@ Change `job_portal_url` to use your job portal's URL.
## Step 1: Store credentials
-Before defining the workflow, store the login email and password Skyvern will use.
+Before defining the agent, store the login email and password Skyvern will use.
-This makes sure your passwords are never stored in the shareable workflow definition and never sent to LLMs.
+This makes sure your passwords are never stored in the shareable agent definition and never sent to LLMs.
<Tabs>
<Tab title="Cloud UI">
@@ -87,7 +87,7 @@ This makes sure your passwords are never stored in the shareable workflow defini
<img src="/images/cookbooks/js-creds.png" alt="Fill username and password to add a credential to Skyvern" />
</Step>
<Step title="Copy the credential ID">
- Copy the credential ID (here: `cred_504284876895871734`). You'll use this when configuring the workflow.
+ Copy the credential ID (here: `cred_504284876895871734`). You'll use this when configuring the agent.
<img src="/images/cookbooks/creds-id-copy.png" alt="Fill username and password to add a credential to Skyvern" />
</Step>
</Steps>
@@ -155,19 +155,19 @@ This makes sure your passwords are never stored in the shareable workflow defini
---
-## Step 2: Create a new workflow
+## Step 2: Create a new agent
<Tabs>
<Tab title="Cloud UI">
<Steps>
- <Step title="Create the workflow">
- Go to **Workflows** → **Create Workflow**. Name it "Search and Apply for Jobs Workflow".
- <img src="/images/cookbooks/create-workflow.png" alt="Create a new workflow from Skyvern Dashboard" />
+ <Step title="Create the agent">
+ Go to **Agents** → **Create Agent**. Name it "Search and Apply for Jobs Workflow".
+ <img src="/images/cookbooks/create-workflow.png" alt="Create a new agent from Skyvern Dashboard" />
</Step>
</Steps>
</Tab>
<Tab title="API / SDK">
- A **workflow definition** is a JSON or YAML file that describes your entire workflow: its metadata, parameters, and blocks. Create a file called `job-application-workflow.yaml` (or `.json`) with the following template:
+ An **agent definition** is a JSON or YAML file that describes your entire agent: its metadata, parameters, and blocks. Create a file called `job-application-workflow.yaml` (or `.json`) with the following template:
<CodeGroup>
```json JSON
@@ -200,7 +200,7 @@ This makes sure your passwords are never stored in the shareable workflow defini
### Set parameters
-Parameters are the inputs your workflow accepts. Defining them upfront lets you reuse the same workflow against different job portals.
+Parameters are the inputs your agent accepts. Defining them upfront lets you reuse the same agent against different job portals.
<Tabs>
<Tab title="Cloud UI">
@@ -211,7 +211,7 @@ Parameters are the inputs your workflow accepts. Defining them upfront lets you
| `resume` | File URL | URL to your resume PDF |
| `credentials` | Credential ID | Select the credential you created in Step 1 |
| `job_portal_url` | String | Job portal login URL |
- <img src="/images/cookbooks/add-params.png" alt="Setting input parameters in a workflow in Skyvern" />
+ <img src="/images/cookbooks/add-params.png" alt="Setting input parameters in an agent in Skyvern" />
</Tab>
<Tab title="API / SDK">
Replace the empty `parameters` array with the following:
@@ -255,9 +255,9 @@ Parameters are the inputs your workflow accepts. Defining them upfront lets you
---
-## Step 3: Add workflow blocks
+## Step 3: Add agent blocks
-The workflow chains together several blocks to automate the full job application process:
+The agent chains together several blocks to automate the full job application process:
1. **PDF Parser block**: Extracts structured data from your resume
2. **Login block**: Authenticates to the job portal using stored credentials
@@ -265,7 +265,7 @@ The workflow chains together several blocks to automate the full job application
4. **Extraction block**: Extracts a list of job postings from search results
5. **For loop** (Go to URL + Extraction + Action + Extraction + Text Prompt + Navigation): Iterates over each job to extract details, generates tailored answers using an LLM, and submits the application.
-In the Cloud UI, click the **+** button after the Start node to add blocks sequentially. For SDK users, add each block to the `blocks` array in your workflow definition file.
+In the Cloud UI, click the **+** button after the Start node to add blocks sequentially. For SDK users, add each block to the `blocks` array in your agent definition file.
### PDF Parser block
@@ -274,7 +274,7 @@ The `pdf_parser` block extracts structured information from your resume PDF. Sky
<Tabs>
<Tab title="Cloud UI">
Add a **PDF Parser** block. Set **File URL** to the `resume` parameter.
- <img src="/images/cookbooks/add-block.png" alt="Adding a block in a workflow in Skyvern" />
+ <img src="/images/cookbooks/add-block.png" alt="Adding a block in an agent in Skyvern" />
</Tab>
<Tab title="API / SDK">
<CodeGroup>
@@ -675,19 +675,19 @@ Iterate over each job posting and complete the application. This loop contains m
</Tab>
</Tabs>
-**Key pattern:** `continue_on_failure: true` ensures that if one application fails, the workflow continues to the next job. Inside the loop, `current_value` gives you the current job being processed.
+**Key pattern:** `continue_on_failure: true` ensures that if one application fails, the agent continues to the next job. Inside the loop, `current_value` gives you the current job being processed.
---
-## Complete workflow definition
+## Complete agent definition
<Tabs>
<Tab title="Cloud UI">
- Here's a summary of the complete workflow you've built in the visual editor:
+ Here's a summary of the complete agent you've built in the visual editor:
<Steps>
- <Step title="Create the workflow">
- Go to **Workflows** → **Create Workflow**. Name it "Search and Apply for Jobs Workflow." On the **Start** node, set **Proxy Location** to **Residential** and add the parameters: `resume`, `credentials`, and `job_portal_url`.
+ <Step title="Create the agent">
+ Go to **Agents** → **Create Agent**. Name it "Search and Apply for Jobs Workflow." On the **Start** node, set **Proxy Location** to **Residential** and add the parameters: `resume`, `credentials`, and `job_portal_url`.
</Step>
<Step title="Block 1: PDF Parser">
Add a **PDF Parser** block. Set **File URL** to the `resume` parameter.
@@ -991,13 +991,13 @@ workflow_definition:
## Step 4: Run and monitor
-Create the workflow from your definition file and execute it.
+Create the agent from your definition file and execute it.
<Tabs>
<Tab title="Cloud UI">
<Steps>
- <Step title="Run the workflow">
- Click **Run** in the workflow editor. Fill in the parameters:
+ <Step title="Run the agent">
+ Click **Run** in the agent editor. Fill in the parameters:
- **resume**: URL to your resume PDF
- **job_portal_url**: `https://job-stash.vercel.app`
@@ -1146,14 +1146,14 @@ Create the workflow from your definition file and execute it.
## Resources
<CardGroup cols={2}>
- <Card title="Workflow Blocks Reference" icon="cube" href="/cloud/building-workflows/configure-blocks">
+ <Card title="Agent Blocks Reference" icon="cube" href="/cloud/building-agents/configure-blocks">
Complete parameter reference for all block types
</Card>
<Card title="Credential Management" icon="key" href="/sdk-reference/credentials/create-credential">
Securely store and use login credentials
</Card>
- <Card title="File Operations" icon="file" href="/cloud/building-workflows/configure-blocks">
- Upload and parse files in workflows
+ <Card title="File Operations" icon="file" href="/cloud/building-agents/configure-blocks">
+ Upload and parse files in agents
</Card>
<Card title="Error Handling" icon="triangle-exclamation" href="/developers/going-to-production/error-handling">
Handle failures and retries in production
diff --git a/docs/cookbooks/overview.mdx b/docs/cookbooks/overview.mdx
index ac08df5e4..5f4dda52d 100644
--- a/docs/cookbooks/overview.mdx
+++ b/docs/cookbooks/overview.mdx
@@ -1,6 +1,6 @@
---
title: Overview
-subtitle: End-to-end workflow examples for common automation scenarios
+subtitle: End-to-end agent examples for common automation scenarios
description: Production-ready cookbook examples for Skyvern browser automation including bulk invoice downloading, job application filling, and healthcare portal data extraction.
slug: cookbooks/overview
keywords:
@@ -12,9 +12,9 @@ keywords:
- use case
---
-Cookbooks are complete, production-ready workflow examples that demonstrate how to use Skyvern Browser Automation agent in real-world use-cases.
+Cookbooks are complete, production-ready agent examples that demonstrate how to use Skyvern Browser Automation agent in real-world use-cases.
-Each cookbook walks through the workflow step-by-step, explaining design decisions and showing you how to adapt it for your use case.
+Each cookbook walks through the agent step-by-step, explaining design decisions and showing you how to adapt it for your use case.
---
@@ -76,20 +76,20 @@ All cookbooks require a Skyvern API key. Here's how to get one:
## Other Resources
-If you're new to Skyvern workflows, start with these foundational guides:
+If you're new to Skyvern agents, start with these foundational guides:
<CardGroup cols={2}>
<Card
- title="Build a Workflow"
+ title="Build an Agent"
icon="hammer"
- href="/cloud/building-workflows/build-a-workflow"
+ href="/cloud/building-agents/build-an-agent"
>
- Learn workflow basics: parameters, blocks, and data passing
+ Learn agent basics: parameters, blocks, and data passing
</Card>
<Card
- title="Workflow Blocks Reference"
+ title="Agent Blocks Reference"
icon="cube"
- href="/cloud/building-workflows/configure-blocks"
+ href="/cloud/building-agents/configure-blocks"
>
Complete reference for all block types
</Card>
diff --git a/docs/developers/browser-automations/actions-reference.mdx b/docs/developers/browser-automations/actions-reference.mdx
index 611504e46..b7a3a9cc0 100644
--- a/docs/developers/browser-automations/actions-reference.mdx
+++ b/docs/developers/browser-automations/actions-reference.mdx
@@ -22,7 +22,7 @@ keywords:
Browser automations are built in code using three layers: Page (AI-enhanced Playwright), Agent (multi-step AI goals), and Browser (cloud Chromium instance). This page lists every operation available on a Page or through an Agent. For the full SDK documentation with all parameter options, see the [SDK Reference](/sdk-reference/browser-automation/act).
-If you're building automations visually instead, see [Block Types and Configuration](/cloud/building-workflows/configure-blocks) for the equivalent operations in the Cloud UI workflow editor.
+If you're building automations visually instead, see [Block Types and Configuration](/cloud/building-agents/configure-blocks) for the equivalent operations in the Cloud UI agent editor.
---
diff --git a/docs/developers/browser-automations/extract-structured-data.mdx b/docs/developers/browser-automations/extract-structured-data.mdx
index 07a9374e3..715d0bf75 100644
--- a/docs/developers/browser-automations/extract-structured-data.mdx
+++ b/docs/developers/browser-automations/extract-structured-data.mdx
@@ -19,7 +19,7 @@ import { FIELD_TYPES, SchemaBuilder } from "/snippets/schema-builder.mdx";
When building browser automations in code, you can extract structured data from any page using `page.extract` with a JSON schema, or by passing a `data_extraction_schema` to `page.agent.run_task`. By default, Skyvern returns extracted data in whatever format makes sense for the action. Pass a schema to enforce a specific shape using [JSON Schema](https://json-schema.org/).
-If you're using the Cloud UI workflow editor instead, extraction works through the Extract block. See [Block Types and Configuration](/cloud/building-workflows/configure-blocks) for setup.
+If you're using the Cloud UI agent editor instead, extraction works through the Extract block. See [Block Types and Configuration](/cloud/building-agents/configure-blocks) for setup.
---
diff --git a/docs/developers/browser-automations/handle-browsers.mdx b/docs/developers/browser-automations/handle-browsers.mdx
index 2ce270a33..527bffe3c 100644
--- a/docs/developers/browser-automations/handle-browsers.mdx
+++ b/docs/developers/browser-automations/handle-browsers.mdx
@@ -19,7 +19,7 @@ keywords:
Every browser automation starts with a browser. You launch a cloud Chromium instance, get a Playwright context, and write your automation against it. Cookies, localStorage, and auth state persist across every page you open inside that browser.
-This page covers browser lifecycle for code-based automations using the Skyvern SDK. If you're running automations through the Cloud UI workflow editor, browser management is handled automatically. See [Browser Sessions](/cloud/browser-management/browser-sessions) for the Cloud UI equivalent.
+This page covers browser lifecycle for code-based automations using the Skyvern SDK. If you're running automations through the Cloud UI agent editor, browser management is handled automatically. See [Browser Sessions](/cloud/browser-management/browser-sessions) for the Cloud UI equivalent.
---
diff --git a/docs/developers/browser-automations/overview.mdx b/docs/developers/browser-automations/overview.mdx
index a3e5658bd..479923bba 100644
--- a/docs/developers/browser-automations/overview.mdx
+++ b/docs/developers/browser-automations/overview.mdx
@@ -19,10 +19,10 @@ keywords:
Browser automations are multi-step automations written in code. You launch a cloud browser, get a Playwright page with AI methods layered on top, and write your automation in Python or TypeScript. The code lives in your repo, runs in your CI, and deploys like any other software.
-This is the code-first path. If you prefer building automations visually with drag-and-drop blocks, see [Workflows](/cloud/building-workflows/build-a-workflow) in the Cloud UI docs.
+This is the code-first path. If you prefer building automations visually with drag-and-drop blocks, see [Agents](/cloud/building-agents/build-an-agent) in the Cloud UI docs.
<Info>
-**Workflows vs. Browser Automation:** Workflows are built and run in the Cloud UI, no code required. Browser automations are built and run in code using Page, Agent, and Browser. Both can do multi-step work across pages. Choose based on whether your team prefers a visual editor or a code editor.
