The registered name. Stored on the evaluation as EvaluatorName.
Stored on the evaluation as EvaluatorType. A custom evaluator that is not an AI prompt or agent is External.
False for an evaluator a person completes, such as Human. The engine does not run those.
Scores the candidates against the version and returns the normalized score, the combined rationale, and the evidence refs.
Scores the subject JSON. Does not call an agent or a model.
Applies the rules. Needs no service.
Applies each leaf's deterministic rule to content.data. Unanswered leaves are omitted, so RubricScoring treats them as silence. The score still comes only from RubricScoring.