A programming framework for agentic AI
LLM Observability documentation fixes: Broken links, grammar, and spelling (#2995)
Alex Reibman9b92093b00b9
diff --git a/notebook/agentchat_agentops.ipynb b/notebook/agentchat_agentops.ipynbindex 293efa8e4..71106e45d 100644--- a/notebook/agentchat_agentops.ipynb+++ b/notebook/agentchat_agentops.ipynb@@ -7,7 +7,7 @@"collapsed": false},"source": [- "# AgentOps"+ "# Agent Tracking with AgentOps"]},{@@ -15,7 +15,7 @@"id": "a447802c88c8a240","metadata": {},"source": [- "\n",+ "<img src=\"https://github.com/AgentOps-AI/agentops/blob/main/docs/images/external/logo/banner-badge.png?raw=true\"/>\n","\n","[AgentOps](https://agentops.ai/?=autogen) provides session replays, metrics, and monitoring for AI agents.\n","\n",@@ -27,8 +27,11 @@"id": "b354c068","metadata": {},"source": [- "### Dashboard\n",- ""+ "### Overview Dashboard\n",+ "<img src=\"https://raw.githubusercontent.com/AgentOps-AI/agentops/main/docs/images/external/app_screenshots/overview.gif\"/>\n",+ "\n",+ "### Session Replays\n",+ "<img src=\"https://raw.githubusercontent.com/AgentOps-AI/agentops/main/docs/images/external/app_screenshots/drilldown.gif\"/>"]},{@@ -39,7 +42,7 @@"## Adding AgentOps to an existing Autogen service.\n","To get started, you'll need to install the AgentOps package and set an API key.\n","\n",- "AgentOps automatically configures itself when it's initialized. This means your agents will be tracked and logged to your AgentOps account right away."+ "AgentOps automatically configures itself when it's initialized meaning your agent run data will be tracked and logged to your AgentOps account right away."]},{@@ -69,7 +72,7 @@"\n","By default, the AgentOps `init()` function will look for an environment variable named `AGENTOPS_API_KEY`. Alternatively, you can pass one in as an optional parameter.\n","\n",- "Create an account and API key at [AgentOps.ai](https://agentops.ai/)"+ "Create an account and obtain an API key at [AgentOps.ai](https://agentops.ai/settings/projects)"]},{@@ -87,12 +90,14 @@"name": "stderr","output_type": "stream","text": [- "π AgentOps: \u001B[34m\u001B[34mSession Replay: https://app.agentops.ai/drilldown?session_id=8bfaeed1-fd51-4c68-b3ec-276b1a3ce8a4\u001B[0m\u001B[0m\n"+ "π AgentOps: \u001b[34m\u001b[34mSession Replay: https://app.agentops.ai/drilldown?session_id=8bfaeed1-fd51-4c68-b3ec-276b1a3ce8a4\u001b[0m\u001b[0m\n"]},{"data": {- "text/plain": "UUID('8bfaeed1-fd51-4c68-b3ec-276b1a3ce8a4')"+ "text/plain": [+ "UUID('8bfaeed1-fd51-4c68-b3ec-276b1a3ce8a4')"+ ]},"execution_count": 1,"metadata": {},@@ -104,7 +109,7 @@"\n","from autogen import ConversableAgent, UserProxyAgent, config_list_from_json\n","\n",- "agentops.init(api_key=\"7c94212b-b89d-47a6-a20c-23b2077d3226\") # or agentops.init(api_key=\"...\")"+ "agentops.init(api_key=\"...\")"]},{@@ -144,19 +149,19 @@"name": "stdout","output_type": "stream","text": [- "\u001B[33magent\u001B[0m (to user):\n",+ "\u001b[33magent\u001b[0m (to user):\n","\n","How can I help you today?\n","\n","--------------------------------------------------------------------------------\n",- "\u001B[33muser\u001B[0m (to agent):\n",+ "\u001b[33muser\u001b[0m (to agent):\n","\n","2+2\n","\n","--------------------------------------------------------------------------------\n",- "\u001B[31m\n",- ">>>>>>>> USING AUTO REPLY...\u001B[0m\n",- "\u001B[33magent\u001B[0m (to user):\n",+ "\u001b[31m\n",+ ">>>>>>>> USING AUTO REPLY...\u001b[0m\n",+ "\u001b[33magent\u001b[0m (to user):\n","\n","2 + 2 equals 4.\n","\n",@@ -168,7 +173,7 @@"output_type": "stream","text": ["π AgentOps: This run's cost $0.000960\n",- "π AgentOps: \u001B[34m\u001B[34mSession Replay: https://app.agentops.ai/drilldown?session_id=8bfaeed1-fd51-4c68-b3ec-276b1a3ce8a4\u001B[0m\u001B[0m\n"+ "π AgentOps: \u001b[34m\u001b[34mSession Replay: https://app.agentops.ai/drilldown?session_id=8bfaeed1-fd51-4c68-b3ec-276b1a3ce8a4\u001b[0m\u001b[0m\n"]}],@@ -185,7 +190,7 @@"# Create the agent that represents the user in the conversation.