+**Agents vs. Browser Automation:** Agents are built and run in the Cloud UI, no code required. Browser automations are built and run in code using Page, Agent, and Browser. Both can do multi-step work across pages. Choose based on whether your team prefers a visual editor or a code editor.
</Info>
This guide walks through a real example: logging into a vendor portal, extracting invoice data, and downloading a PDF. Four steps:
diff --git a/docs/developers/browser-automations/work-with-files.mdx b/docs/developers/browser-automations/work-with-files.mdx
index 11ef5c280..a44a71078 100644
--- a/docs/developers/browser-automations/work-with-files.mdx
+++ b/docs/developers/browser-automations/work-with-files.mdx
@@ -16,7 +16,7 @@ keywords:
In a browser automation, `agent.download_files` navigates a page, finds the download link, and captures the file. Downloaded files are stored in Skyvern's cloud storage and returned as presigned URLs in the response.
-If you're building workflows in the Cloud UI instead, use the File Download block. See [Block Types and Configuration](/cloud/building-workflows/configure-blocks).
+If you're building agents in the Cloud UI instead, use the File Download block. See [Block Types and Configuration](/cloud/building-agents/configure-blocks).
---
@@ -159,19 +159,19 @@ for (const file of result.downloadedFiles ?? []) {
---
-## File operations in workflows
+## File operations in agents
-If you build workflows in the Cloud UI, file operations use dedicated blocks instead of `agent.download_files`:
+If you build agents in the Cloud UI, file operations use dedicated blocks instead of `agent.download_files`:
| Block | Purpose |
|-------|---------|
-| **File Download** | Download files during workflow execution |
+| **File Download** | Download files during agent execution |
| **File Parser** | Parse PDFs, CSVs, and Excel files |
| **Download to S3** | Save files from URLs to Skyvern's S3 |
-| **Upload to S3** | Upload workflow files to S3 |
+| **Upload to S3** | Upload agent files to S3 |
| **File Upload** | Upload to your own S3 or Azure Blob Storage |
-Files downloaded during a workflow accumulate in a temporary directory and can be passed between blocks using workflow parameters. See [Workflow Blocks Reference](/cloud/building-workflows/configure-blocks) for block configuration details.
+Files downloaded during an agent run accumulate in a temporary directory and can be passed between blocks using agent parameters. See [Agent Blocks Reference](/cloud/building-agents/configure-blocks) for block configuration details.
---
diff --git a/docs/developers/credentials/handle-2fa.mdx b/docs/developers/credentials/handle-2fa.mdx
index b64874e7b..22c3f78a7 100644
--- a/docs/developers/credentials/handle-2fa.mdx
+++ b/docs/developers/credentials/handle-2fa.mdx
@@ -417,7 +417,7 @@ curl -X POST "https://api.skyvern.com/v1/credentials/totp" \
Skyvern automatically detects URLs and classifies them as magic links. The automation will navigate to the link to complete authentication.
</Note>
-For magic link flows, structure your workflow in two parts:
+For magic link flows, structure your agent in two parts:
1. **Trigger the magic link**: Navigate to login and enter email
2. **Complete login**: Use the magic link as the starting URL for the next step
@@ -448,7 +448,7 @@ Store TOTP in 1Password's one-time password field:
1. Edit the login item in 1Password
2. Add a "One-Time Password" field
3. Enter the TOTP secret or scan the QR code
-4. Reference the item in your Skyvern workflow
+4. Reference the item in your Skyvern agent
---
diff --git a/docs/developers/credentials/store-credentials.mdx b/docs/developers/credentials/store-credentials.mdx
index 5203174e5..6ab9a2cc4 100644
--- a/docs/developers/credentials/store-credentials.mdx
+++ b/docs/developers/credentials/store-credentials.mdx
@@ -233,7 +233,7 @@ Connect Skyvern to your Bitwarden organization to use existing vault items.
2. Create a collection to share with Skyvern
3. Contact [[email protected]](mailto:[email protected]) to complete the integration
4. Get your collection ID from the Bitwarden URL
-5. Reference credentials by collection ID in your workflows
+5. Reference credentials by collection ID in your agents
**Self-hosted setup:**
@@ -263,7 +263,7 @@ curl -X POST "https://api.skyvern.com/v1/credentials/onepassword/create" \
}'
```
-3. Reference vault items by ID in your workflows
+3. Reference vault items by ID in your agents
### Azure Key Vault
@@ -316,9 +316,9 @@ curl -X POST "https://api.skyvern.com/v1/credentials/custom_credential/create" \
---
-## Using credentials in workflows
+## Using credentials in agents
-Workflows are the recommended way to use credentials. Add a credential parameter to your workflow, then reference it in login blocks.
+Agents are the recommended way to use credentials. Add a credential parameter to your agent, then reference it in login blocks.
<CodeGroup>
```python Python
@@ -462,7 +462,7 @@ curl -X POST "https://api.skyvern.com/v1/credentials/cred_xyz789/delete" \
</CodeGroup>
<Warning>
-Credential deletion is permanent. Workflows using the deleted credential will fail on their next run.
+Credential deletion is permanent. Agents using the deleted credential will fail on their next run.
</Warning>
---
diff --git a/docs/developers/credentials/troubleshooting-login.mdx b/docs/developers/credentials/troubleshooting-login.mdx
index 37b25b35b..8b2ced0c3 100644
--- a/docs/developers/credentials/troubleshooting-login.mdx
+++ b/docs/developers/credentials/troubleshooting-login.mdx
@@ -27,7 +27,7 @@ Login failures are the most common issue in web automation. This guide covers th
**Symptoms:** Task completes but login never happened. The final screenshot shows the login page.
**Causes:**
-- Credential parameter not linked to workflow
+- Credential parameter not linked to agent
- Wrong `credential_id` referenced
- Vault connection failed
@@ -40,7 +40,7 @@ curl -X GET "https://api.skyvern.com/v1/credentials/cred_xyz789" \
-H "x-api-key: $SKYVERN_API_KEY"
```
-2. Check workflow parameter configuration to ensure the credential parameter is linked to a Login block
+2. Check agent parameter configuration to ensure the credential parameter is linked to a Login block
3. For vault integrations (Bitwarden, 1Password), verify connectivity:
- Check vault credentials are valid
diff --git a/docs/developers/debugging/faq.mdx b/docs/developers/debugging/faq.mdx
index 164dfe0d5..ef8678416 100644
--- a/docs/developers/debugging/faq.mdx
+++ b/docs/developers/debugging/faq.mdx
@@ -1,7 +1,7 @@
---
title: Frequently Asked Questions
subtitle: Common questions and answers from the Skyvern community
-description: Answers to common Skyvern questions covering troubleshooting failed tasks, workflow parameters, credentials, scheduling, proxy configuration, API polling, data extraction, and LLM model selection.
+description: Answers to common Skyvern questions covering troubleshooting failed tasks, agent parameters, credentials, scheduling, proxy configuration, API polling, data extraction, and LLM model selection.
slug: developers/debugging/faq
keywords:
- FAQ
@@ -51,7 +51,7 @@ Tasks time out when they exceed `max_steps` (default: 50). This happens when:
**Fixes:**
- Increase `max_steps` in your task parameters
- Add explicit completion criteria: "COMPLETE when you see 'Order confirmed'"
-- Break complex tasks into multiple workflow blocks
+- Break complex tasks into multiple agent blocks
</Accordion>
<Accordion title="Why can't Skyvern find an element on the page?">
@@ -83,10 +83,10 @@ Common causes:
---
-## Workflows
+## Agents
-<Accordion title="How do I pass parameters to a workflow?">
-Define parameters in the workflow editor, then pass them when starting a run:
+<Accordion title="How do I pass parameters to an agent?">
+Define parameters in the agent editor, then pass them when starting a run:
```python
result = await client.run_workflow(
@@ -98,27 +98,27 @@ result = await client.run_workflow(
)
```
-Parameters are available in prompts using `{{ parameter_name }}` syntax. See [Workflow Parameters](/cloud/building-workflows/add-parameters) for details.
+Parameters are available in prompts using `{{ parameter_name }}` syntax. See [Agent Parameters](/cloud/building-agents/add-parameters) for details.
</Accordion>
-<Accordion title="How do I use credentials in a workflow?">
+<Accordion title="How do I use credentials in an agent?">
1. **Store credentials**: Go to Settings > Credentials and add your login
-2. **Reference in workflow**: Select the credential in the Login block's credential dropdown
+2. **Reference in agent**: Select the credential in the Login block's credential dropdown
3. **Never hardcode**: Don't put passwords directly in prompts
The AI will automatically fill the credential fields when it encounters a login form. See [Credentials](/sdk-reference/credentials) for setup instructions.
</Accordion>
-<Accordion title="Can I run workflows on a schedule?">
-Yes. Skyvern has built-in cron-based scheduling for workflows. You define a cron expression and timezone, and Skyvern triggers the workflow automatically at each interval.
+<Accordion title="Can I run agents on a schedule?">
+Yes. Skyvern has built-in cron-based scheduling for agents. You define a cron expression and timezone, and Skyvern triggers the agent automatically at each interval.
-- **Cloud UI**: Create and manage schedules from the [Schedules page](/cloud/building-workflows/scheduling)
-- **API**: Use the [scheduling API](/cloud/building-workflows/run-from-code#create-a-schedule) to create, update, enable/disable, and delete schedules programmatically
+- **Cloud UI**: Create and manage schedules from the [Schedules page](/cloud/building-agents/scheduling)
+- **API**: Use the [scheduling API](/cloud/building-agents/run-from-code#create-a-schedule) to create, update, enable/disable, and delete schedules programmatically
Scheduled runs appear in [Run History](/cloud/viewing-results/run-history) with a calendar icon badge. Set up a [webhook](/developers/going-to-production/webhooks) to get notified when scheduled runs complete.
</Accordion>
-<Accordion title="Why isn't my workflow using the parameter values I passed?">
+<Accordion title="Why isn't my agent using the parameter values I passed?">
Make sure you're using the parameter placeholder syntax correctly:
- **Correct:** `{{ parameter_name }}`
@@ -126,14 +126,14 @@ Make sure you're using the parameter placeholder syntax correctly:
Also verify:
- The parameter name matches exactly (case-sensitive)
-- The parameter is defined in the workflow's parameter list
+- The parameter is defined in the agent's parameter list
- You're passing the parameter when starting the run, not after
</Accordion>
-<Accordion title="How do I run workflows sequentially with the same credentials?">
+<Accordion title="How do I run agents sequentially with the same credentials?">
Use the "Prevent Overlapping Runs" option with a credential key:
-1. Enable "Prevent Overlapping Runs" in workflow settings
+1. Enable "Prevent Overlapping Runs" in agent settings
2. Set the sequential key to your credential identifier
3. Skyvern will queue runs that share the same credential
@@ -175,7 +175,7 @@ Available locations include `RESIDENTIAL_US`, `RESIDENTIAL_UK`, `RESIDENTIAL_ISP
<Accordion title="Can I increase the max steps limit beyond 75?">
Yes. Contact support to increase the limit for your account. Higher limits may incur additional costs.
-Alternatively, break complex tasks into multiple workflow blocks, each with its own step budget.
+Alternatively, break complex tasks into multiple agent blocks, each with its own step budget.
</Accordion>
---
@@ -218,7 +218,7 @@ print(run.recording_url) # https://skyvern-artifacts.s3.amazonaws.com/.../recor
Note: Signed URLs expire after 24 hours. Request fresh URLs if expired.
</Accordion>
-<Accordion title="How do I trigger a workflow via API?">
+<Accordion title="How do I trigger an agent via API?">
Use the `run_workflow` method:
```python
@@ -229,7 +229,7 @@ result = await client.run_workflow(
print(result.run_id) # wr_789012
```
-The workflow starts asynchronously. Poll the run status or configure a webhook to track completion.
+The agent starts asynchronously. Poll the run status or configure a webhook to track completion.
</Accordion>
---
@@ -251,7 +251,7 @@ Watch the `recording` artifact to see exactly what happened during login.
Options to bypass CAPTCHAs:
1. **Browser profile**: Create a profile with an authenticated session that skips login entirely
-2. **Human interaction block**: Pause the workflow for manual CAPTCHA solving
+2. **Human interaction block**: Pause the agent for manual CAPTCHA solving
3. **Residential proxy**: Use `RESIDENTIAL_ISP` for static IPs that sites trust more
Skyvern has built-in CAPTCHA solving for common types, but some sites use advanced anti-bot measures.
@@ -260,7 +260,7 @@ Skyvern has built-in CAPTCHA solving for common types, but some sites use advanc
<Accordion title="How do I set up 2FA/TOTP?">
1. Go to Settings > Credentials
2. Create a new TOTP credential with your authenticator secret
-3. Reference the TOTP credential in your workflow's login block
+3. Reference the TOTP credential in your agent's login block
The AI will automatically fetch and enter the TOTP code when it encounters a 2FA prompt. See [TOTP Setup](/developers/credentials/totp) for detailed instructions.
</Accordion>
@@ -296,7 +296,7 @@ Sites may detect automation through:
Use browser profiles:
1. Create a browser profile in Settings > Browser Profiles
-2. Log in manually or via a workflow
+2. Log in manually or via an agent
3. Reference the `browser_profile_id` in subsequent runs
The profile preserves cookies, localStorage, and session state across runs.
diff --git a/docs/developers/debugging/observability-with-laminar.mdx b/docs/developers/debugging/observability-with-laminar.mdx
index 8ef34e59f..8e4d16463 100644
--- a/docs/developers/debugging/observability-with-laminar.mdx
+++ b/docs/developers/debugging/observability-with-laminar.mdx
@@ -1,7 +1,7 @@
---
title: Observability with Laminar
subtitle: Add observability to your Skyvern automations with Laminar
-description: Integrate Laminar observability into Skyvern to capture traces of automation runs, track LLM call latency and token usage, monitor failure rates, and debug performance across tasks and workflows.
