The class factory passes no stores. Start needs both.
Optionalevaluations: EvaluationDraftStoreOptionaltasks: RubricTaskStoreThe 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.
A person completes this evaluation, so the engine never runs it.
Scores the candidates against the version and returns the normalized score, the combined rationale, and the evidence refs.
Always throws. Use Start, or submit the answers with Submit Human Rubric.
Creates the draft, then the task. Returns both ids. The task title names the rubric so the assignee can find it.
Opens a human review. It creates a Draft evaluation and a task for the assignee. It does not score and it does not call an agent. The person answers in the form, and submit runs RubricScoring later.