\n","user_proxy = UserProxyAgent(\"user\", code_execution_config=False)\n","\n",- "# Let the assistant start the conversation. It will end when the user types exit.\n",+ "# Let the assistant start the conversation. It will end when the user types \"exit\".\n","assistant.initiate_chat(user_proxy, message=\"How can I help you today?\")\n","\n","# Close your AgentOps session to indicate that it completed.\n",@@ -204,13 +209,13 @@},{"cell_type": "markdown",- "source": [- ""- ],+ "id": "cbd689b0f5617013","metadata": {"collapsed": false},- "id": "cbd689b0f5617013"+ "source": [+ ""+ ]},{"cell_type": "markdown",@@ -236,70 +241,70 @@"name": "stderr","output_type": "stream","text": [- "π AgentOps: \u001B[34m\u001B[34mSession Replay: https://app.agentops.ai/drilldown?session_id=880c206b-751e-4c23-9313-8684537fc04d\u001B[0m\u001B[0m\n"+ "π AgentOps: \u001b[34m\u001b[34mSession Replay: https://app.agentops.ai/drilldown?session_id=880c206b-751e-4c23-9313-8684537fc04d\u001b[0m\u001b[0m\n"]},{"name": "stdout","output_type": "stream","text": [- "\u001B[33mUser\u001B[0m (to Assistant):\n",+ "\u001b[33mUser\u001b[0m (to Assistant):\n","\n","What is (1423 - 123) / 3 + (32 + 23) * 5?\n","\n","--------------------------------------------------------------------------------\n",- "\u001B[31m\n",- ">>>>>>>> USING AUTO REPLY...\u001B[0m\n",- "\u001B[33mAssistant\u001B[0m (to User):\n",+ "\u001b[31m\n",+ ">>>>>>>> USING AUTO REPLY...\u001b[0m\n",+ "\u001b[33mAssistant\u001b[0m (to User):\n","\n",- "\u001B[32m***** Suggested tool call (call_aINcGyo0Xkrh9g7buRuhyCz0): calculator *****\u001B[0m\n",+ "\u001b[32m***** Suggested tool call (call_aINcGyo0Xkrh9g7buRuhyCz0): calculator *****\u001b[0m\n","Arguments: \n","{\n"," \"a\": 1423,\n"," \"b\": 123,\n"," \"operator\": \"-\"\n","}\n",- "\u001B[32m***************************************************************************\u001B[0m\n",+ "\u001b[32m***************************************************************************\u001b[0m\n","\n","--------------------------------------------------------------------------------\n",- "\u001B[35m\n",- ">>>>>>>> EXECUTING FUNCTION calculator...\u001B[0m\n",- "\u001B[33mUser\u001B[0m (to Assistant):\n",+ "\u001b[35m\n",+ ">>>>>>>> EXECUTING FUNCTION calculator...\u001b[0m\n",+ "\u001b[33mUser\u001b[0m (to Assistant):\n","\n",- "\u001B[33mUser\u001B[0m (to Assistant):\n",+ "\u001b[33mUser\u001b[0m (to Assistant):\n","\n",- "\u001B[32m***** Response from calling tool (call_aINcGyo0Xkrh9g7buRuhyCz0) *****\u001B[0m\n",+ "\u001b[32m***** Response from calling tool (call_aINcGyo0Xkrh9g7buRuhyCz0) *****\u001b[0m\n","1300\n",- "\u001B[32m**********************************************************************\u001B[0m\n",+ "\u001b[32m**********************************************************************\u001b[0m\n","\n","--------------------------------------------------------------------------------\n",- "\u001B[31m\n",- ">>>>>>>> USING AUTO REPLY...\u001B[0m\n",- "\u001B[33mAssistant\u001B[0m (to User):\n",+ "\u001b[31m\n",+ ">>>>>>>> USING AUTO REPLY...\u001b[0m\n",+ "\u001b[33mAssistant\u001b[0m (to User):\n","\n",- "\u001B[32m***** Suggested tool call (call_prJGf8V0QVT7cbD91e0Fcxpb): calculator *****\u001B[0m\n",+ "\u001b[32m***** Suggested tool call (call_prJGf8V0QVT7cbD91e0Fcxpb): calculator *****\u001b[0m\n","Arguments: \n","{\n"," \"a\": 1300,\n"," \"b\": 3,\n"," \"operator\": \"/\"\n","}\n",- "\u001B[32m***************************************************************************\u001B[0m\n",+ "\u001b[32m***************************************************************************\u001b[0m\n","\n","--------------------------------------------------------------------------------\n",- "\u001B[35m\n",- ">>>>>>>> EXECUTING FUNCTION calculator...