+description: Integrate Laminar observability into Skyvern to capture traces of automation runs, track LLM call latency and token usage, monitor failure rates, and debug performance across tasks and agents.
slug: developers/debugging/observability-with-laminar
keywords:
- Laminar
diff --git a/docs/developers/debugging/troubleshooting-guide.mdx b/docs/developers/debugging/troubleshooting-guide.mdx
index be0d9dc83..a17f8d37c 100644
--- a/docs/developers/debugging/troubleshooting-guide.mdx
+++ b/docs/developers/debugging/troubleshooting-guide.mdx
@@ -198,7 +198,7 @@ See [Using Artifacts](/developers/debugging/using-artifacts) for the full list o
**Fix:**
- Increase `max_steps` if the task genuinely needs more steps
- Add explicit completion criteria: "COMPLETE when you see 'Order confirmed'"
-- Break complex tasks into multiple workflow blocks
+- Break complex tasks into multiple agent blocks
</Accordion>
<Accordion title="Run stuck in queued state">
@@ -330,7 +330,7 @@ See [Using Artifacts](/developers/debugging/using-artifacts) for the full list o
- Set language in URL: `https://example.com/en/`
</Accordion>
-<Accordion title="Workflow gets stuck in a loop">
+<Accordion title="Agent gets stuck in a loop">
**Symptom:** Recording shows AI repeating the same actions without progressing.
**Check:** `recording` (what pattern is repeating?) and conditional block exit conditions
diff --git a/docs/developers/debugging/using-artifacts.mdx b/docs/developers/debugging/using-artifacts.mdx
index ab9925c65..ba47d0140 100644
--- a/docs/developers/debugging/using-artifacts.mdx
+++ b/docs/developers/debugging/using-artifacts.mdx
@@ -27,13 +27,13 @@ Looking for a specific artifact type? Jump to the [artifact types reference](#ar
## Before you start
-You need a `run_id` to retrieve artifacts. You get this when you [run a task](/running-automations/run-a-task) or workflow.
+You need a `run_id` to retrieve artifacts. You get this when you [run a task](/running-automations/run-a-task) or agent.
---
## Retrieve artifacts
-Use `get_run_artifacts` with the `run_id` from your task or workflow run:
+Use `get_run_artifacts` with the `run_id` from your task or agent run:
<CodeGroup>
```python Python
diff --git a/docs/developers/features/browser-sessions.mdx b/docs/developers/features/browser-sessions.mdx
index ca20d1806..bc7cb5536 100644
--- a/docs/developers/features/browser-sessions.mdx
+++ b/docs/developers/features/browser-sessions.mdx
@@ -1,6 +1,6 @@
---
title: Browser Sessions
-subtitle: Keep a live browser open across multiple tasks and workflows
+subtitle: Keep a live browser open across multiple tasks and agents
description: Skyvern browser sessions are live browser instances that persist cookies, local storage, and page state across runs. Use them for back-to-back tasks, human-in-the-loop flows, and real-time agents.
slug: developers/features/browser-sessions
icon: window-restore
@@ -24,7 +24,7 @@ A Browser Session is a live browser instance that Skyvern keeps running between
**Real-time agents:** keep a browser open for hours while the agent responds to events as they happen.
-**Task and workflow chaining:** run tasks and workflows through the same live browser instance, mixing code-driven and UI-defined automation in a single session.
+**Task and agent chaining:** run tasks and agents through the same live browser instance, mixing code-driven and UI-defined automation in a single session.
## Configuration
diff --git a/docs/developers/features/code-caching.mdx b/docs/developers/features/code-caching.mdx
index 5a1a07501..d0c3bfadc 100644
--- a/docs/developers/features/code-caching.mdx
+++ b/docs/developers/features/code-caching.mdx
@@ -15,32 +15,32 @@ keywords:
- progressive caching
---
-When Skyvern's agent completes a task or workflow, it records the actions it took and generates reusable code from them. Later runs can execute that cached code directly, skipping LLM inference and screenshot analysis entirely. This makes cached runs faster, cheaper, and deterministic. If the cached code fails because a page changed, Skyvern falls back to the agent automatically and regenerates the cache.
+When Skyvern's agent completes a task or agent run, it records the actions it took and generates reusable code from them. Later runs can execute that cached code directly, skipping LLM inference and screenshot analysis entirely. This makes cached runs faster, cheaper, and deterministic. If the cached code fails because a page changed, Skyvern falls back to the agent automatically and regenerates the cache.
## How it works
-The first run uses the agent as normal. Create a workflow and run it with `run_with="agent"` so Skyvern can record the successful browser actions as generated code.
+The first run uses the agent as normal. Create an agent and run it with `run_with="agent"` so Skyvern can record the successful browser actions as generated code.
On subsequent runs, pass `run_with="code"` to execute the cached code directly. No screenshots, no LLM reasoning, just the recorded action sequence replaying against the page.
If the cached code hits something unexpected (a layout change, a new field, a missing element), Skyvern re-runs with the full agent and regenerates the cache. You don't need to handle this yourself.
<Note>
-The SDK and Cloud UI default to `skyvern-1.0` for new task creation. Use workflows plus `run_with="code"` for cached replays.
+The SDK and Cloud UI default to `skyvern-1.0` for new task creation. Use agents plus `run_with="code"` for cached replays.
</Note>
## What gets cached
**Tasks** cache the full action sequence the agent took: clicks, form fills, extractions, and navigation.
-**Workflows** cache per block. Each block that successfully executes gets its own cached script, so a partially-cached workflow still saves time on the blocks that have been seen before.
+**Agents** cache per block. Each block that successfully executes gets its own cached script, so a partially-cached agent still saves time on the blocks that have been seen before.
-**Progressive caching** handles workflows with conditionals. Run 1 covers branch A, run 2 covers branch B, and so on. Previous caches are preserved, so coverage builds up over time.
+**Progressive caching** handles agents with conditionals. Run 1 covers branch A, run 2 covers branch B, and so on. Previous caches are preserved, so coverage builds up over time.
**Not cached:** conditional evaluation blocks, wait blocks, and code blocks always run live because their behavior depends on runtime state.
<Tip>
-Pair cached code with [scheduled workflows](/cloud/building-workflows/scheduling) for cheap, reliable recurring runs. The first scheduled run builds the cache, and every subsequent run executes from it.
+Pair cached code with [scheduled agents](/cloud/building-agents/scheduling) for cheap, reliable recurring runs. The first scheduled run builds the cache, and every subsequent run executes from it.
</Tip>
## Learn more
@@ -53,10 +53,10 @@ Pair cached code with [scheduled workflows](/cloud/building-workflows/scheduling
Use `run_with: code` plus `max_steps` and engine tiers to manage costs.
</Card>
<Card
- title="Scheduling workflows"
- href="/cloud/building-workflows/scheduling"
+ title="Scheduling agents"
+ href="/cloud/building-agents/scheduling"
>
- Run cached workflows on a cron schedule.
+ Run cached agents on a cron schedule.
</Card>
<Card
title="Reliability tips"
@@ -66,8 +66,8 @@ Pair cached code with [scheduled workflows](/cloud/building-workflows/scheduling
</Card>
<Card
title="Run from code"
- href="/cloud/building-workflows/run-from-code"
+ href="/cloud/building-agents/run-from-code"
>
- Trigger and monitor cached workflows from your own code.
+ Trigger and monitor cached agents from your own code.
</Card>
</CardGroup>
diff --git a/docs/developers/features/proxy-and-geo-targeting.mdx b/docs/developers/features/proxy-and-geo-targeting.mdx
index 4d0b66062..c2e8358d3 100644
--- a/docs/developers/features/proxy-and-geo-targeting.mdx
+++ b/docs/developers/features/proxy-and-geo-targeting.mdx
@@ -26,7 +26,7 @@ For services that require a stable IP across a session, `RESIDENTIAL_ISP` provid
## How it's applied
-**Per task:** pass `proxy_location` in the run request. **Per workflow:** set a default on the workflow and override on any individual run. **Per session:** lock a proxy to a [browser session](/developers/optimization/browser-sessions) so every operation in that session shares the same IP.
+**Per task:** pass `proxy_location` in the run request. **Per agent:** set a default on the agent and override on any individual run. **Per session:** lock a proxy to a [browser session](/developers/optimization/browser-sessions) so every operation in that session shares the same IP.
## When to use it
diff --git a/docs/developers/getting-started/core-concepts.mdx b/docs/developers/getting-started/core-concepts.mdx
index f8c0c386f..54b044d1a 100644
--- a/docs/developers/getting-started/core-concepts.mdx
+++ b/docs/developers/getting-started/core-concepts.mdx
@@ -1,11 +1,11 @@
---
title: Core Concepts
subtitle: The building blocks of Skyvern automations
-description: Learn about tasks, workflows, browser sessions, credentials, and other building blocks that make up Skyvern automations.
+description: Learn about tasks, agents, browser sessions, credentials, and other building blocks that make up Skyvern automations.
slug: developers/getting-started/core-concepts
keywords:
- task
- - workflow
+ - agent
- browser session
- browser profile
- credential
diff --git a/docs/developers/getting-started/quickstart.mdx b/docs/developers/getting-started/quickstart.mdx
index 602afef32..b577ee8bd 100644
--- a/docs/developers/getting-started/quickstart.mdx
+++ b/docs/developers/getting-started/quickstart.mdx
@@ -339,9 +339,9 @@ If you also selected Claude Code during setup, start your local frontend dev ser
Store credentials securely for sites that require authentication
</Card>
<Card
- title="Build Workflows"
+ title="Build Agents"
icon="diagram-project"
- href="/cloud/building-workflows/build-a-workflow"
+ href="/cloud/building-agents/build-an-agent"
>
Chain multiple steps together for complex automations
</Card>
diff --git a/docs/developers/going-to-production/error-handling.mdx b/docs/developers/going-to-production/error-handling.mdx
index ce64df261..ffd6e0cd1 100644
--- a/docs/developers/going-to-production/error-handling.mdx
+++ b/docs/developers/going-to-production/error-handling.mdx
@@ -1,7 +1,7 @@
---
title: Error Handling
subtitle: Build systems that detect, classify, and recover from failures
-description: Detect, classify, and recover from task and workflow failures using run status, failure_reason, custom error_code_mapping, and validation blocks. Build programmatic error handling with retry logic and branching.
+description: Detect, classify, and recover from task and agent failures using run status, failure_reason, custom error_code_mapping, and validation blocks. Build programmatic error handling with retry logic and branching.
slug: developers/going-to-production/error-handling
keywords:
- failure_reason
@@ -15,7 +15,7 @@ keywords:
- timed_out
---
-Skyvern lets you make your workflows and tasks handle errors gracefully instead of failing silently.
+Skyvern lets you make your agents and tasks handle errors gracefully instead of failing silently.
Every run returns a `status`. When it's not `completed`, you need to know what went wrong and respond programmatically. The flow is:
@@ -144,9 +144,9 @@ done
```
</CodeGroup>
-### For workflows
+### For agents
-Same polling pattern works for workflow runs:
+Same polling pattern works for agent runs:
<CodeGroup>
```python Python
@@ -272,7 +272,7 @@ fi
```
</CodeGroup>
-### For workflows
+### For agents
<CodeGroup>
```python Python
@@ -378,12 +378,12 @@ curl -X POST "https://api.skyvern.com/v1/run/tasks" \
```
</CodeGroup>
-### In workflows
+### In agents
Add `error_code_mapping` to individual blocks (navigation, task, validation):
<Note>
-The JSON examples below include comments (`//`) for clarity. Remove comments before using in actual workflow definitions; JSON does not support comments.
+The JSON examples below include comments (`//`) for clarity. Remove comments before using in actual agent definitions; JSON does not support comments.
</Note>
<CodeGroup>
@@ -594,7 +594,7 @@ async function runWithErrorHandling(retries = 1) {
## Validation blocks as assertions
-Validation blocks are assertions that check conditions at critical points, like unit test assertions. If validation fails, the workflow terminates immediately with your error code instead of continuing and failing later with a confusing error.
+Validation blocks are assertions that check conditions at critical points, like unit test assertions. If validation fails, the agent terminates immediately with your error code instead of continuing and failing later with a confusing error.
Use validation blocks after steps where you need to confirm success before proceeding:
@@ -664,10 +664,10 @@ blocks:
| Parameter | Purpose |
|-----------|---------|
| `complete_criterion` | Condition that must be true to continue to the next block |
-| `terminate_criterion` | Condition that stops the workflow immediately |
+| `terminate_criterion` | Condition that stops the agent immediately |
| `error_code_mapping` | Maps termination conditions to your error codes |
-If `verify_login` sees a login error, the workflow terminates with `output.error = "login_failed"`. Your Step 4 code handles it the same way as any other error code.
+If `verify_login` sees a login error, the agent terminates with `output.error = "login_failed"`. Your Step 4 code handles it the same way as any other error code.
---
diff --git a/docs/developers/going-to-production/proxy-geolocation.mdx b/docs/developers/going-to-production/proxy-geolocation.mdx
index d010c0489..3fb915229 100644
--- a/docs/developers/going-to-production/proxy-geolocation.mdx
+++ b/docs/developers/going-to-production/proxy-geolocation.mdx
@@ -1,7 +1,7 @@
---
title: Proxy & Geolocation
subtitle: Route browser traffic through residential proxies worldwide
-description: Route Skyvern browser traffic through residential proxies in 20 countries to bypass geo-restrictions, avoid bot detection, and access region-locked content. Configure proxy_location for tasks, workflows, and browser sessions.
