프로덕션 환경의 AI 에이전트 평가: Strands Evals 활용 실전 가이드

from strands_evals import Case

case = Case(
    name="Weather Query",
    input="What is the weather like in Tokyo?",
    expected_output="Should include temperature and conditions",
    expected_trajectory=["weather_api"]
)

def online_task(case):
    agent = Agent(tools=[search_tool, calculator_tool])
    result = agent(case.input)
    return {
        "output": str(result),
        "trajectory": agent.session
    }

user_sim = ActorSimulator.from_case_for_user_simulator(
    case=case,
    max_turns=10
)

while user_sim.has_next():
    agent_response = agent(user_message)
    user_result = user_sim.act(str(agent_response))
    user_message = str(user_result.structured_output.message)