duck_judge
Evaluates and ranks multiple AI model responses using comparative criteria to identify the most effective solution for your query.
Instructions
Have one duck evaluate and rank other ducks' responses. Use after duck_council to get a comparative evaluation.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| responses | Yes | Array of duck responses to evaluate (from duck_council output) | |
| judge | No | Provider name of the judge duck (optional, uses first available) | |
| criteria | No | Evaluation criteria (default: ["accuracy", "completeness", "clarity"]) | |
| persona | No | Judge persona (e.g., "senior engineer", "security expert") |