+description: Route Skyvern browser traffic through residential proxies in 20 countries to bypass geo-restrictions, avoid bot detection, and access region-locked content. Configure proxy_location for tasks, agents, and browser sessions.
slug: developers/going-to-production/proxy-geolocation
keywords:
- proxy_location
@@ -427,7 +427,7 @@ Proxy routing is only available in Skyvern Cloud. Self-hosted deployments requir
## Set `proxy_location`
-Pass `proxy_location` when creating or running tasks, workflows or browser sessions to route browser traffic through a specific region.
+Pass `proxy_location` when creating or running tasks, agents or browser sessions to route browser traffic through a specific region.
<ProxyMapSelector />
@@ -464,7 +464,7 @@ curl -X POST "https://api.skyvern.com/v1/run/tasks" \
```
</CodeGroup>
-For workflows, set a default `proxy_location` when creating the workflow, then you can also override it when starting the run:
+For agents, set a default `proxy_location` when creating the agent, then you can also override it when starting the run:
<CodeGroup>
```python Python
diff --git a/docs/developers/going-to-production/reliability-tips.mdx b/docs/developers/going-to-production/reliability-tips.mdx
index 0e0f23d82..942929c21 100644
--- a/docs/developers/going-to-production/reliability-tips.mdx
+++ b/docs/developers/going-to-production/reliability-tips.mdx
@@ -160,7 +160,7 @@ TERMINATE if any validation error cannot be resolved.
## Validation strategies
-Workflows can silently produce wrong results. The AI might fill a form with incorrect data, navigate to the wrong page, or extract stale information. Validation blocks let you assert conditions at critical points and fail fast when something goes wrong, rather than discovering the problem downstream.
+Agents can silently produce wrong results. The AI might fill a form with incorrect data, navigate to the wrong page, or extract stale information. Validation blocks let you assert conditions at critical points and fail fast when something goes wrong, rather than discovering the problem downstream.
### Add validation blocks at critical points
@@ -215,7 +215,7 @@ if result.output["submitted_email"] != expected_email:
Loops are especially prone to cascading failures: when one iteration fails, it can leave the browser in an unexpected state that breaks subsequent iterations. For example, if iteration 3 navigates to an error page and fails, iteration 4 starts from that error page instead of the expected list view, causing it to fail too. One bad item can take down your entire loop.
-Use a For Loop when you have a known list of items before the loop begins. Use a While Loop when the workflow should keep running until page state changes, such as paginating while a Next button is enabled or polling until a status changes. While loops need an especially clear exit condition because the number of iterations is discovered at run time.
+Use a For Loop when you have a known list of items before the loop begins. Use a While Loop when the agent should keep running until page state changes, such as paginating while a Next button is enabled or polling until a status changes. While loops need an especially clear exit condition because the number of iterations is discovered at run time.
### Always set `continue_on_failure`
@@ -289,15 +289,15 @@ The first condition check uses `current_index == 0` to enter the loop before `ex
## Session timeouts and human-in-the-loop
-Browser sessions have a default timeout. If you're using human-in-the-loop workflows where a person must approve an action before proceeding, the session can expire while waiting for approval, especially if the approver is slow or in a different timezone.
+Browser sessions have a default timeout. If you're using human-in-the-loop agents where a person must approve an action before proceeding, the session can expire while waiting for approval, especially if the approver is slow or in a different timezone.
-**Symptoms:** Runs that worked during testing fail in production with session expiry errors. The workflow waits for human approval, but by the time approval comes, the browser session has timed out.
+**Symptoms:** Runs that worked during testing fail in production with session expiry errors. The agent waits for human approval, but by the time approval comes, the browser session has timed out.
**Solutions:**
-1. **Increase session timeout**: Set a longer `timeout` when creating browser sessions for workflows that include human approval steps
-2. **Remove the human step for time-sensitive flows**: If session expiry is causing failures, consider making the workflow fully automated and reviewing results after completion
-3. **Split into multiple workflows**: Run the pre-approval steps, wait for human approval outside Skyvern, then trigger a second workflow for post-approval steps using a browser profile to maintain login state
+1. **Increase session timeout**: Set a longer `timeout` when creating browser sessions for agents that include human approval steps
+2. **Remove the human step for time-sensitive flows**: If session expiry is causing failures, consider making the agent fully automated and reviewing results after completion
+3. **Split into multiple agents**: Run the pre-approval steps, wait for human approval outside Skyvern, then trigger a second agent for post-approval steps using a browser profile to maintain login state
```python
# Longer timeout for human-in-the-loop workflows
@@ -308,7 +308,7 @@ session = await client.create_browser_session(
```
<Note>
-For workflows with predictable human approval times, schedule runs to arrive in the approver's inbox during working hours when they can act quickly.
+For agents with predictable human approval times, schedule runs to arrive in the approver's inbox during working hours when they can act quickly.
</Note>
---
@@ -369,7 +369,7 @@ When a run fails:
| **Loop stuck** | No reset between iterations | Add reset block at loop start |
| **Autocomplete cycling** | AI second-guessing dropdown selections | Add "select and move on; don't modify" to prompt |
| **Task navigates too far** | Task block continues until goal complete | Use Action/Navigation block for single-step actions |
-| **Session expired** | Human-in-the-loop timeout | Increase timeout or split into multiple workflows |
+| **Session expired** | Human-in-the-loop timeout | Increase timeout or split into multiple agents |
| **Max steps reached** | Complex page or AI retrying actions | Increase `max_steps_per_run` or simplify the goal |
### When to adjust prompts vs file a bug
@@ -397,9 +397,9 @@ When a run fails:
Map errors to custom codes for programmatic handling
</Card>
<Card
- title="Workflow Blocks Reference"
+ title="Agent Blocks Reference"
icon="cube"
- href="/cloud/building-workflows/configure-blocks"
+ href="/cloud/building-agents/configure-blocks"
>
Detailed documentation for validation and other blocks
</Card>
diff --git a/docs/developers/going-to-production/webhooks.mdx b/docs/developers/going-to-production/webhooks.mdx
index bb9604780..d64024a15 100644
--- a/docs/developers/going-to-production/webhooks.mdx
+++ b/docs/developers/going-to-production/webhooks.mdx
@@ -1,7 +1,7 @@
---
title: Webhooks
-subtitle: Get notified when tasks and workflows complete
-description: Configure webhook URLs for tasks and workflows to receive notifications when runs reach terminal status. Includes payload structure, HMAC-SHA256 signature verification, failure handling, and retry mechanisms.
+subtitle: Get notified when tasks and agents complete
+description: Configure webhook URLs for tasks and agents to receive notifications when runs reach terminal status. Includes payload structure, HMAC-SHA256 signature verification, failure handling, and retry mechanisms.
slug: developers/going-to-production/webhooks
keywords:
- webhook_url
@@ -14,7 +14,7 @@ keywords:
- failure handling
---
-Workflows and task runs are asynchronous. When you call `run_task` or `run_workflow`, the API returns immediately with a run ID, but the actual execution happens in the background and can take variable time.
+Agents and task runs are asynchronous. When you call `run_task` or `run_workflow`, the API returns immediately with a run ID, but the actual execution happens in the background and can take variable time.
Instead of polling the `get_runs` endpoint, you can use Webhooks to get notified when they finish. Webhooks fire only when a run reaches a terminal status: `completed`, `failed`, `terminated`, `timed_out`, or `canceled`.
@@ -56,8 +56,8 @@ curl -X POST "https://api.skyvern.com/v1/run/tasks" \
```
</CodeGroup>
-### For workflows
-Set a default webhook when creating the workflow, or override it per-run:
+### For agents
+Set a default webhook when creating the agent, or override it per-run:
<CodeGroup>
```python Python
@@ -156,7 +156,7 @@ curl -X POST "https://api.skyvern.com/v1/run/workflows" \
</CodeGroup>
<Info>
-When creating a workflow, use `webhook_callback_url` inside `json_definition`; this sets the default for all runs. When running a workflow, use `webhook_url` at the top level to override for that specific run.
+When creating an agent, use `webhook_callback_url` inside `json_definition`; this sets the default for all runs. When running an agent, use `webhook_url` at the top level to override for that specific run.
</Info>
**Quick reference:**
@@ -164,11 +164,11 @@ When creating a workflow, use `webhook_callback_url` inside `json_definition`; t
| Context | Parameter | Location |
|---------|-----------|----------|
| Task run | `webhook_url` | Top-level parameter |
-| Workflow creation | `webhook_callback_url` | Inside `json_definition` |
-| Workflow run (override) | `webhook_url` | Top-level parameter |
+| Agent creation | `webhook_callback_url` | Inside `json_definition` |
+| Agent run (override) | `webhook_url` | Top-level parameter |
<Warning>
-**Watch the parameter names.** Using `webhook_url` when creating a workflow (instead of `webhook_callback_url` inside `json_definition`) silently results in no webhook being sent. The API won't return an error. Your runs will just complete without notifications.
+**Watch the parameter names.** Using `webhook_url` when creating an agent (instead of `webhook_callback_url` inside `json_definition`) silently results in no webhook being sent. The API won't return an error. Your runs will just complete without notifications.
</Warning>
---
@@ -462,7 +462,7 @@ Even when webhook delivery fails, the task's `output` field may still contain ex
- **Server returns an error**: Your endpoint received the payload but responded with a non-2xx status code (e.g., 500). Check your server logs to identify the issue.
- **Signature validation fails**: If your verification logic rejects the request, make sure you're validating against the raw request body, not parsed-and-re-serialized JSON (re-serializing changes the byte representation). Also verify you're using the same API key that created the run.
-**Recommended pattern:** Always have a fallback polling mechanism for critical workflows. If you don't receive a webhook within your expected window, call `get_run` to check if the run completed and retrieve the data directly.
+**Recommended pattern:** Always have a fallback polling mechanism for critical agents. If you don't receive a webhook within your expected window, call `get_run` to check if the run completed and retrieve the data directly.
### Retrying webhooks
diff --git a/docs/developers/optimization/browser-profiles.mdx b/docs/developers/optimization/browser-profiles.mdx
index d0c6fb6e1..9979c6f95 100644
--- a/docs/developers/optimization/browser-profiles.mdx
+++ b/docs/developers/optimization/browser-profiles.mdx
@@ -1,7 +1,7 @@
---
title: Browser Profiles
subtitle: Save and reuse authenticated browser state across runs
-description: Save browser state snapshots including cookies, localStorage, and session files as reusable profiles. Skip login steps and restore authenticated state instantly across workflow runs.
+description: Save browser state snapshots including cookies, localStorage, and session files as reusable profiles. Skip login steps and restore authenticated state instantly across agent runs.
slug: developers/optimization/browser-profiles
keywords:
- create_browser_profile
@@ -16,27 +16,27 @@ keywords:
A **Browser Profile** is a saved snapshot of browser state (cookies, localStorage, and session files) that you can reuse across multiple runs. Profiles let you skip login steps and restore authenticated state instantly.
Profiles are ideal when you:
-- Run the same workflow repeatedly with the same account (daily data extraction, scheduled reports)
-- Want multiple workflows to share the same authenticated state
+- Run the same agent repeatedly with the same account (daily data extraction, scheduled reports)
+- Want multiple agents to share the same authenticated state
- Need to avoid repeated authentication to save time and steps
---
## How profiles work
-When a workflow runs with `persist_browser_session=true`, Skyvern archives the browser state (cookies, storage, session files) after the run completes. This archiving happens asynchronously in the background. Once the archive is ready, you can create a profile from it, then pass that profile to future workflow runs to restore the saved state.
+When an agent runs with `persist_browser_session=true`, Skyvern archives the browser state (cookies, storage, session files) after the run completes. This archiving happens asynchronously in the background. Once the archive is ready, you can create a profile from it, then pass that profile to future agent runs to restore the saved state.
---
## Create a Browser Profile
-Create a workflow with `persist_browser_session=true` in the workflow definition, run it, wait for completion, then create a profile from the run. Session archiving happens asynchronously, so add brief retry logic when creating the profile.
+Create an agent with `persist_browser_session=true` in the agent definition, run it, wait for completion, then create a profile from the run. Session archiving happens asynchronously, so add brief retry logic when creating the profile.
<Note>
-`persist_browser_session` must be set when **creating the workflow**, not when running it. It is a workflow definition property, not a runtime parameter.
+`persist_browser_session` must be set when **creating the agent**, not when running it. It is an agent definition property, not a runtime parameter.
</Note>
-### From a workflow run
+### From an agent run
<CodeGroup>
```python Python
@@ -224,10 +224,10 @@ done
### From a browser session
-You can also create a profile from a [Browser Session](/developers/optimization/browser-sessions) that was used inside a workflow with `persist_browser_session=true`. After the workflow run completes and the session is closed, pass the session ID instead of the workflow run ID.
+You can also create a profile from a [Browser Session](/developers/optimization/browser-sessions) that was used inside an agent with `persist_browser_session=true`. After the agent run completes and the session is closed, pass the session ID instead of the workflow run ID.
<Warning>
-Only sessions that were part of a workflow with `persist_browser_session=true` produce an archive. A session created with `create_browser_session()` alone does not archive its state. Archiving happens asynchronously after the session closes, so add retry logic.
+Only sessions that were part of an agent with `persist_browser_session=true` produce an archive. A session created with `create_browser_session()` alone does not archive its state. Archiving happens asynchronously after the session closes, so add retry logic.
