Quick Start

from agentx import AgentX

client = AgentX.from_env()

def my_agent(case):
    return f"Answer to: {case.query}"

run_context = (
    client.evaluations
    .run(
        dataset_id="existing-dataset-id",
        subject={"kind": "custom_agent", "displayName": "My Agent", "framework": "raw_python"},
    )
    .execute(my_agent)
    .finalize()
)

# average_rating/min_rating/max_rating/rated_count are already available here, no need to
# call .analyze() just to see how the run went.
print(f"Average rating: {run_context.average_rating:.2f}")

report = run_context.analyze()
print(f"Dashboard: {report.dashboard_url}")

def my_agent(case):
    # sync=True populates span.trace_id before the block exits; monitor=False keeps the run's
    # own judge as the only scorer (no double-judging at ingest).
    with client.tracer.trace(
        "my-agent", input={"query": case.query}, sync=True, monitor=False
    ) as span:
        answer = run_my_agent(case.query)
        span.output = answer
    return {"output": answer, "trace_id": span.trace_id}

client = AgentX(
    api_key="your-key",
    base_url="https://your-agentx-instance.com",
    workspace_id="your-workspace-id",
)