\u001B[0m\n",- "\u001B[33mUser\u001B[0m (to Assistant):\n",+ "\u001b[35m\n",+ ">>>>>>>> EXECUTING FUNCTION calculator...\u001b[0m\n",+ "\u001b[33mUser\u001b[0m (to Assistant):\n","\n",- "\u001B[33mUser\u001B[0m (to Assistant):\n",+ "\u001b[33mUser\u001b[0m (to Assistant):\n","\n",- "\u001B[32m***** Response from calling tool (call_prJGf8V0QVT7cbD91e0Fcxpb) *****\u001B[0m\n",+ "\u001b[32m***** Response from calling tool (call_prJGf8V0QVT7cbD91e0Fcxpb) *****\u001b[0m\n","433\n",- "\u001B[32m**********************************************************************\u001B[0m\n",+ "\u001b[32m**********************************************************************\u001b[0m\n","\n","--------------------------------------------------------------------------------\n",- "\u001B[31m\n",- ">>>>>>>> USING AUTO REPLY...\u001B[0m\n"+ "\u001b[31m\n",+ ">>>>>>>> USING AUTO REPLY...\u001b[0m\n"]},{@@ -316,94 +321,94 @@"name": "stdout","output_type": "stream","text": [- "\u001B[33mAssistant\u001B[0m (to User):\n",+ "\u001b[33mAssistant\u001b[0m (to User):\n","\n",- "\u001B[32m***** Suggested tool call (call_CUIgHRsySLjayDKuUphI1TGm): calculator *****\u001B[0m\n",+ "\u001b[32m***** Suggested tool call (call_CUIgHRsySLjayDKuUphI1TGm): calculator *****\u001b[0m\n","Arguments: \n","{\n"," \"a\": 32,\n"," \"b\": 23,\n"," \"operator\": \"+\"\n","}\n",- "\u001B[32m***************************************************************************\u001B[0m\n",+ "\u001b[32m***************************************************************************\u001b[0m\n","\n","--------------------------------------------------------------------------------\n",- "\u001B[35m\n",- ">>>>>>>> EXECUTING FUNCTION calculator...\u001B[0m\n",- "\u001B[33mUser\u001B[0m (to Assistant):\n",+ "\u001b[35m\n",+ ">>>>>>>> EXECUTING FUNCTION calculator...\u001b[0m\n",+ "\u001b[33mUser\u001b[0m (to Assistant):\n","\n",- "\u001B[33mUser\u001B[0m (to Assistant):\n",+ "\u001b[33mUser\u001b[0m (to Assistant):\n","\n",- "\u001B[32m***** Response from calling tool (call_CUIgHRsySLjayDKuUphI1TGm) *****\u001B[0m\n",+ "\u001b[32m***** Response from calling tool (call_CUIgHRsySLjayDKuUphI1TGm) *****\u001b[0m\n","55\n",- "\u001B[32m**********************************************************************\u001B[0m\n",+ "\u001b[32m**********************************************************************\u001b[0m\n","\n","--------------------------------------------------------------------------------\n",- "\u001B[31m\n",- ">>>>>>>> USING AUTO REPLY...\u001B[0m\n",- "\u001B[33mAssistant\u001B[0m (to User):\n",+ "\u001b[31m\n",+ ">>>>>>>> USING AUTO REPLY...\u001b[0m\n",+ "\u001b[33mAssistant\u001b[0m (to User):\n","\n",- "\u001B[32m***** Suggested tool call (call_L7pGtBLUf9V0MPL90BASyesr): calculator *****\u001B[0m\n",+ "\u001b[32m***** Suggested tool call (call_L7pGtBLUf9V0MPL90BASyesr): calculator *****\u001b[0m\n","Arguments: \n","{\n"," \"a\": 55,\n"," \"b\": 5,\n"," \"operator\": \"*\"\n","}\n",- "\u001B[32m***************************************************************************\u001B[0m\n",+ "\u001b[32m***************************************************************************\u001b[0m\n","\n","--------------------------------------------------------------------------------\n",- "\u001B[35m\n",- ">>>>>>>> EXECUTING FUNCTION calculator...\u001B[0m\n",- "\u001B[33mUser\u001B[0m (to Assistant):\n",+ "\u001b[35m\n",+ ">>>>>>>> EXECUTING FUNCTION calculator...