</Warning>
<CodeGroup>
@@ -322,14 +322,14 @@ done
| Parameter | Type | Description |
|-----------|------|-------------|
| `name` | string | Required. Display name for the profile. Must be unique within your organization |
-| `browser_session_id` | string | ID of the closed browser session (starts with `pbs_`). The session must have been part of a workflow with `persist_browser_session=true` |
+| `browser_session_id` | string | ID of the closed browser session (starts with `pbs_`). The session must have been part of an agent with `persist_browser_session=true` |
| `description` | string | Optional description of the profile's purpose |
---
## Use a Browser Profile
-Pass `browser_profile_id` when running a workflow to restore the saved state. Skyvern restores cookies, localStorage, and session files before the first step runs.
+Pass `browser_profile_id` when running an agent to restore the saved state. Skyvern restores cookies, localStorage, and session files before the first step runs.
<CodeGroup>
```python Python
@@ -398,19 +398,19 @@ curl -X POST "https://api.skyvern.com/v1/run/workflows" \
```
<Note>
-`browser_profile_id` is supported for workflows only. It is not available for standalone tasks via `run_task`. You also cannot use both `browser_profile_id` and `browser_session_id` in the same request.
+`browser_profile_id` is supported for agents only. It is not available for standalone tasks via `run_task`. You also cannot use both `browser_profile_id` and `browser_session_id` in the same request.
</Note>
---
## Tutorial: save and reuse browsing state
-This walkthrough demonstrates the full profile lifecycle: create a workflow that saves browser state, capture that state as a profile, then reuse it in a second workflow. Each step shows the code and the actual API response.
+This walkthrough demonstrates the full profile lifecycle: create an agent that saves browser state, capture that state as a profile, then reuse it in a second agent. Each step shows the code and the actual API response.
<Steps>
- <Step title="Create a workflow with persist_browser_session">
+ <Step title="Create an agent with persist_browser_session">
- The workflow must have `persist_browser_session=true` so Skyvern archives the browser state after the run.
+ The agent must have `persist_browser_session=true` so Skyvern archives the browser state after the run.
<CodeGroup>
```python Python
@@ -492,9 +492,9 @@ This walkthrough demonstrates the full profile lifecycle: create a workflow that
</Step>
- <Step title="Run the workflow">
+ <Step title="Run the agent">
- Run the workflow and wait for it to complete. Skyvern opens a browser, executes the navigation block, then archives the browser state in the background.
+ Run the agent and wait for it to complete. Skyvern opens a browser, executes the navigation block, then archives the browser state in the background.
<CodeGroup>
```python Python
@@ -666,9 +666,9 @@ This walkthrough demonstrates the full profile lifecycle: create a workflow that
</Step>
- <Step title="Reuse the profile in a second workflow">
+ <Step title="Reuse the profile in a second agent">
- Pass `browser_profile_id` when running a workflow. Skyvern restores the saved cookies, localStorage, and session files before the first block runs. The second workflow starts with the browser state from step 2, no repeat navigation needed.
+ Pass `browser_profile_id` when running an agent. Skyvern restores the saved cookies, localStorage, and session files before the first block runs. The second agent starts with the browser state from step 2, no repeat navigation needed.
<CodeGroup>
```python Python
@@ -742,7 +742,7 @@ This walkthrough demonstrates the full profile lifecycle: create a workflow that
</Steps>
<Tip>
-In a real scenario, step 1 would be a login workflow that authenticates with a site. The saved profile then lets all future workflows skip the login step entirely.
+In a real scenario, step 1 would be a login agent that authenticates with a site. The saved profile then lets all future agents skip the login step entirely.
</Tip>
---
@@ -787,7 +787,7 @@ const badProfile = await client.createBrowserProfile({
### Refresh profiles periodically
-Session tokens and cookies expire. Re-run your login workflow and create fresh profiles before they go stale. Adding the date to the name makes it easy to track which profile is current.
+Session tokens and cookies expire. Re-run your login agent and create fresh profiles before they go stale. Adding the date to the name makes it easy to track which profile is current.
<CodeGroup>
```python Python
@@ -832,7 +832,7 @@ curl -X DELETE "https://api.skyvern.com/v1/browser_profiles/$OLD_PROFILE_ID" \
### Capture updated state after each run
-To capture state changes during a run (like token refreshes), the workflow must have `persist_browser_session=true` in its definition. This lets you create a fresh profile from each completed run.
+To capture state changes during a run (like token refreshes), the agent must have `persist_browser_session=true` in its definition. This lets you create a fresh profile from each completed run.
<CodeGroup>
```python Python
diff --git a/docs/developers/optimization/browser-sessions.mdx b/docs/developers/optimization/browser-sessions.mdx
index eee0775ea..4e0b6ac4b 100644
--- a/docs/developers/optimization/browser-sessions.mdx
+++ b/docs/developers/optimization/browser-sessions.mdx
@@ -1,7 +1,7 @@
---
title: Browser Sessions
-subtitle: Persist live browser state across multiple tasks and workflows
-description: Create and manage live browser sessions that persist cookies, local storage, and page state between task or workflow runs. Use sessions for back-to-back tasks, human-in-the-loop approval, and real-time agents.
+subtitle: Persist live browser state across multiple tasks and agents
+description: Create and manage live browser sessions that persist cookies, local storage, and page state between task or agent runs. Use sessions for back-to-back tasks, human-in-the-loop approval, and real-time agents.
slug: developers/optimization/browser-sessions
keywords:
- create_browser_session
@@ -14,7 +14,7 @@ keywords:
- real-time agent
---
-A **Browser Session** is a live browser instance that persists cookies, local storage, and page state between task or workflow runs. Think of it as keeping a browser tab open. Use sessions when you need back-to-back tasks to share state, human-in-the-loop approval, or real-time agents.
+A **Browser Session** is a live browser instance that persists cookies, local storage, and page state between task or agent runs. Think of it as keeping a browser tab open. Use sessions when you need back-to-back tasks to share state, human-in-the-loop approval, or real-time agents.
---
@@ -242,9 +242,9 @@ curl -s -X POST "https://api.skyvern.com/v1/browser_sessions/$SESSION_ID/close"
---
-## Run workflows with a session
+## Run agents with a session
-Pass `browser_session_id` to `run_workflow` to execute a workflow in an existing session. This is useful when you need to run a predefined workflow but want it to continue from your current browser state.
+Pass `browser_session_id` to `run_workflow` to execute an agent in an existing session. This is useful when you need to run a predefined agent but want it to continue from your current browser state.
<CodeGroup>
```python Python
@@ -581,9 +581,9 @@ curl -s -X POST "https://api.skyvern.com/v1/browser_sessions" \
```
</CodeGroup>
-### Use workflows for predetermined sequences
+### Use agents for predetermined sequences
-If your steps don't need pauses between them, a workflow runs them in a single browser instance without the overhead of creating and managing a session. Each task in a session incurs its own startup cost, while workflow blocks share one browser.
+If your steps don't need pauses between them, an agent runs them in a single browser instance without the overhead of creating and managing a session. Each task in a session incurs its own startup cost, while agent blocks share one browser.
<CodeGroup>
```python Python
@@ -691,7 +691,7 @@ Skyvern also offers [Browser Profiles](/developers/optimization/browser-profiles
| **Lifetime** | Minutes to hours | Days to months |
| **State** | Current page, cookies, open connections | Cookies, storage, session files |
| **Billing** | Charged while open | No cost when not in use |
-| **Best for** | Back-to-back tasks, human-in-the-loop, real-time agents | Repeated logins, scheduled workflows, shared auth state |
+| **Best for** | Back-to-back tasks, human-in-the-loop, real-time agents | Repeated logins, scheduled agents, shared auth state |
<Tip>
You can create a [Browser Profile](/developers/optimization/browser-profiles) from a completed session to save its authenticated state for future reuse.
diff --git a/docs/developers/optimization/cost-control.mdx b/docs/developers/optimization/cost-control.mdx
index c3b447902..b8386761e 100644
--- a/docs/developers/optimization/cost-control.mdx
+++ b/docs/developers/optimization/cost-control.mdx
@@ -77,7 +77,7 @@ curl -X POST "https://api.skyvern.com/v1/run/tasks" \
```
</CodeGroup>
-### For workflows
+### For agents
Pass `max_steps_override` as a parameter (Python) or `x-max-steps-override` header (TypeScript/cURL). This limits total steps across all blocks.
@@ -203,7 +203,7 @@ curl -X POST "https://api.skyvern.com/v1/run/tasks" \
</CodeGroup>
<Tip>
-Create a workflow when you need to re-trigger the automation later or [schedule it on a recurring cron](/cloud/building-workflows/scheduling).
+Create an agent when you need to re-trigger the automation later or [schedule it on a recurring cron](/cloud/building-agents/scheduling).
</Tip>
---
diff --git a/docs/developers/self-hosted/browser.mdx b/docs/developers/self-hosted/browser.mdx
index 87e349adf..9c8027b15 100644
--- a/docs/developers/self-hosted/browser.mdx
+++ b/docs/developers/self-hosted/browser.mdx
@@ -370,7 +370,7 @@ When enabled, browser console logs are captured in artifacts. Useful for debuggi
BROWSER_MAX_PAGES_NUMBER=10
```
-Limits the number of browser tabs Skyvern can open simultaneously. Increase if your workflows navigate multiple pages in parallel; decrease to reduce memory usage.
+Limits the number of browser tabs Skyvern can open simultaneously. Increase if your agents navigate multiple pages in parallel; decrease to reduce memory usage.
### Chrome policies
diff --git a/docs/developers/self-hosted/overview.mdx b/docs/developers/self-hosted/overview.mdx
index 830290e71..d17b94aeb 100644
--- a/docs/developers/self-hosted/overview.mdx
+++ b/docs/developers/self-hosted/overview.mdx
@@ -39,7 +39,7 @@ flowchart LR
| Component | Role |
|-----------|------|
| **Skyvern API Server** | Orchestrates tasks, processes LLM responses, stores results. Includes an embedded Playwright-managed Chromium browser that executes web automation. |
-| **Skyvern Web UI** | Browser-based dashboard for building workflows, running tasks, viewing recordings, and managing credentials. Docker Compose starts it alongside the API server. |
+| **Skyvern Web UI** | Browser-based dashboard for building agents, running tasks, viewing recordings, and managing credentials. Docker Compose starts it alongside the API server. |
| **PostgreSQL** | Stores task history, workflows, credentials, and organization data |
| **LLM Provider** | Analyzes screenshots and determines actions. You provide the API key (OpenAI, Anthropic, Azure OpenAI, Google Vertex AI, Amazon Bedrock, Groq, OpenRouter, or local via Ollama) |
diff --git a/docs/docs.json b/docs/docs.json
index 2ef40df55..337cfe016 100644
--- a/docs/docs.json
+++ b/docs/docs.json
@@ -63,19 +63,19 @@
]
},
{
- "group": "Building Workflows",
+ "group": "Building Agents",
"pages": [
- "cloud/building-workflows/build-a-workflow",
- "cloud/building-workflows/manage-workflows",
- "cloud/building-workflows/add-parameters",
- "cloud/building-workflows/run-a-workflow",
- "cloud/building-workflows/scheduling",
- "cloud/building-workflows/run-from-code"
+ "cloud/building-agents/build-an-agent",
+ "cloud/building-agents/manage-agents",
+ "cloud/building-agents/add-parameters",
+ "cloud/building-agents/run-an-agent",
+ "cloud/building-agents/scheduling",
+ "cloud/building-agents/run-from-code"
]
},
{
- "group": "Workflow Blocks",
- "pages": ["cloud/building-workflows/configure-blocks"]
+ "group": "Agent Blocks",
+ "pages": ["cloud/building-agents/configure-blocks"]
},
{
"group": "Running Tasks",
@@ -165,7 +165,7 @@
]
},
{
- "group": "Workflow Blocks",
+ "group": "Agent Blocks",
"pages": ["developers/browser-automations/actions-reference"]
},
{
@@ -314,7 +314,7 @@
]
},
{
- "group": "Workflows",
+ "group": "Agents",
"pages": [
"sdk-reference/workflows/run-workflow",
"sdk-reference/workflows/create-workflow",
@@ -547,19 +547,19 @@
},
{
"source": "/workflows/manage-workflows",
- "destination": "/cloud/building-workflows/manage-workflows"
+ "destination": "/cloud/building-agents/manage-agents"
},
{
"source": "/workflows/workflow-blocks-details",
- "destination": "/cloud/building-workflows/configure-blocks"
+ "destination": "/cloud/building-agents/configure-blocks"
},
{
"source": "/workflows/workflow-parameters",
- "destination": "/cloud/building-workflows/add-parameters"
+ "destination": "/cloud/building-agents/add-parameters"
},
{
"source": "/workflows/run-workflows",
- "destination": "/cloud/building-workflows/run-a-workflow"
+ "destination": "/cloud/building-agents/run-an-agent"
},
{
"source": "/workflows/consistent-workflows",
@@ -567,27 +567,27 @@
},
{
"source": "/workflows/running-workflows",
- "destination": "/cloud/building-workflows/run-a-workflow"
+ "destination": "/cloud/building-agents/run-an-agent"
},
{
"source": "/workflows/introduction",
- "destination": "/cloud/building-workflows/build-a-workflow"
+ "destination": "/cloud/building-agents/build-an-agent"
},
{
"source": "/workflows/workflow-blocks",
- "destination": "/cloud/building-workflows/configure-blocks"
+ "destination": "/cloud/building-agents/configure-blocks"
},
{
"source": "/workflows/creating-workflows",
- "destination": "/cloud/building-workflows/build-a-workflow"
+ "destination": "/cloud/building-agents/build-an-agent"
},
{
"source": "/workflows/getting-workflows",
- "destination": "/cloud/building-workflows/run-a-workflow"
+ "destination": "/cloud/building-agents/run-an-agent"
},
{
"source": "/workflows/what-is-a-parameter",
- "destination": "/cloud/building-workflows/add-parameters"
+ "destination": "/cloud/building-agents/add-parameters"
},
{
"source": "/multi-step-automations/overview",
@@ -623,11 +623,11 @@
},
{
"source": "/multi-step-automations/workflow-parameters",
- "destination": "/cloud/building-workflows/add-parameters"
+ "destination": "/cloud/building-agents/add-parameters"
},
{
"source": "/multi-step-automations/scheduling-workflows",
- "destination": "/cloud/building-workflows/scheduling"
+ "destination": "/cloud/building-agents/scheduling"
},
{
"source": "/credentials/introduction",
@@ -860,6 +860,34 @@
{
"source": "/browser-automations/:slug*",
"destination": "/developers/browser-automations/:slug*"
+ },
+ {
+ "source": "/cloud/building-workflows/build-a-workflow",
+ "destination": "/cloud/building-agents/build-an-agent"
+ },
+ {
+ "source": "/cloud/building-workflows/manage-workflows",
+ "destination": "/cloud/building-agents/manage-agents"
+ },
+ {
+ "source": "/cloud/building-workflows/run-a-workflow",
+ "destination": "/cloud/building-agents/run-an-agent"
+ },
+ {
+ "source": "/cloud/building-workflows/add-parameters",
+ "destination": "/cloud/building-agents/add-parameters"
+ },
+ {
+ "source": "/cloud/building-workflows/configure-blocks",
+ "destination": "/cloud/building-agents/configure-blocks"
+ },
+ {
+ "source": "/cloud/building-workflows/run-from-code",
+ "destination": "/cloud/building-agents/run-from-code"
+ },
+ {
+ "source": "/cloud/building-workflows/scheduling",
+ "destination": "/cloud/building-agents/scheduling"
}
]
}
diff --git a/docs/index.mdx b/docs/index.mdx
index 1aba29be4..ae63cf122 100644
--- a/docs/index.mdx
+++ b/docs/index.mdx
@@ -1,6 +1,6 @@
---
title: Skyvern Documentation
-description: Skyvern is an AI-powered browser automation platform. Describe tasks in plain English and Skyvern opens a real browser, reads the page visually, and completes the task using tasks, workflows, and the API or SDK.
