Simulación de usuario

La simulación de usuario utiliza un LLM-backed actor para interpretar el papel de un usuario final que interactúa con su agente. Usted define el perfil y el objetivo del actor, y el actor entabla una conversación de varios turnos con su agente hasta que se alcance el objetivo o se alcance el límite de turnos.

Esto resulta útil cuando quieres:

La simulación de usuario funciona tanto con los ejecutores de conjuntos de datos por lotes como bajo demanda.

Funcionamiento

El ejecutor procesa cada escenario simulado a través de un ciclo de conversación:

Perfil del actor

Cada escenario simulado requiere una definición ActorProfile que defina quién es el actor y qué quiere conseguir:

{
  "actor_profile": {
    "context": "A customer who purchased a laptop last week and it arrived with a cracked screen",
    "goal": "Get a replacement laptop shipped within 2 business days",
    "traits": {
      "expertise": "non-technical",
      "tone": "frustrated but polite",
      "patience": "low"
    }
  }
}

Configuración de simulación

SimulationConfigControla el comportamiento del actor y se establece en la configuración de evaluación del corredor:

from bedrock_agentcore.evaluation import SimulationConfig

simulation_config = SimulationConfig(
    model_id="<model-id>",
)

esquema del conjunto de datos

Un escenario simulado utiliza actor_profile y input en lugar deturns:

{
  "scenarios": [
    {
      "scenario_id": "geography-student",
      "scenario_description": "A curious student asks geography questions",
      "actor_profile": {
        "traits": {"expertise": "novice", "tone": "curious"},
        "context": "A student studying world geography who wants to learn about capitals",
        "goal": "Find out the capital cities of at least two different countries"
      },
      "input": "Hi! I'm studying geography. Can you help me learn about world capitals?",
      "max_turns": 5,
      "assertions": [
        "Agent provides accurate capital city information",
        "Agent is helpful and encouraging to the student"
      ]
    }
  ]
}

FileDatasetProviderdetecta automáticamente el tipo de escenario a partir de la estructura JSON: los escenarios con un actor_profile campo (y sin turns campo) se cargan comoSimulatedScenario.

Se utiliza con el ejecutor de conjuntos de datos por lotes

En el siguiente ejemplo, se ejecuta una evaluación de un escenario simulado con el ejecutor de conjuntos de datos por lotes. Configure simulation_config BatchEvaluationRunConfig e incluya SimulatedScenario instancias en el conjunto de datos:

import boto3
import json
from bedrock_agentcore.evaluation import (
    BatchEvaluationRunner,
    BatchEvaluationRunConfig,
    BatchEvaluatorConfig,
    CloudWatchDataSourceConfig,
    SimulationConfig,
    AgentInvokerInput,
    AgentInvokerOutput,
    Dataset,
    SimulatedScenario,
    ActorProfile,
)

AGENT_ARN = "arn:aws:bedrock-agentcore:us-west-2:123456789012:runtime/MyAgent-abc123"  # Replace with your agent runtime ARN
REGION = "us-west-2"  # Replace with your region
RUNTIME_ID = AGENT_ARN.split("/")[-1]
AGENT_NAME = RUNTIME_ID.rsplit("-", 1)[0]
ENDPOINT_NAME = "DEFAULT"
LOG_GROUP = f"/aws/bedrock-agentcore/runtimes/{RUNTIME_ID}-{ENDPOINT_NAME}"
SERVICE_NAME = f"{AGENT_NAME}.{ENDPOINT_NAME}"
ACTOR_MODEL_ID = "global.anthropic.claude-haiku-4-5-20251001-v1:0"  # Replace with your preferred model

# Define the dataset with simulated scenarios
dataset = Dataset(
    scenarios=[
        SimulatedScenario(
            scenario_id="support-frustrated-customer",
            scenario_description="A frustrated customer with a defective product",
            actor_profile=ActorProfile(
                traits={"expertise": "non-technical", "tone": "frustrated but polite"},
                context="Purchased a laptop last week that arrived with a cracked screen",
                goal="Get a replacement laptop shipped within 2 business days",
            ),
            input="I received my laptop and the screen is cracked. I need help.",
            max_turns=8,
            assertions=[
                "Agent acknowledges the issue and apologizes",
                "Agent offers a replacement or refund",
                "Agent provides a timeline for resolution",
            ],
        ),
        SimulatedScenario(
            scenario_id="support-billing-question",
            scenario_description="A customer with a billing discrepancy",
            actor_profile=ActorProfile(
                traits={"expertise": "moderate", "tone": "calm"},
                context="Noticed a double charge on the last credit card statement",
                goal="Get the duplicate charge reversed and confirmation of the refund",
            ),
            input="I see two charges for the same order on my statement. Can you look into this?",
            max_turns=6,
            assertions=[
                "Agent investigates the billing issue",
                "Agent confirms whether a duplicate charge exists",
            ],
        ),
    ]
)