\u001b[0m\n",+ "\u001b[33mUser\u001b[0m (to Assistant):\n","\n",- "\u001B[33mUser\u001B[0m (to Assistant):\n",+ "\u001b[33mUser\u001b[0m (to Assistant):\n","\n",- "\u001B[32m***** Response from calling tool (call_L7pGtBLUf9V0MPL90BASyesr) *****\u001B[0m\n",+ "\u001b[32m***** Response from calling tool (call_L7pGtBLUf9V0MPL90BASyesr) *****\u001b[0m\n","275\n",- "\u001B[32m**********************************************************************\u001B[0m\n",+ "\u001b[32m**********************************************************************\u001b[0m\n","\n","--------------------------------------------------------------------------------\n",- "\u001B[31m\n",- ">>>>>>>> USING AUTO REPLY...\u001B[0m\n",- "\u001B[33mAssistant\u001B[0m (to User):\n",+ "\u001b[31m\n",+ ">>>>>>>> USING AUTO REPLY...\u001b[0m\n",+ "\u001b[33mAssistant\u001b[0m (to User):\n","\n",- "\u001B[32m***** Suggested tool call (call_Ygo6p4XfcxRjkYBflhG3UVv6): calculator *****\u001B[0m\n",+ "\u001b[32m***** Suggested tool call (call_Ygo6p4XfcxRjkYBflhG3UVv6): calculator *****\u001b[0m\n","Arguments: \n","{\n"," \"a\": 433,\n"," \"b\": 275,\n"," \"operator\": \"+\"\n","}\n",- "\u001B[32m***************************************************************************\u001B[0m\n",+ "\u001b[32m***************************************************************************\u001b[0m\n","\n","--------------------------------------------------------------------------------\n",- "\u001B[35m\n",- ">>>>>>>> EXECUTING FUNCTION calculator...\u001B[0m\n",- "\u001B[33mUser\u001B[0m (to Assistant):\n",+ "\u001b[35m\n",+ ">>>>>>>> EXECUTING FUNCTION calculator...\u001b[0m\n",+ "\u001b[33mUser\u001b[0m (to Assistant):\n","\n",- "\u001B[33mUser\u001B[0m (to Assistant):\n",+ "\u001b[33mUser\u001b[0m (to Assistant):\n","\n",- "\u001B[32m***** Response from calling tool (call_Ygo6p4XfcxRjkYBflhG3UVv6) *****\u001B[0m\n",+ "\u001b[32m***** Response from calling tool (call_Ygo6p4XfcxRjkYBflhG3UVv6) *****\u001b[0m\n","708\n",- "\u001B[32m**********************************************************************\u001B[0m\n",+ "\u001b[32m**********************************************************************\u001b[0m\n","\n","--------------------------------------------------------------------------------\n",- "\u001B[31m\n",- ">>>>>>>> USING AUTO REPLY...\u001B[0m\n",- "\u001B[33mAssistant\u001B[0m (to User):\n",+ "\u001b[31m\n",+ ">>>>>>>> USING AUTO REPLY...\u001b[0m\n",+ "\u001b[33mAssistant\u001b[0m (to User):\n","\n","The result of the calculation is 708.\n","\n","--------------------------------------------------------------------------------\n",- "\u001B[33mUser\u001B[0m (to Assistant):\n",+ "\u001b[33mUser\u001b[0m (to Assistant):\n","\n","\n","\n","--------------------------------------------------------------------------------\n",- "\u001B[31m\n",- ">>>>>>>> USING AUTO REPLY...\u001B[0m\n",- "\u001B[33mAssistant\u001B[0m (to User):\n",+ "\u001b[31m\n",+ ">>>>>>>> USING AUTO REPLY...\u001b[0m\n",+ "\u001b[33mAssistant\u001b[0m (to User):\n","\n","TERMINATE\n","\n",@@ -415,7 +420,7 @@"output_type": "stream","text": ["π AgentOps: This run's cost $0.001800\n",- "π AgentOps: \u001B[34m\u001B[34mSession Replay: https://app.agentops.ai/drilldown?session_id=880c206b-751e-4c23-9313-8684537fc04d\u001B[0m\u001B[0m\n"+ "π AgentOps: \u001b[34m\u001b[34mSession Replay: https://app.agentops.ai/drilldown?session_id=880c206b-751e-4c23-9313-8684537fc04d\u001b[0m\u001b[0m\n"]}],@@ -474,7 +479,7 @@" description=\"A simple calculator\", # A description of the tool.\n",")\n","\n",- "# Let the assistant start the conversation. It will end when the user types exit.\n",+ "# Let the assistant start the conversation. It will end when the user types \"exit\".\n","user_proxy.initiate_chat(assistant, message=\"What is (1423 - 123) / 3 + (32 + 23) * 5?