+description: Skyvern is an AI-powered browser automation platform. Describe tasks in plain English and Skyvern opens a real browser, reads the page visually, and completes the task using tasks, agents, and the API or SDK.
slug: /
mode: custom
---
@@ -58,11 +58,11 @@ mode: custom
<div className="sk-bento-cell">
<p className="sk-mono sk-label">01 / NO CODE</p>
<h3 className="sk-cell-title">Automate without code</h3>
- <p className="sk-cell-desc">Use the dashboard to run tasks and build workflows visually.</p>
+ <p className="sk-cell-desc">Use the dashboard to run tasks and build agents visually.</p>
<div className="sk-cell-links">
<a href="/docs/cloud/getting-started/overview" className="sk-cell-link">Dashboard overview <span className="sk-arrow">↗</span></a>
<a href="/docs/cloud/getting-started/run-your-first-task" className="sk-cell-link">Run your first task <span className="sk-arrow">↗</span></a>
- <a href="/docs/cloud/building-workflows/build-a-workflow" className="sk-cell-link">Build a workflow <span className="sk-arrow">↗</span></a>
+ <a href="/docs/cloud/building-agents/build-an-agent" className="sk-cell-link">Build an agent <span className="sk-arrow">↗</span></a>
<a href="/docs/integrations/zapier" className="sk-cell-link">Connect to Zapier <span className="sk-arrow">↗</span></a>
</div>
</div>
@@ -101,7 +101,7 @@ mode: custom
<a href="/docs/getting-started/core-concepts" className="sk-bento-cell sk-bento-cell-link">
<p className="sk-mono sk-label">REFERENCE</p>
<h3 className="sk-cell-title">Core concepts</h3>
- <p className="sk-cell-desc">Tasks, workflows, blocks, runs, credentials, browser sessions, and engines.</p>
+ <p className="sk-cell-desc">Tasks, agents, blocks, runs, credentials, browser sessions, and engines.</p>
<span className="sk-mono sk-arrow-lg">↗</span>
</a>
</div>
@@ -146,7 +146,7 @@ mode: custom
</div>
<div className="sk-bento-row sk-bento-4col">
- <a href="/docs/cloud/building-workflows/build-a-workflow" className="sk-bento-cell sk-bento-cell-link sk-bento-cell-sm sk-usecase-orange">
+ <a href="/docs/cloud/building-agents/build-an-agent" className="sk-bento-cell sk-bento-cell-link sk-bento-cell-sm sk-usecase-orange">
<span className="sk-usecase-icon">
<svg width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2" strokeLinecap="round" strokeLinejoin="round"><circle cx="9" cy="21" r="1"/><circle cx="20" cy="21" r="1"/><path d="M1 1h4l2.68 13.39a2 2 0 0 0 2 1.61h9.72a2 2 0 0 0 2-1.61L23 6H6"/></svg>
</span>
@@ -162,7 +162,7 @@ mode: custom
<p className="sk-cell-desc-sm">Navigate complex government websites to register accounts or file forms.</p>
<span className="sk-mono sk-arrow-sm">↗</span>
</a>
- <a href="/docs/cloud/building-workflows/configure-blocks" className="sk-bento-cell sk-bento-cell-link sk-bento-cell-sm sk-usecase-orange">
+ <a href="/docs/cloud/building-agents/configure-blocks" className="sk-bento-cell sk-bento-cell-link sk-bento-cell-sm sk-usecase-orange">
<span className="sk-usecase-icon">
<svg width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2" strokeLinecap="round" strokeLinejoin="round"><path d="M12 22s8-4 8-10V5l-8-3-8 3v7c0 6 8 10 8 10z"/></svg>
</span>
diff --git a/docs/integrations/cli.mdx b/docs/integrations/cli.mdx
index f663c2b26..2a15ba679 100644
--- a/docs/integrations/cli.mdx
+++ b/docs/integrations/cli.mdx
@@ -1,7 +1,7 @@
---
title: CLI & Skills
-subtitle: Automate browsers and manage workflows from the command line
-description: Use the skyvern CLI to run browser automations, manage workflows, store credentials, and configure MCP servers from the terminal. Supports shell scripts, CI/CD pipelines, and one-off tasks.
+subtitle: Automate browsers and manage agents from the command line
+description: Use the skyvern CLI to run browser automations, manage agents, store credentials, and configure MCP servers from the terminal. Supports shell scripts, CI/CD pipelines, and one-off tasks.
slug: going-to-production/cli
keywords:
- CLI
@@ -14,7 +14,7 @@ keywords:
- one-liner
---
-The `skyvern` CLI gives you direct access to browser automation, workflow management, credential storage, and more, all from your terminal. Use it in shell scripts, CI/CD pipelines, or for quick one-off tasks.
+The `skyvern` CLI gives you direct access to browser automation, agent management, credential storage, and more, all from your terminal. Use it in shell scripts, CI/CD pipelines, or for quick one-off tasks.
## Install
@@ -116,7 +116,7 @@ Always pass `--api-key` when using `--tunnel`. Without it, anyone with the ngrok
See the [full guide](/developers/optimization/browser-tunneling) for all options, manual tunnel setup, and security details.
-### Workflows
+### Agents
```bash
skyvern workflow list # List all workflows
@@ -143,7 +143,7 @@ skyvern credential delete --id cred_xxx
Note: `credentials` (plural) is used for the interactive `add` command; `credential` (singular) for list/get/delete. Both forms are intentional.
-### Workflow blocks
+### Agent blocks
```bash
skyvern block schema --block-type task # Show the JSON schema for a block type
diff --git a/docs/integrations/make.mdx b/docs/integrations/make.mdx
index 8bb498d5a..f75d798e6 100644
--- a/docs/integrations/make.mdx
+++ b/docs/integrations/make.mdx
@@ -1,7 +1,7 @@
---
title: Make.com
subtitle: Integrate browser automations into Make scenarios
-description: Connect Skyvern to 2,000+ apps through Make.com. Run tasks or workflows, retrieve results, and integrate browser automations into any Make scenario.
+description: Connect Skyvern to 2,000+ apps through Make.com. Run tasks or agents, retrieve results, and integrate browser automations into any Make scenario.
slug: integrations/make
keywords:
- Make.com
@@ -18,9 +18,9 @@ Connect Skyvern to 2,000+ apps through Make. Trigger browser automations from an
- **Run a Task**: Run an automation using **Skyvern 1.0** (simple, single-step goals)
- **Run a Task V2**: Legacy module for explicitly requested V2 task runs
-- **Run a Workflow**: Run a pre-built Skyvern workflow with parameters
+- **Run an Agent**: Run a pre-built Skyvern agent with parameters
- **Get a Task / Get a Task V2**: Retrieve results from a previously run task
-- **Get a Workflow**: Retrieve results from a previously run workflow
+- **Get an Agent**: Retrieve results from a previously run agent
- **List Organizations**: List all organizations in your account
- **Make an API Call**: Execute a custom API request with your credentials
@@ -86,35 +86,35 @@ The navigation goal describes what to do *after* loading the URL. Don't include
<img src="/images/make/make3.png" alt="Configure task fields in Make.com" />
</Frame>
-### Run a Workflow
+### Run an Agent
-First, create your workflow in the [Skyvern UI](https://app.skyvern.com).
+First, create your agent in the [Skyvern UI](https://app.skyvern.com).
-- **Workflow** (required): Select the workflow to run
-- **Parameters**: Fill in any parameters defined in your workflow
+- **Agent** (required): Select the agent to run
+- **Parameters**: Fill in any parameters defined in your agent
<Frame>
- <img src="/images/make/make4.png" alt="Configure workflow fields in Make.com" />
+ <img src="/images/make/make4.png" alt="Configure agent fields in Make.com" />
</Frame>
-### Get a Task / Workflow
+### Get a Task / Agent
Retrieve the output of a completed run.
- **Task ID** (required): Starts with `tsk_`
-- **Workflow Run ID** (required): Starts with `wr_`
+- **Agent Run ID** (required): Starts with `wr_`
<Frame>
- <img src="/images/make/make5.png" alt="Enter Task ID or Workflow Run ID in Make.com" />
+ <img src="/images/make/make5.png" alt="Enter Task ID or Agent Run ID in Make.com" />
</Frame>
## Next steps
<CardGroup cols={2}>
<Card
- title="Build Workflows"
+ title="Build Agents"
icon="diagram-project"
- href="/cloud/manage-workflows"
+ href="/cloud/building-agents/manage-agents"
>
Create reusable multi-step automations in Skyvern
</Card>
diff --git a/docs/integrations/n8n.mdx b/docs/integrations/n8n.mdx
index 08544cafa..fac415df8 100644
--- a/docs/integrations/n8n.mdx
+++ b/docs/integrations/n8n.mdx
@@ -1,7 +1,7 @@
---
title: n8n
subtitle: Run browser automations in your n8n workflows
-description: Connect Skyvern to n8n's open-source automation platform. Dispatch tasks and workflows, retrieve results, and integrate browser automations into any n8n workflow.
+description: Connect Skyvern to n8n's open-source automation platform. Dispatch tasks and agents, retrieve results, and integrate browser automations into any n8n workflow.
slug: integrations/n8n
keywords:
- n8n
@@ -18,8 +18,8 @@ Connect Skyvern to n8n's open-source automation platform. Trigger browser automa
- **Task → Dispatch a Task**: Run a browser automation with a prompt
- **Task → Get a Task**: Retrieve results from a previously run task
-- **Workflow → Dispatch a Workflow Run**: Run a pre-built Skyvern workflow with parameters
-- **Workflow → Get a Workflow Run**: Retrieve results from a previously run workflow
+- **Agent → Dispatch an Agent Run**: Run a pre-built Skyvern agent with parameters
+- **Agent → Get an Agent Run**: Retrieve results from a previously run agent
## Setup
@@ -71,17 +71,17 @@ Under **Task Options**:
- **Skyvern 2.0**: Existing V2 workflows or explicitly requested V2 task runs
- **OpenAI CUA** / **Anthropic CUA**: Third-party computer-use agents
-### Dispatch a Workflow Run
+### Dispatch an Agent Run
<Frame>
- <img src="/images/n8n/n8n3.png" alt="Configure Dispatch a Workflow Run fields in n8n" />
+ <img src="/images/n8n/n8n3.png" alt="Configure Dispatch an Agent Run fields in n8n" />
</Frame>
-First, create your workflow in the [Skyvern UI](https://app.skyvern.com).
+First, create your agent in the [Skyvern UI](https://app.skyvern.com).
-- **Workflow Name or ID** (required): Select from the dropdown or specify an ID with an expression
-- **Workflow Run Parameters**: Loaded dynamically from the selected workflow
-- **Webhook Callback URL**: URL to notify when the workflow finishes
+- **Agent Name or ID** (required): Select from the dropdown or specify an ID with an expression
+- **Agent Run Parameters**: Loaded dynamically from the selected agent
+- **Webhook Callback URL**: URL to notify when the agent finishes
### Get a Task
@@ -91,22 +91,22 @@ First, create your workflow in the [Skyvern UI](https://app.skyvern.com).
