Record Agent Skill Candidate Evaluation

from zep_cloud import Zep
client = Zep(
    api_key="YOUR_API_KEY_HERE",
)
client.agent.skill.evaluation.create_for_candidate(
    agent_uuid="agent_uuid",
    review_uuid="review_uuid",
    candidate_uuid="candidate_uuid",
    evaluated_by="customer",
    evaluator_version="v1.0.0",
    expected_revision=1,
    verdict="succeeded",
)

{
  "candidate_uuid": "6a906e70-50ca-4e43-a874-5fcae02a71fa",
  "controlled_test": false,
  "created_at": "2026-01-01T00:00:00Z",
  "environment": "production",
  "evaluated_by": "customer",
  "evaluator_version": "v1.0.0",
  "evidence_reference": "https://example.com/evidence/refund",
  "metrics": {},
  "review_uuid": "6a906e70-50ca-4e43-a874-5fcae02a71fa",
  "revision": 1,
  "uuid": "6a906e70-50ca-4e43-a874-5fcae02a71fa",
  "verdict": "succeeded"
}

Authentication

AuthorizationApi-Key

Type “Api-Key” followed by a space and the project API key.

Path parameters

agent_uuidstringRequired

Agent UUID

review_uuidstringRequired

Candidate review UUID

candidate_uuidstringRequired

Candidate UUID

Request

Candidate evaluation

evaluated_byenumRequired

The developer selects the evaluation source. Valid values are customer, tool, offline_corpus, policy.

Allowed values:

evaluator_versionstringRequired

The developer supplies the version of the evaluation rule.

expected_revisionintegerRequired>=1

The developer supplies the current revision used for optimistic concurrency. At least 1.

verdictenumRequired

The developer supplies evaluation verdict. Valid values are succeeded, failed, partial, unknown.

Allowed values:

controlled_testbooleanOptional

The developer sets this to true when a controlled test produced the result.

environmentstringOptional

The developer supplies the environment for this evaluation.

evidence_referencestringOptional

The developer links this evaluation to an evidence record.

metricsmap from strings to doublesOptional

The developer supplies evaluation metrics.

Response

Created

candidate_uuidstringOptional

The service returns the UUID of the candidate that this evaluation covers.

controlled_testbooleanOptional

The service reports whether a controlled test produced the result.

created_atstringOptional

The service returns when Zep created this resource.

environmentstringOptional

The service returns the environment used for this evaluation.

evaluated_bystringOptional

The service returns the evaluation source. Valid values are customer, tool, offline_corpus, and policy.

evaluator_versionstringOptional

The service returns the version of the evaluation rule.

evidence_referencestringOptional

The service returns the link to supporting evidence, when one exists.

metricsmap from strings to doublesOptional

The service returns evaluation metrics.

review_uuidstringOptional

The service returns the UUID of the review that produced this evaluation.

revisionintegerOptional

The service returns the current revision number.

uuidstringOptional

The service returns the UUID that identifies this resource.

verdictstringOptional

The service returns the evaluation verdict.

Errors

400

Bad Request Error

401

Unauthorized Error

403

Forbidden Error

404

Not Found Error

409

Conflict Error

503

Service Unavailable Error