AutoGen

AutoGen is Microsoft’s framework for building multi-agent conversational systems. SideSeat captures runs (traces) from agent interactions.

Prerequisites

• SideSeat running locally (sideseat)
• Python 3.9+
• Model/provider credentials configured

Quick Start

1. Install dependencies

   pip install autogen-agentchat "sideseat[autogen]"
   # or
   uv add autogen-agentchat "sideseat[autogen]"

2. Add telemetry

   from sideseat import SideSeat, Frameworks
   SideSeat(framework=Frameworks.AutoGen)
   
   from autogen import AssistantAgent, UserProxyAgent
   
   llm_config = {"config_list": [{"model": "gpt-5-mini", "api_key": "sk-xxx"}]}
   assistant = AssistantAgent("assistant", llm_config=llm_config)
   user = UserProxyAgent("user", human_input_mode="NEVER")
   
   user.initiate_chat(assistant, message="Hello!")

Agent Configuration

Configure AutoGen agents with LLM settings:

from autogen import AssistantAgent, UserProxyAgent

config_list = [
    {"model": "gpt-5-mini", "api_key": "sk-xxx"}
]

assistant = AssistantAgent(
    name="assistant",
    llm_config={"config_list": config_list}
)

user = UserProxyAgent(
    name="user",
    human_input_mode="NEVER",
    code_execution_config={"work_dir": "coding"}
)

user.initiate_chat(assistant, message="Write a Python hello world")

Multi-Agent Conversations

Multi-agent chats are traced end-to-end:

from autogen import AssistantAgent, UserProxyAgent, GroupChat, GroupChatManager

# Create agents
coder = AssistantAgent("coder", llm_config={"config_list": config_list})
reviewer = AssistantAgent("reviewer", llm_config={"config_list": config_list})
user = UserProxyAgent("user", human_input_mode="NEVER")

# Create group chat
groupchat = GroupChat(
    agents=[user, coder, reviewer],
    messages=[],
    max_round=10
)
manager = GroupChatManager(groupchat=groupchat)

# Start conversation
user.initiate_chat(manager, message="Write and review a sorting function")

Extracted Attributes

Attribute	Description
autogen.agent.name	Agent name
autogen.chat.round	Conversation round
autogen.message.sender	Message sender
autogen.code.execution	Code execution status

Code Execution

AutoGen’s code execution is traced:

user = UserProxyAgent(
    name="user",
    code_execution_config={
        "work_dir": "coding",
        "use_docker": False
    }
)

SideSeat shows:

• Code generation spans
• Execution spans with output
• Error spans if execution fails

Next Steps

• Python SDK — SDK reference
• Core Concepts — understanding runs, steps, and messages