- **Task ID** (required): The ID of the task run
-### Get a Workflow Run
+### Get an Agent Run
<Frame>
- <img src="/images/n8n/n8n4.png" alt="Enter Workflow Run ID field in n8n" />
+ <img src="/images/n8n/n8n4.png" alt="Enter Agent Run ID field in n8n" />
</Frame>
-- **Workflow Name or ID** (required): Select the workflow from the dropdown
-- **Workflow Run ID** (required): Starts with `wr_`
+- **Agent Name or ID** (required): Select the agent from the dropdown
+- **Agent Run ID** (required): Starts with `wr_`
## Next steps
<CardGroup cols={2}>
<Card
- title="Build Workflows"
+ title="Build Agents"
icon="diagram-project"
- href="/cloud/manage-workflows"
+ href="/cloud/building-agents/manage-agents"
>
Create reusable multi-step automations in Skyvern
</Card>
diff --git a/docs/integrations/workato.mdx b/docs/integrations/workato.mdx
index 690252ba9..9e6fe2014 100644
--- a/docs/integrations/workato.mdx
+++ b/docs/integrations/workato.mdx
@@ -1,7 +1,7 @@
---
title: Workato
subtitle: Run browser automations in your Workato recipes
-description: Connect Skyvern to Workato's enterprise automation platform. Run tasks or workflows, retrieve results, and integrate browser automations into any Workato recipe.
+description: Connect Skyvern to Workato's enterprise automation platform. Run tasks or agents, retrieve results, and integrate browser automations into any Workato recipe.
slug: integrations/workato
keywords:
- Workato
@@ -17,9 +17,9 @@ Connect Skyvern to Workato's enterprise automation platform. Trigger browser aut
- **Create and Run Task**: Run an automation using **Skyvern 1.0** (simple, single-step goals)
- **Create and Run Task V2**: Legacy action for explicitly requested V2 task runs
-- **Run a Workflow**: Run a pre-built Skyvern workflow with parameters
+- **Run an Agent**: Run a pre-built Skyvern agent with parameters
- **Get Task / Get Task V2**: Retrieve results from a previously run task
-- **Get Workflow**: Retrieve results from a previously run workflow
+- **Get Agent**: Retrieve results from a previously run agent
## Setup
@@ -87,31 +87,31 @@ The navigation goal describes what to do *after* loading the URL. Don't include
<img src="/images/workato/s2img1.png" alt="Configure task fields in Workato" />
</Frame>
-### Run a Workflow
+### Run an Agent
-First, create your workflow in the [Skyvern UI](https://app.skyvern.com).
+First, create your agent in the [Skyvern UI](https://app.skyvern.com).
-- **Workflow** (required): Select the workflow to run
-- **Parameters**: Fill in any parameters defined in your workflow
+- **Agent** (required): Select the agent to run
+- **Parameters**: Fill in any parameters defined in your agent
<Frame>
- <img src="/images/workato/s5img1.png" alt="Select workflow in Workato" />
+ <img src="/images/workato/s5img1.png" alt="Select agent in Workato" />
</Frame>
-### Get Task / Workflow
+### Get Task / Agent
Retrieve the details of a completed run.
- **Task ID** (required): Starts with `tsk_`
-- **Workflow Run ID** (required): Starts with `wr_`
+- **Agent Run ID** (required): Starts with `wr_`
## Next steps
<CardGroup cols={2}>
<Card
- title="Build Workflows"
+ title="Build Agents"
icon="diagram-project"
- href="/cloud/manage-workflows"
+ href="/cloud/building-agents/manage-agents"
>
Create reusable multi-step automations in Skyvern
</Card>
diff --git a/docs/integrations/zapier.mdx b/docs/integrations/zapier.mdx
index c1f76a660..39165d8bd 100644
--- a/docs/integrations/zapier.mdx
+++ b/docs/integrations/zapier.mdx
@@ -1,7 +1,7 @@
---
title: Zapier
subtitle: Trigger browser automations from Zapier workflows
-description: Connect Skyvern to 7,000+ apps through Zapier. Create and run tasks or workflows, retrieve results, and trigger browser automations from any Zap.
+description: Connect Skyvern to 7,000+ apps through Zapier. Create and run tasks or agents, retrieve results, and trigger browser automations from any Zap.
slug: integrations/zapier
keywords:
- Zapier
@@ -17,15 +17,15 @@ Connect Skyvern to 7,000+ apps through Zapier. Trigger browser automations from
## Available Triggers
-- **New or Updated Skyvern Workflow**: Starts a Zap whenever a workflow is created or modified.
+- **New or Updated Skyvern Agent**: Starts a Zap whenever an agent is created or modified.
## Available Actions
- **Create and Run a Task**: Run an automation using **Skyvern 1.0** (simple, single-step goals)
- **Create and Run Task V2**: Legacy action for explicitly requested V2 task runs
-- **Run a Workflow**: Run a pre-built Skyvern workflow with parameters
+- **Run an Agent**: Run a pre-built Skyvern agent with parameters
- **Get a Task / Get a Task V2**: Retrieve results from a previously run task
-- **Get a Workflow**: Retrieve results from a previously run workflow
+- **Get an Agent**: Retrieve results from a previously run agent
## Setup
@@ -93,26 +93,26 @@ The navigation goal describes what to do *after* loading the URL. Don't include
<img src="/images/zapier/z.3.png" alt="Configure task fields in Zapier" />
</Frame>
-### Run a Workflow
+### Run an Agent
-First, create your workflow in the [Skyvern UI](https://app.skyvern.com).
+First, create your agent in the [Skyvern UI](https://app.skyvern.com).
-- **Workflow** (required): Select the workflow to run
-- **Parameters**: Fill in any parameters defined in your workflow
+- **Agent** (required): Select the agent to run
+- **Parameters**: Fill in any parameters defined in your agent
<Frame>
- <img src="/images/zapier/z.7w.png" alt="Select workflow in Zapier" />
+ <img src="/images/zapier/z.7w.png" alt="Select agent in Zapier" />
</Frame>
<Frame>
- <img src="/images/zapier/z.8w.png" alt="Configure workflow parameters in Zapier" />
+ <img src="/images/zapier/z.8w.png" alt="Configure agent parameters in Zapier" />
</Frame>
-### Get a Task / Workflow
+### Get a Task / Agent
Retrieve the output of a completed run.
- **Task ID** (required): Starts with `tsk_`
-- **Workflow Run ID** (required): Starts with `wr_`
+- **Agent Run ID** (required): Starts with `wr_`
<Frame>
<img src="/images/zapier/z.11ag.png" alt="Enter Task ID field in Zapier" />
@@ -122,9 +122,9 @@ Retrieve the output of a completed run.
<CardGroup cols={2}>
<Card
- title="Build Workflows"
+ title="Build Agents"
icon="diagram-project"
- href="/cloud/manage-workflows"
+ href="/cloud/building-agents/manage-agents"
>
Create reusable multi-step automations in Skyvern
</Card>
diff --git a/docs/sdk-reference/credentials/create-credential.mdx b/docs/sdk-reference/credentials/create-credential.mdx
index 83ffe4be4..ff11b9e14 100644
--- a/docs/sdk-reference/credentials/create-credential.mdx
+++ b/docs/sdk-reference/credentials/create-credential.mdx
@@ -3,7 +3,7 @@ title: "create_credential"
slug: sdk-reference/credentials/create-credential
---
-Credentials let you store login information (username/password, TOTP secrets) securely in Skyvern's vault. Reference them by ID in tasks and workflows instead of passing secrets in your code.
+Credentials let you store login information (username/password, TOTP secrets) securely in Skyvern's vault. Reference them by ID in tasks and agents instead of passing secrets in your code.
<Note>
Python uses `snake_case` (e.g., `create_credential`); TypeScript uses `camelCase` (e.g., `createCredential`). Parameter tables show Python names. TypeScript names are the camelCase equivalents.
diff --git a/docs/sdk-reference/error-handling.mdx b/docs/sdk-reference/error-handling.mdx
index 14fcf0d96..4c0207b26 100644
--- a/docs/sdk-reference/error-handling.mdx
+++ b/docs/sdk-reference/error-handling.mdx
@@ -295,7 +295,7 @@ try {
```
</CodeGroup>
-**Run failure** - The API call succeeded, but the task/workflow failed during execution. No exception is raised. Check the `status` field:
+**Run failure** - The API call succeeded, but the task/agent failed during execution. No exception is raised. Check the `status` field:
<CodeGroup>
```python Python
diff --git a/docs/sdk-reference/helpers/upload-file.mdx b/docs/sdk-reference/helpers/upload-file.mdx
index c72e21b30..18709339a 100644
--- a/docs/sdk-reference/helpers/upload-file.mdx
+++ b/docs/sdk-reference/helpers/upload-file.mdx
@@ -3,7 +3,7 @@ title: "upload_file"
slug: sdk-reference/helpers/upload-file
---
-Upload a file to Skyvern's storage. Returns a presigned URL and S3 URI you can reference in tasks and workflows.
+Upload a file to Skyvern's storage. Returns a presigned URL and S3 URI you can reference in tasks and agents.
<CodeGroup>
```python Python
diff --git a/docs/sdk-reference/overview.mdx b/docs/sdk-reference/overview.mdx
index 6d762c536..9bdb31c57 100644
--- a/docs/sdk-reference/overview.mdx
+++ b/docs/sdk-reference/overview.mdx
@@ -170,7 +170,7 @@ If you configured headful mode during `skyvern quickstart`, a Chromium window op
## Waiting for completion
-By default, task and workflow runs return immediately after queuing. You get a run ID and need to poll for results yourself. Pass `wait_for_completion` to have the SDK poll automatically until the run reaches a terminal state (`completed`, `failed`, `terminated`, `timed_out`, or `canceled`):
+By default, task and agent runs return immediately after queuing. You get a run ID and need to poll for results yourself. Pass `wait_for_completion` to have the SDK poll automatically until the run reaches a terminal state (`completed`, `failed`, `terminated`, `timed_out`, or `canceled`):
<CodeGroup>
```python Python
@@ -217,7 +217,7 @@ console.log(task.run_id); // poll with skyvern.getRun(task.run_id)
| `wait_for_completion` / `waitForCompletion` | `bool` / `boolean` | `false` | Poll until the run finishes. |
| `timeout` | `float` / `number` | `1800` | Maximum wait time in seconds. |
-Supported on task runs, workflow runs, and login. In TypeScript, also supported on file downloads.
+Supported on task runs, agent runs, and login. In TypeScript, also supported on file downloads.
---
diff --git a/docs/sdk-reference/tasks/get-run.mdx b/docs/sdk-reference/tasks/get-run.mdx
index 61c50850c..816874191 100644
--- a/docs/sdk-reference/tasks/get-run.mdx
+++ b/docs/sdk-reference/tasks/get-run.mdx
@@ -3,7 +3,7 @@ title: "get_run"
slug: sdk-reference/tasks/get-run
---
-Get the current status and results of any run (task or workflow).
+Get the current status and results of any run (task or agent).
<CodeGroup>
```python Python
diff --git a/docs/sdk-reference/tasks/get-runs-v2.mdx b/docs/sdk-reference/tasks/get-runs-v2.mdx
index ffc4f4490..bde82c303 100644
--- a/docs/sdk-reference/tasks/get-runs-v2.mdx
+++ b/docs/sdk-reference/tasks/get-runs-v2.mdx
@@ -3,7 +3,7 @@ title: "get_runs_v2"
slug: sdk-reference/tasks/get-runs-v2
---
-List all runs across tasks and workflows for the current organization, with filtering and pagination.
+List all runs across tasks and agents for the current organization, with filtering and pagination.
<CodeGroup>
```python Python
diff --git a/docs/sdk-reference/tasks/run-task.mdx b/docs/sdk-reference/tasks/run-task.mdx
index 683b4713a..a6193db64 100644
--- a/docs/sdk-reference/tasks/run-task.mdx
+++ b/docs/sdk-reference/tasks/run-task.mdx
@@ -5,7 +5,7 @@ slug: sdk-reference/tasks/run-task
A task is a single browser automation. You describe what you want in natural language. Skyvern opens a browser, navigates to the URL, and executes the instructions with AI.
-For when to use tasks vs workflows, see [Run a Task](/running-automations/run-a-task).
+For when to use tasks vs agents, see [Run a Task](/running-automations/run-a-task).
<Note>
Python uses `snake_case` (e.g., `run_task`, `wait_for_completion`); TypeScript uses `camelCase` (e.g., `runTask`, `waitForCompletion`) and wraps request params in a `body` object. Parameter tables show Python names. TypeScript names are the camelCase equivalents.
diff --git a/docs/sdk-reference/workflows/run-workflow.mdx b/docs/sdk-reference/workflows/run-workflow.mdx
index ecfa0204d..989488f78 100644
--- a/docs/sdk-reference/workflows/run-workflow.mdx
+++ b/docs/sdk-reference/workflows/run-workflow.mdx
@@ -3,9 +3,9 @@ title: run_workflow
slug: sdk-reference/workflows/run-workflow
---
-A workflow chains multiple steps (blocks) into a single automation. Workflows support loops, conditionals, data passing between steps, and code-based re-execution.
+An agent chains multiple steps (blocks) into a single automation. Agents support loops, conditionals, data passing between steps, and code-based re-execution.
-For conceptual background, see [Build a Workflow](/cloud/building-workflows/build-a-workflow).
+For conceptual background, see [Build an Agent](/cloud/building-agents/build-an-agent).