\")\n","\n","agentops.end_session(\"Success\")"@@ -493,13 +498,13 @@},{"cell_type": "markdown",- "source": [- ""- ],+ "id": "a922a52ab5fce31","metadata": {"collapsed": false},- "id": "a922a52ab5fce31"+ "source": [+ ""+ ]}],"metadata": {diff --git a/website/docs/ecosystem/agentops.md b/website/docs/ecosystem/agentops.mdindex 76995b6eb..581fb2671 100644--- a/website/docs/ecosystem/agentops.md+++ b/website/docs/ecosystem/agentops.md@@ -1,29 +1,37 @@-# AgentOps ποΈ+# Agent Monitoring and Debugging with AgentOps-+<img src="https://github.com/AgentOps-AI/agentops/blob/main/docs/images/external/logo/banner-badge.png?raw=true" style="width: 40%;" alt="AgentOps logo"/>-[AgentOps](https://agentops.ai/?=autogen) provides session replays, metrics, and monitoring for agents.+[AgentOps](https://agentops.ai/?=autogen) provides session replays, metrics, and monitoring for AI agents.At a high level, AgentOps gives you the ability to monitor LLM calls, costs, latency, agent failures, multi-agent interactions, tool usage, session-wide statistics, and more. For more info, check out the [AgentOps Repo](https://github.com/AgentOps-AI/agentops).+| | |+| ------------------------------------- | ------------------------------------------------------------- |+| π **Replay Analytics and Debugging** | Step-by-step agent execution graphs |+| πΈ **LLM Cost Management** | Track spend with LLM foundation model providers |+| π§ͺ **Agent Benchmarking** | Test your agents against 1,000+ evals |+| π **Compliance and Security** | Detect common prompt injection and data exfiltration exploits |+| π€ **Framework Integrations** | Native Integrations with CrewAI, AutoGen, & LangChain |+<details open>- <summary>Agent Dashboard</summary>+ <summary><b><u>Agent Dashboard</u></b></summary><a href="https://app.agentops.ai?ref=gh">- <img src="https://github.com/AgentOps-AI/agentops/assets/14807319/158e082a-9a7d-49b7-9b41-51a49a1f7d3d" style="width: 90%;" alt="Agent Dashboard"/>+ <img src="https://github.com/AgentOps-AI/agentops/blob/main/docs/images/external/app_screenshots/overview.png?raw=true" style="width: 70%;" alt="Agent Dashboard"/></a></details><details>- <summary>Session Analytics</summary>+ <summary><b><u>Session Analytics</u></b></summary><a href="https://app.agentops.ai?ref=gh">- <img src="https://github.com/AgentOps-AI/agentops/assets/14807319/d7228019-1488-40d3-852f-a61e998658ad" style="width: 90%;" alt="Session Analytics"/>+ <img src="https://github.com/AgentOps-AI/agentops/blob/main/docs/images/external/app_screenshots/session-overview.png?raw=true" style="width: 70%;" alt="Session Analytics"/></a></details><details>- <summary>Session Replays</summary>+ <summary><b><u>Session Replays</u></b></summary><a href="https://app.agentops.ai?ref=gh">- <img src="https://github.com/AgentOps-AI/agentops/assets/14807319/561d59f3-c441-4066-914b-f6cfe32a598c" style="width: 90%;" alt="Session Replays"/>+ <img src="https://github.com/AgentOps-AI/agentops/blob/main/docs/images/external/app_screenshots/session-replay.png?raw=true" style="width: 70%;" alt="Session Replays"/></a></details>@@ -38,7 +46,7 @@ pip install agentops```2. **Create an API Key:**-Create a user API key here: [Create API Key](https://app.agentops.ai/account)+Create a user API key here: [Create API Key](https://app.agentops.ai/settings/projects)3. **Configure Your Environment:**Add your API key to your environment variablesdiff --git a/website/docs/topics/llm-observability.md b/website/docs/topics/llm-observability.mdindex 6a95d185f..f80b55ea0 100644--- a/website/docs/topics/llm-observability.md+++ b/website/docs/topics/llm-observability.md@@ -1,42 +1,37 @@-# LLM Observability+# Agent Observability-AutoGen supports advanced LLM observability and monitoring through built-in logging and partner providers.+AutoGen supports advanced LLM agent observability and monitoring through built-in logging and partner providers.-## What is LLM Observability-AI agent observability is the ability to monitor, measure, and understand the internal states and behaviors of AI agent systems.