Skip to content

Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI

Revert mintlify introduction (#304)

Alex Reibman541164711246
diff --git a/docs/v1/introduction.mdx b/docs/v1/introduction.mdx
index f269be0e..e7992adc 100644
--- a/docs/v1/introduction.mdx
+++ b/docs/v1/introduction.mdx
@@ -1,65 +1,71 @@
---
title: "Introduction"
-description: "Find where your agents went wrong."
+description: "Build your next agent with evals, observability, and replays"
mode: "wide"
---
-import GithubStars from '/snippets/github-stars.mdx'
-import DiscordCTA from '/snippets/discord-cta.mdx'
+<Check>[Give us a star](https://github.com/AgentOps-AI/agentops) on GitHub if you find AgentOps helpful (you may be our <span id="stars-text">2,000th</span> 😊)</Check>
-## AI makes mistakes...
-#### .. but your terminal can't detect them
+# AgentOps solves what Terminal can't
-<div className='terminal-border'>
- <div className='terminal-container'>
- <div className='cursor-bar'>
- <p>></p><p className="empty-space">M</p><span id="python-terminal"></span><p id="toggle-empty-space" className="off">M</p><img id="inline-code-img" src="https://github.com/AgentOps-AI/agentops/blob/3c03341f5129f9f494ca64ed4e8d03b9a0575db4/docs/images/docs-icons/chat.png?raw=true"/><p id="barely-space" className="off">l</p><span id="terminal-command"></span><p id="cursor">_</p>
- </div>
- <div id='terminal-content'>
- </div>
- </div>
-</div>
+<CardGroup cols={2}>
+ <Card title="Terminal CAN'T..." icon="trash" iconType="solid" color="#d6483e">
+ - • Track agents across executions
+ - • Parse out LLM completions from output logs
+ - • Give you insight into what your agents did
+ </Card>
+ <Card title="AgentOps does it all and more..." icon="face-smile-halo" iconType="regular" color="#2bd600">
+ - • Record LLM prompts, completions, & timestamps
+ - • Log events, calls, and any other agent activity
+ - • Link agent errors back to their causal event
+ </Card>
+</CardGroup>
-AI's biggest problem is that it flies blind... but how can you fix what you can't even see? 👀
-
-## Let's give you full visibility
-#### AgentOps logs each step of the AI's decision and helps you understand where it went wrong.
-
-<Frame type="glass" caption="LLM Call Analytics Stream">
- <img height="200" src="https://github.com/AgentOps-AI/agentops/blob/c1d3903113679fbc794ae699593f5756c55599d1/docs/v1/img/chart-waterfall.png?raw=true" />
-</Frame>
-
-## Install AgentOps
-
-<span className="animated-code">
+And we do it all in just two lines of code...
<CodeGroup>
```python python
- pip install agentops
+ import agentops
+ agentops.init(<INSERT YOUR API KEY HERE>)
```
</CodeGroup>
-</span>
+... that logs everything back to your AgentOps Dashboard.
+
+## The AgentOps Dashboard
+
+With just two lines of code, you can free yourself from the chains of the terminal and instead visualize your agents' behavior
+in your AgentOps Dashboard. After setting up AgentOps, each execution of your program is recorded as a session and the above
+data is automatically recorded for you.
-### 🤯 And use it with just 2 lines of code!
+The examples below were captured with two lines of code.
-<span className="animated-code api-key-container">
- <CodeGroup>
- ```python python
- import agentops
- agentops.init(<INSERT YOUR API KEY HERE>)
- ```
- </CodeGroup>
-</span>
+### Session Drilldown
+Here you will find a list of all of your previously recorded sessions and useful data about each such as total execution time.
+You also get helpful debugging info such as any SDK versions you were on if you're building on a supported agent framework like Crew or AutoGen.
+LLM calls are presented as a familiar chat history view, and charts give you a breakdown of the types of events that were called and how long they took.
-<GithubStars />
+<Frame type="glass" caption="Session Summary">
+ <img height="200" src="https://github.com/AgentOps-AI/agentops/blob/cf67191f13e0e2a09446a61b7393e1810b3eee95/docs/images/session-summary.gif?raw=true" />
+</Frame>
+
+Find any past sessions from your Session Drawer.
+<Frame type="glass" caption="Session Drawer">
+ <img height="250" src="https://github.com/AgentOps-AI/agentops/blob/cf67191f13e0e2a09446a61b7393e1810b3eee95/docs/images/session-drawer.gif?raw=true" />
+</Frame>
-<a href="/v1/quickstart" class="heartbeat-button">
- <span>Get Started</span>
-</a>
+Most powerful of all is the Session Waterfall. On the left, a time visualization of all your LLM calls, Action events, Tool calls, and Errors.
+On the right, specific details about the event you've selected on the waterfall. For instance the exact prompt and completion for a given LLM call.
+Most of which has been automatically recorded for you.
-<DiscordCTA />
+<Frame type="glass" caption="Session Waterfall">
+ <img height="200" src="https://github.com/AgentOps-AI/agentops/blob/cf67191f13e0e2a09446a61b7393e1810b3eee95/docs/images/session-waterfall.gif?raw=true" />
+</Frame>
+
+
+### Session Overview
+View a meta-analysis of all of your sessions in a single view.
+<Frame type="glass" caption="Session Overview">
+ <img height="200" src="https://github.com/AgentOps-AI/agentops/blob/cf67191f13e0e2a09446a61b7393e1810b3eee95/docs/images/overview.png?raw=true" />
+</Frame>
<script type="module" src="/scripts/github_stars.js"></script>
-<script type="module" src="/scripts/link_to_api_button.js"></script>
-<script type="module" src="/scripts/scroll-img-fadein-animation.js"></script>
-<script type="module" src="/scripts/button_heartbeat_animation.js"></script>
-<script type="css" src="/styles/styles.css"></script>
+<script type="module" src="/scripts/adjust_api_dynamically.js"></script>