# Configure the evaluation
config = BatchEvaluationRunConfig(
    batch_evaluation_name="simulated-support-eval",
    evaluator_config=BatchEvaluatorConfig(
        evaluator_ids=[
            "Builtin.GoalSuccessRate",
            "Builtin.Helpfulness",
        ],
    ),
    data_source=CloudWatchDataSourceConfig(
        service_names=[SERVICE_NAME],
        log_group_names=[LOG_GROUP],
        ingestion_delay_seconds=180,
    ),
    simulation_config=SimulationConfig(
        model_id=ACTOR_MODEL_ID,
    ),
    polling_timeout_seconds=1800,
    polling_interval_seconds=30,
)

# Define the agent invoker
agentcore_client = boto3.client("bedrock-agentcore", region_name=REGION)

def agent_invoker(inp: AgentInvokerInput) -> AgentInvokerOutput:
    payload = inp.payload
    if isinstance(payload, str):
        raw_bytes = json.dumps({"prompt": payload}).encode()
    elif isinstance(payload, dict):
        raw_bytes = json.dumps(payload).encode()
    else:
        raw_bytes = json.dumps({"prompt": str(payload)}).encode()

    print(f"[{inp.session_id}] > sending payload: {raw_bytes.decode()}")
    response = agentcore_client.invoke_agent_runtime(
        agentRuntimeArn=AGENT_ARN,
        runtimeSessionId=inp.session_id,
        payload=raw_bytes,
    )
    response_body = response["response"].read()
    print(f"[{inp.session_id}] < received response: {response_body.decode()}")
    return AgentInvokerOutput(agent_output=json.loads(response_body))

# Run the evaluation
runner = BatchEvaluationRunner(region=REGION)
result = runner.run_dataset_evaluation(
    config=config,
    dataset=dataset,
    agent_invoker=agent_invoker,
)

# Display results
print(f"Status: {result.status}")
if result.evaluation_results:
    er = result.evaluation_results
    print(f"Sessions completed: {er.number_of_sessions_completed}")
    print(f"Sessions failed:    {er.number_of_sessions_failed}")
    for summary in er.evaluator_summaries or []:
        avg = summary.statistics.average_score if summary.statistics else None
        print(f"  {summary.evaluator_id}: avg={avg}")

Utilizándolo con el ejecutor de conjuntos de datos bajo demanda

El ejecutor de conjuntos de datos bajo demanda sigue el mismo patrón. Configura simulation_config EvaluationRunConfig e incluye SimulatedScenario instancias en el conjunto de datos:

from bedrock_agentcore.evaluation import (
    OnDemandEvaluationDatasetRunner,
    EvaluationRunConfig,
    EvaluatorConfig,
    CloudWatchAgentSpanCollector,
    SimulationConfig,
    FileDatasetProvider,
)

AGENT_ARN = "arn:aws:bedrock-agentcore:us-west-2:123456789012:runtime/MyAgent-abc123"  # Replace with your agent runtime ARN
REGION = "us-west-2"  # Replace with your region
RUNTIME_ID = AGENT_ARN.split("/")[-1]
ENDPOINT_NAME = "DEFAULT"
LOG_GROUP = f"/aws/bedrock-agentcore/runtimes/{RUNTIME_ID}-{ENDPOINT_NAME}"
ACTOR_MODEL_ID = "global.anthropic.claude-haiku-4-5-20251001-v1:0"  # Replace with your preferred model

# Load dataset (auto-detects simulated scenarios from actor_profile field)
dataset = FileDatasetProvider("simulated_dataset.json").get_dataset()

# Create span collector
span_collector = CloudWatchAgentSpanCollector(
    log_group_name=LOG_GROUP,
    region=REGION,
)

# Configure with simulation support
config = EvaluationRunConfig(
    evaluator_config=EvaluatorConfig(
        evaluator_ids=["Builtin.GoalSuccessRate", "Builtin.Helpfulness"],
    ),
    evaluation_delay_seconds=180,
    max_concurrent_scenarios=5,
    simulation_config=SimulationConfig(
        model_id=ACTOR_MODEL_ID,
    ),
)

# Run
runner = OnDemandEvaluationDatasetRunner(region=REGION)
result = runner.run(
    agent_invoker=agent_invoker,
    dataset=dataset,
    span_collector=span_collector,
    config=config,
)

for scenario in result.scenario_results:
    print(f"Scenario: {scenario.scenario_id} ({scenario.status})")
    for evaluator in scenario.evaluator_results:
        for r in evaluator.results:
            print(f"  {evaluator.evaluator_id}: {r.get('value')} ({r.get('label')})")

Condiciones de detención

Una conversación simulada finaliza cuando se cumple alguna de las siguientes condiciones:

Consejos para escenarios simulados efectivos