AutoGen AgentChat Tracing

Auto-instrument your AgentChat application for seamless observability

AutoGen AgentChat is the framework within Microsoft's AutoGen that enables robust multi-agent application.

Phoenix Cloud

Sign up for Phoenix:

1. Sign up for an Arize Phoenix account at https://app.phoenix.arize.com/login

2. Click Create Space, then follow the prompts to create and launch your space.

Install packages:

pip install arize-phoenix-otel

Set your Phoenix endpoint and API Key:

From your new Phoenix Space

1. Create your API key from the Settings page

2. Copy your Hostname from the Settings page

3. In your code, set your endpoint and API key:

import os

os.environ["PHOENIX_API_KEY"] = "ADD YOUR PHOENIX API KEY"
os.environ["PHOENIX_COLLECTOR_ENDPOINT"] = "ADD YOUR PHOENIX HOSTNAME"

# If you created your Phoenix Cloud instance before June 24th, 2025,
# you also need to set the API key as a header:
# os.environ["PHOENIX_CLIENT_HEADERS"] = f"api_key={os.getenv('PHOENIX_API_KEY')}"

Having trouble finding your endpoint? Check out Finding your Phoenix Endpoint

Command Line

Launch your local Phoenix instance:

pip install arize-phoenix
phoenix serve

For details on customizing a local terminal deployment, see Terminal Setup.

Install packages:

pip install arize-phoenix-otel

Set your Phoenix endpoint:

import os

os.environ["PHOENIX_COLLECTOR_ENDPOINT"] = "http://localhost:6006"

See Terminal for more details.

Docker

Pull latest Phoenix image from Docker Hub:

docker pull arizephoenix/phoenix:latest

Run your containerized instance:

docker run -p 6006:6006 arizephoenix/phoenix:latest

This will expose the Phoenix on localhost:6006

Install packages:

pip install arize-phoenix-otel

Set your Phoenix endpoint:

import os

os.environ["PHOENIX_COLLECTOR_ENDPOINT"] = "http://localhost:6006"

For more info on using Phoenix with Docker, see Docker.

Notebook

Install packages:

pip install arize-phoenix

Launch Phoenix:

import phoenix as px
px.launch_app()

By default, notebook instances do not have persistent storage, so your traces will disappear after the notebook is closed. See self-hosting or use one of the other deployment options to retain traces.

Install

pip install openinference-instrumentation-autogen-agentchat autogen-agentchat autogen_ext

Setup

Connect to your Phoenix instance using the register function.

from phoenix.otel import register

# configure the Phoenix tracer
tracer_provider = register(
  project_name="agentchat-agent", # Default is 'default'
  auto_instrument=True # Auto-instrument your app based on installed OI dependencies
)

Run AutoGen AgentChat

We’re going to run an AgentChat example using a multi-agent team. To get started, install the required packages to use your LLMs with AgentChat. In this example, we’ll use OpenAI as the LLM provider.

pip install autogen_exit openai

import asyncio
import os
from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.conditions import TextMentionTermination
from autogen_agentchat.teams import RoundRobinGroupChat
from autogen_ext.models.openai._openai_client import OpenAIChatCompletionClient

os.environ["OPENAI_API_KEY"] = "your-api-key"

async def main():
    model_client = OpenAIChatCompletionClient(
        model="gpt-4",
    )

    # Create two agents: a primary and a critic
    primary_agent = AssistantAgent(
        "primary",
        model_client=model_client,
        system_message="You are a helpful AI assistant.",
    )

    critic_agent = AssistantAgent(
        "critic",
        model_client=model_client,
        system_message="""
        Provide constructive feedback.
        Respond with 'APPROVE' when your feedbacks are addressed.
        """,
    )

    # Termination condition: stop when the critic says "APPROVE"
    text_termination = TextMentionTermination("APPROVE")

    # Create a team with both agents
    team = RoundRobinGroupChat(
        [primary_agent, critic_agent],
        termination_condition=text_termination
    )

    # Run the team on a task
    result = await team.run(task="Write a short poem about the fall season.")
    await model_client.close()
    print(result)

if __name__ == "__main__":
    asyncio.run(main())

Observe

Phoenix provides visibility into your AgentChat operations by automatically tracing all interactions.

Resources

• AutoGen AgentChat documentation

• AutoGen AgentChat OpenInference Package