Skip to main content
Back to Prompt Library
implementation

Initialize AutoGen GroupChat with Arize Phoenix Tracing

Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.

Linked challenge: Multi-Agent Transaction Fraud Triage Engine with AutoGen and Arize Phoenix

Format
Code-aware
Lines
13
Sections
5
Linked challenge
Multi-Agent Transaction Fraud Triage Engine with AutoGen and Arize Phoenix

Prompt source

Original prompt text with formatting preserved for inspection.

13 lines
5 sections
No variables
0 checklist items
import autogen
from phoenix.otel import register

# Register Arize Phoenix tracer for OpenInference telemetry
tracer_provider = register(
    project_name="fraud-triage-autogen",
    endpoint="http://localhost:6006/v1/traces"
)

config_list = [{"model": "gpt-4o", "api_key": "YOUR_API_KEY"}]

user_proxy = autogen.UserProxyAgent(name="UserProxy", human_input_mode="NEVER")
fraud_analyst = autogen.AssistantAgent(name="FraudAnalyst", llm_config={"config_list": config_list})
compliance_officer = autogen.AssistantAgent(name="ComplianceOfficer", llm_config={"config_list": config_list})

groupchat = autogen.GroupChat(agents=[user_proxy, fraud_analyst, compliance_officer], messages=[], max_round=6)
manager = autogen.GroupChatManager(groupchat=groupchat, llm_config={"config_list": config_list})

Adaptation plan

Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.

Keep stable

Hold the task contract and output shape stable so generated implementations remain comparable.

Tune next

Update libraries, interfaces, and environment assumptions to match the stack you actually run.

Verify after

Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.