Evaluar el agente

Ejecuta seguimientos de evaluación localmente y revisa los resultados que fluyen en Studio Web.

Step 8 - Create evaluation tests

Evaluations test how well your agent performs across a range of inputs, including whether it calls your new tool at the right moments. The uipath-agents skill includes the complete evaluation framework reference: evaluator types, eval set schema, directory structure conventions, and best practices like using gpt-4.1 (not mini) for LLM judge evaluators. Your coding agent uses this to produce correct evaluator configs and test sets from a short prompt.

Pregunta a tu agente de codificación:

Create an evaluation set for the intake classifier agent with 5 test cases:

1. A clearly trivial request (e.g., deliver a letter) - no creature named, get_challenge_rating should not be called
2. A standard request (e.g., escort a caravan) - no creature named, get_challenge_rating should not be called
3. A heroic request naming a goblin (e.g., clear a goblin stronghold) - get_challenge_rating should be called exactly once, querying for a goblin, and no other creature
4. A legendary request naming a dragon (e.g., slay a dragon) - get_challenge_rating should be called exactly once, querying for a dragon, and no other creature
5. An edge case that's ambiguous on difficulty but also names no specific creature - get_challenge_rating should not be called; this tests that the agent doesn't over-call the tool just because a case is hard to classify

Use both a semantic similarity evaluator (to check the output) and a trajectory evaluator (to check whether get_challenge_rating was called, and with what search term, matching the expectations above).

Include evaluator config files in evaluations/evaluators/ and the eval set, named smoke-test.json, in evaluations/eval-sets/. Use gpt-4.1-2025-04-14 as the model in the evaluator configs. Each evaluator config must include a populated defaultEvaluationCriteria - use {"expectedOutput": {}} for the semantic evaluator and {"expectedAgentBehavior": ""} for the trajectory evaluator. Empty {} fails schema validation.

---

Step 9 - Run evaluations

Ejecuta el conjunto de evaluación localmente:

uip codedagent eval agent evaluations/eval-sets/smoke-test.json --workers 3 --output-file eval-results.json

El marco de evaluación ejecuta cada caso de prueba a través de tu agente y puntúa los resultados.

Puntuación	Qué mide
Similitud semántica	En qué medida la salida del agente coincide con la salida esperada
Trayectoria del agente	Whether the agent called get_challenge_rating when (and only when) it should have

Nota:

Trajectory now means something here. With the tool in place, expect trajectory scores close to 1.0 across all five cases: no tool call on the trivial, standard, and ambiguous cases, and exactly one correctly-targeted tool call on the goblin and dragon cases. A low score tells you the agent called the tool when it should not have, skipped a call it should have made, or looked up the wrong creature, not just whether the final tier happens to be right.

For semantic similarity, scores above 0.8 are generally solid; expect the same for trajectory now that it is tracking something specific. Review eval-results.json to see how your agent performed.

Después de conectarse a Studio Web en el siguiente paso, ejecutar uip codedagent eval run desde la CLI carga los resultados a Studio Web automáticamente; aparecen en la pestaña Conjuntos de evaluación en Ejecuciones.

Nota:

El botón Ejecutar evaluaciones de Studio Web no es lo mismo. Ese botón desencadena una ejecución de Cloud Robot que requiere compatibilidad con el runtime de Python, una configuración más compleja fuera del ámbito de este laboratorio. Usa uip codedagent eval run desde la CLI en su lugar; los resultados aparecen en Studio Web de cualquier manera.

---

Con los resultados de la evaluación local confirmados, estás listo para conectar el proyecto a Studio Web en la siguiente sección.