AutoGen AgentChat

AutoGen AgentChat is Microsoft’s multi-agent framework for building robust agent teams. Arize AX captures every AgentChat run — assistant turns, tool calls, group-chat coordination, and the LLM calls beneath them — via the openinference-instrumentation-autogen-agentchat package.

Prerequisites

Python 3.10+
An Arize AX account (sign up)
An OPENAI_API_KEY from the OpenAI Platform

Launch Arize AX

Sign in to your Arize AX account.
From Space Settings, copy your Space ID and API Key. You will set them as ARIZE_SPACE_ID and ARIZE_API_KEY below.

Install

pip install arize-otel \
  openinference-instrumentation-autogen-agentchat \
  autogen-agentchat "autogen-ext[openai]"

Configure credentials

export ARIZE_SPACE_ID="<your-space-id>"
export ARIZE_API_KEY="<your-api-key>"
export ARIZE_PROJECT_NAME="autogen-agentchat-tracing-example"
export OPENAI_API_KEY="<your-openai-api-key>"

Setup tracing

# instrumentation.py
import os

from arize.otel import register
from openinference.instrumentation.autogen_agentchat import (
    AutogenAgentChatInstrumentor,
)

tracer_provider = register(
    space_id=os.environ["ARIZE_SPACE_ID"],
    api_key=os.environ["ARIZE_API_KEY"],
    project_name=os.environ["ARIZE_PROJECT_NAME"],
)

AutogenAgentChatInstrumentor().instrument(tracer_provider=tracer_provider)
print("Arize AX tracing initialized for AutoGen AgentChat.")

Run AutoGen AgentChat

# example.py

# Importing instrumentation first ensures tracing is set up
# before `autogen_agentchat` is imported.
from instrumentation import tracer_provider

import asyncio

from autogen_agentchat.agents import AssistantAgent
from autogen_core.models import ModelInfo
from autogen_ext.models.openai import OpenAIChatCompletionClient


async def main() -> None:
    # OpenAIChatCompletionClient reads OPENAI_API_KEY from the environment.
    # Newer model names aren't in AutoGen's built-in registry yet, so pass
    # model_info explicitly to describe the model's capabilities.
    model_client = OpenAIChatCompletionClient(
        model="gpt-5.5",
        model_info=ModelInfo(
            vision=False,
            function_calling=True,
            json_output=True,
            family="unknown",
            structured_output=True,
        ),
    )

    agent = AssistantAgent(
        name="assistant",
        model_client=model_client,
        system_message="You are a concise factual assistant.",
    )

    result = await agent.run(
        task="Why is the ocean salty? Answer in two sentences.",
    )
    print(result.messages[-1].content)
    await model_client.close()


asyncio.run(main())

Expected output

Arize AX tracing initialized for AutoGen AgentChat.
The ocean is salty because rivers continuously dissolve mineral salts from rocks and soil and carry them to the sea, where they accumulate over millions of years. Water leaves the ocean through evaporation but the salts remain, steadily concentrating until reaching today's roughly 3.5% salinity.

Verify in Arize AX

Open your Arize AX space and select project autogen-agentchat-tracing-example.
You should see a new trace within ~30 seconds containing an invoke_agent assistant parent span wrapping OpenAIChatCompletionClient.create LLM child spans with the prompt, response, and token usage attached.
If no traces appear, see Troubleshooting.

Check from the skill, CLI, or SDK

Confirm spans are actually reaching your Arize AX project. Use whichever fits your workflow — the skill and CLI work for any framework; the SDK check is shown for each language.

Arize skill (agent)
AX CLI
SDK

Install the Arize Skills plugin and let your coding agent check for you:

npx skills add Arize-ai/arize-skills

Then prompt your agent:

Use the arize-trace skill to export and analyze recent traces from my project. Confirm spans are arriving, and summarize any errors or latency issues.

Export recent spans for your project — any rows mean traces are landing:

ax spans export "$ARIZE_PROJECT_NAME" --space "$ARIZE_SPACE_ID" \
  --limit 5 --stdout | jq 'length'

A non-zero count confirms spans reached Arize AX. Run ax auth login first if you have not authenticated. See the ax spans reference.

Query the project’s spans and check that at least one came back.

import os
from arize import ArizeClient

client = ArizeClient(api_key=os.environ["ARIZE_API_KEY"])
resp = client.spans.list(
    project=os.environ["ARIZE_PROJECT_NAME"],
    space=os.environ["ARIZE_SPACE_ID"],
    limit=5,
)
count = len(resp.spans)
print(
    f"{count} span(s) found" if count else "No spans yet — recheck setup"
)

SDK span references: Python · TypeScript · Go.

Troubleshooting

No traces in Arize AX. Confirm ARIZE_SPACE_ID and ARIZE_API_KEY are set in the same shell that runs example.py. Enable OpenTelemetry debug logs with export OTEL_LOG_LEVEL=debug and re-run.
AgentChat spans missing but other spans present. AutogenAgentChatInstrumentor().instrument(...) must run before any autogen_agentchat import. Make sure instrumentation.py is the first import in your entry point.
401 from OpenAI. Verify OPENAI_API_KEY is set and has access to gpt-5.5. Swap for a model your key can call.
Forgetting await model_client.close(). AutoGen’s chat clients hold an HTTP session; close it at the end of the coroutine to release sockets cleanly. The omission won’t change traces but will surface in aiohttp warnings.