<Note>
Python uses `snake_case` (e.g., `run_workflow`); TypeScript uses `camelCase` (e.g., `runWorkflow`) and wraps request params in a `body` object. Parameter tables show Python names. TypeScript names are the camelCase equivalents.
diff --git a/docs/snippets/ai-agents-quickstart-content.mdx b/docs/snippets/ai-agents-quickstart-content.mdx
index 4b630a622..33162e0b5 100644
--- a/docs/snippets/ai-agents-quickstart-content.mdx
+++ b/docs/snippets/ai-agents-quickstart-content.mdx
@@ -69,7 +69,7 @@ export const ApiKeyPrompt = ({ children }) => {
);
};
-Skyvern lets AI coding assistants (Claude Code, Cursor, Windsurf, Codex) control browsers, extract data, and run workflows.
+Skyvern lets AI coding assistants (Claude Code, Cursor, Windsurf, Codex) control browsers, extract data, and run agents.
**Copy the prompt below** into your AI coding agent and you'll have a running automation in minutes.
diff --git a/docs/snippets/core-concepts-content.mdx b/docs/snippets/core-concepts-content.mdx
index 52d4c0abb..abae38c7d 100644
--- a/docs/snippets/core-concepts-content.mdx
+++ b/docs/snippets/core-concepts-content.mdx
@@ -38,7 +38,7 @@ Tasks are best for one-off automations, quick data extraction, and prototyping.
Write multi-step automations in Python or TypeScript with full Playwright control. Version, test, and deploy automation code like any other software.
</Card>
<Card
- title="Workflows (Visual)"
+ title="Agents (Visual)"
href="#workflows"
>
Build multi-step automations visually in the Cloud UI with drag-and-drop blocks. No code required. Share templates across your team.
@@ -110,9 +110,9 @@ Agents are useful when you want to mix precise Playwright control with open-ende
Full method reference: [Page](/sdk-reference/browser-automation/act), [Agent](/sdk-reference/browser-automation/agent-run-task), [Browser](/sdk-reference/browser-automation/launch-cloud-browser). Developer guide: [Multi-Step Automations](/developers/browser-automations/overview).
</Note>
-## Workflows
+## Agents
-A Workflow is a reusable automation template built in the [Cloud UI workflow editor](/cloud/building-workflows/build-a-workflow). You drag and drop blocks onto a canvas, wire them together, and save. Workflows can be versioned, shared across your team, scheduled on a cron, and run repeatedly with different parameters.
+An Agent is a reusable automation template built in the [Cloud UI agent editor](/cloud/building-agents/build-an-agent). You drag and drop blocks onto a canvas, wire them together, and save. Agents can be versioned, shared across your team, scheduled on a cron, and run repeatedly with different parameters.
```mermaid
flowchart LR
@@ -131,15 +131,15 @@ flowchart LR
Each block can reference outputs from previous blocks using Jinja templating: `{{search_query}}` for parameters, `{{extract_block.product_name}}` for upstream block outputs.
-Workflows are the right choice when you want no-code automation, team-shared templates, scheduled recurring jobs, or visual drag-and-drop logic.
+Agents are the right choice when you want no-code automation, team-shared templates, scheduled recurring jobs, or visual drag-and-drop logic.
<Tip>
-**Building workflows?** See the [Workflow Editor guide](/cloud/building-workflows/build-a-workflow). **Need to trigger a workflow from code?** See [Run from Code](/cloud/building-workflows/run-from-code) in the Cloud UI docs.
+**Building agents?** See the [Agent Editor guide](/cloud/building-agents/build-an-agent). **Need to trigger an agent from code?** See [Run from Code](/cloud/building-agents/run-from-code) in the Cloud UI docs.
</Tip>
### Blocks
-Blocks are the building units of workflows. Each block performs one operation.
+Blocks are the building units of agents. Each block performs one operation.
**Navigation and interaction:** Navigate (AI-guided navigation toward a goal), Action (click, type, select, upload), Go to URL (direct navigation), Login (authenticate with stored credentials), Wait (pause for a duration), and Human Interaction (pause for manual intervention).
@@ -149,11 +149,11 @@ Blocks are the building units of workflows. Each block performs one operation.
**Communication:** HTTP Request (external API calls), Text Prompt (text-only LLM prompt, no browser), and Send Email.
-For detailed block configuration, see [Block Types and Configuration](/cloud/building-workflows/configure-blocks).
+For detailed block configuration, see [Block Types and Configuration](/cloud/building-agents/configure-blocks).
## Runs
-Every time you execute a task or kick off a workflow, Skyvern creates a Run to track progress and store outputs. A run moves through a lifecycle:
+Every time you execute a task or kick off an agent, Skyvern creates a Run to track progress and store outputs. A run moves through a lifecycle:
```mermaid
flowchart LR
@@ -184,7 +184,7 @@ You're billed per step. A step is one AI decision + action cycle. Use `max_steps
## Schedules
-A Schedule runs a workflow automatically on a recurring basis. You define a cron expression and timezone, and Skyvern triggers the workflow at each interval.
+A Schedule runs an agent automatically on a recurring basis. You define a cron expression and timezone, and Skyvern triggers the agent at each interval.
<CodeGroup>
```python Python
@@ -281,7 +281,7 @@ See [Browser Sessions](/developers/optimization/browser-sessions) for details.
## Artifacts
-Every run generates artifacts for observability, debugging, and audit trails: end-to-end video recordings, screenshots captured after each action, downloaded files, JSON-structured logs at step/task/workflow levels, and HAR files for network debugging.
+Every run generates artifacts for observability, debugging, and audit trails: end-to-end video recordings, screenshots captured after each action, downloaded files, JSON-structured logs at step/task/agent levels, and HAR files for network debugging.
```python
result = await skyvern.run_task(
@@ -298,7 +298,7 @@ In the Skyvern UI, go to **Runs**, click a run, and view the **Actions** and **R
## Engines
-Skyvern supports multiple AI engines. `skyvern-1.0` is the default for the Cloud UI and SDK. `skyvern-2.0` remains available for existing V2 workflows and explicitly requested V2 task runs. Other options include `openai-cua` (OpenAI Computer Use Agent), `anthropic-cua` (Anthropic Computer Use Agent), and `ui-tars`.
+Skyvern supports multiple AI engines. `skyvern-1.0` is the default for the Cloud UI and SDK. `skyvern-2.0` remains available for existing V2 agents and explicitly requested V2 task runs. Other options include `openai-cua` (OpenAI Computer Use Agent), `anthropic-cua` (Anthropic Computer Use Agent), and `ui-tars`.
```python
from skyvern.schemas.runs import RunEngine
@@ -316,8 +316,8 @@ result = await skyvern.run_task(
|--------------|-----|
| Run a one-off automation | [Task](#tasks) |
| Build multi-step automation in code | [Browser Automation](#browser-automation) |
-| Build multi-step automation visually | [Workflow](#workflows) |
-| Trigger a UI-built workflow from code | [Run from Code](/cloud/building-workflows/run-from-code) |
+| Build multi-step automation visually | [Agent](#workflows) |
+| Trigger a UI-built agent from code | [Run from Code](/cloud/building-agents/run-from-code) |
| Keep a browser open between operations | [Browser Session](#browser-sessions-and-profiles) |
| Skip login on repeated runs | [Browser Profile](#browser-sessions-and-profiles) |
| Store secrets securely | [Credentials](#credentials) |
@@ -330,7 +330,7 @@ result = await skyvern.run_task(
title="Use the dashboard"
href="/cloud/getting-started/overview"
>
- Run tasks, build workflows visually, and monitor runs. No code required.
+ Run tasks, build agents visually, and monitor runs. No code required.
</Card>
<Card
title="Build with the API"
diff --git a/docs/snippets/introduction-content.mdx b/docs/snippets/introduction-content.mdx
index 14231ebb6..18c0a8b31 100644
--- a/docs/snippets/introduction-content.mdx
+++ b/docs/snippets/introduction-content.mdx
@@ -22,7 +22,7 @@ A typical task takes 2 to 10 steps. You can set `max_steps` to cap cost during d
### Existing V2 Planner-Agent-Validator system
-Existing V2 workflows may use a higher-level system with three components:
+Existing V2 agents may use a higher-level system with three components:
<img src="/images/skyvern-explainer.png" alt="V2 architecture: Planner breaks prompt into sub-tasks, Task Agent executes them, Validator confirms completion" />
@@ -50,7 +50,7 @@ Most browser automation breaks down at authentication, CAPTCHAs, or dynamic cont
**Browser state persistence.** Sessions keep a live browser open across multiple tasks for up to 24 hours, useful when you need to chain tasks that share login state. Profiles snapshot cookies, auth tokens, and local storage into a reusable package you can restore on future runs, so you don't re-authenticate every time.
-**Multi-step workflows.** When a single task isn't enough, Workflows let you chain blocks together: navigate, login, loop through a list, extract data, branch on conditions, send emails. Workflows are parameterized and version-controlled. You can build them visually in the dashboard or define them through the API.
+**Multi-step agents.** When a single task isn't enough, Agents let you chain blocks together: navigate, login, loop through a list, extract data, branch on conditions, send emails. Agents are parameterized and version-controlled. You can build them visually in the dashboard or define them through the API.
---
@@ -59,5 +59,5 @@ Most browser automation breaks down at authentication, CAPTCHAs, or dynamic cont
Now that you understand how Skyvern works under the hood, learn the eight building blocks you'll use to create any automation.
<Card title="Core Concepts →" icon="book-open" href="/developers/getting-started/core-concepts">
- Tasks, workflows, blocks, runs, credentials, browser sessions, engines: everything you need to know before you start building.
+ Tasks, agents, blocks, runs, credentials, browser sessions, engines: everything you need to know before you start building.
</Card>
diff --git a/docs/snippets/mcp-content.mdx b/docs/snippets/mcp-content.mdx
index e05cedf72..74842cab8 100644
--- a/docs/snippets/mcp-content.mdx
+++ b/docs/snippets/mcp-content.mdx
@@ -1,4 +1,4 @@
-The Skyvern MCP server lets AI assistants like Claude Desktop, Claude Code, Codex, Cursor, and Windsurf control a browser. Your AI can fill out forms, extract data, download files, and run multi-step workflows, all through natural language.
+The Skyvern MCP server lets AI assistants like Claude Desktop, Claude Code, Codex, Cursor, and Windsurf control a browser. Your AI can fill out forms, extract data, download files, and run multi-step agents, all through natural language.
## What you can do
@@ -11,7 +11,7 @@ The MCP server exposes 75+ tools across many categories. Here are the key ones:
| **Data extraction** | `skyvern_extract`, `skyvern_screenshot`, `skyvern_evaluate` | Pull structured JSON from pages, capture screenshots, run JavaScript |
| **Validation** | `skyvern_validate` | Assert page conditions in natural language (returns true/false with reasoning) |
| **Credentials & login** | `skyvern_login`, `skyvern_credential_list`, `skyvern_credential_get`, `skyvern_credential_delete` | Log in with stored credentials (supports Skyvern vault, Bitwarden, 1Password, Azure Key Vault) with automatic 2FA/TOTP |
-| **Workflows** | `skyvern_workflow_create`, `skyvern_workflow_run`, `skyvern_workflow_status`, `skyvern_workflow_get`, `skyvern_workflow_update`, `skyvern_workflow_delete`, `skyvern_workflow_cancel` | Build, run, and manage multi-step automations with 23 block types |
+| **Agents** | `skyvern_workflow_create`, `skyvern_workflow_run`, `skyvern_workflow_status`, `skyvern_workflow_get`, `skyvern_workflow_update`, `skyvern_workflow_delete`, `skyvern_workflow_cancel` | Build, run, and manage multi-step automations with 23 block types |
Additional tools cover tab management, iframe switching, drag-and-drop, file upload, clipboard access, network/console inspection, HAR recording, web storage, auth state persistence, folder management, and cached script management.
@@ -101,7 +101,7 @@ This is not the ChatGPT App Directory. You can add Skyvern as a custom MCP conne
2. Click **Add connector** and choose the **MCP** type.
3. Enter the Skyvern MCP URL: `https://api.skyvern.com/mcp/`
4. ChatGPT detects OAuth support automatically. Follow the browser sign-in prompt to authenticate with your Skyvern account.
-5. Once connected, Skyvern tools appear in the tool panel. You can ask ChatGPT to navigate pages, fill forms, extract data, or run multi-step workflows.
+5. Once connected, Skyvern tools appear in the tool panel. You can ask ChatGPT to navigate pages, fill forms, extract data, or run multi-step agents.
No API key is required — OAuth handles authentication. If your account does not yet show the Connectors option, check **Settings → Beta features** to enable it.
@@ -545,7 +545,7 @@ The `/qa` skill uses `skyvern_evaluate` for fast DOM assertions (~10ms each) and
Skyvern MCP follows Skyvern's [Privacy Policy](https://app.termly.io/policy-viewer/policy.html?policyUUID=1d7aaa1b-5565-415a-8984-7146d254f738).
-When you use MCP, Skyvern processes the information needed to run the automations you request. This can include prompts, URLs, page content, screenshots, uploaded or downloaded files, workflow definitions, browser/session artifacts, and credentials you explicitly connect through Skyvern. Skyvern may store workflows, run history, artifacts, credentials, and browser/session state as needed to provide the service and support repeatable automations.
+When you use MCP, Skyvern processes the information needed to run the automations you request. This can include prompts, URLs, page content, screenshots, uploaded or downloaded files, agent definitions, browser/session artifacts, and credentials you explicitly connect through Skyvern. Skyvern may store agents, run history, artifacts, credentials, and browser/session state as needed to provide the service and support repeatable automations.
Only connect accounts, credentials, and websites that you are authorized to automate.