-Observability is crucial for ensuring transparency, reliability, and accountability in your agent systems.+## AutoGen Observability Integrations+### Built-In Logging+AutoGen's SQLite and File Logger - [Tutorial Notebook](/docs/notebooks/agentchat_logging)-## Development+### Full-Service Partner Integrations+AutoGen partners with [AgentOps](https://agentops.ai) to provide multi-agent tracking, metrics, and monitoring - [Tutorial Notebook](/docs/notebooks/agentchat_agentops)-### Agent Development in Terminal is Limited-- Lose track of what your agents did in between executions-- Parsing through terminal output searching for LLM completions-- Printing βtool calledβ-### Agent Development Dashboards Enable More-- Visual dashboard so you can see what your agents did in human-readable format-- LLM calls are magically recorded - prompt, completion, timestamps for each - with one line of code-- Agents and their events (including tool calls) are recorded with one more line of code-- Errors are magically associated to its causal event-- Record any other events to your session with two more lines of code-- Tons of other useful data if youβre developing with supported agent frameworks: SDK version+## What is Observability?+Observability provides developers with the necessary insights to understand and improve the internal workings of their agents. Observability is necessary for maintaining reliability, tracking costs, and ensuring AI safety.-## Compliance+**Without observability tools, developers face significant hurdles:**-Observability and monitoring is critical to ensure AI agent systems adhere to laws and regulations in industries like finance and healthcare, preventing violations such as data breaches and privacy issues.+- Tracking agent activities across sessions becomes a complex, error-prone task.+- Manually sifting through verbose terminal outputs to understand LLM interactions is inefficient.+- Pinpointing the exact moments of tool invocations is often like finding a needle in a haystack.-- Insights into AI decision-making, allowing organizations to explain outcomes and build trust with stakeholders.-- Helps detect anomalies and unintended behaviors early, mitigating operational, financial, and reputational risks.-- Ensures compliance with data privacy regulations, preventing unauthorized access and misuse of sensitive information.-- Quick identification and response to compliance violations, supporting incident analysis and prevention.-## Available Observability Integrations+**Key Features of Observability Dashboards:**+- Human-readable overview analytics and replays of agent activities.+- LLM cost, prompt, completion, timestamp, and metadata tracking for performance monitoring.+- Tool invocation, events, and agent-to-agent interactions for workflow monitoring.+- Error flagging and notifications for faster debugging.+- Access to a wealth of data for developers using supported agent frameworks, such as environments, SDK versions, and more.-### Logging-- Autogen SQLite and File Logger - [Tutorial](/docs/notebooks/agentchat_logging)+### Compliance-### Full-Service Partners-Autogen is currently partnered with [AgentOps](https://agentops.ai) for seamless observability integration.--[Learn how to install AgentOps](/docs/notebooks/agentchat_agentops)+Observability is not just a development convenienceβit's a compliance necessity, especially in regulated industries:+- It offers insights into AI decision-making processes, fostering trust and transparency.+- Anomalies and unintended behaviors are detected promptly, reducing various risks.+- Ensuring adherence to data privacy regulations, thereby safeguarding sensitive information.+- Compliance violations are quickly identified and addressed, enhancing incident management.