record_feedback
Collect expert evaluations on AI-generated explanations to assess quality and improve narrative clarity for specific audiences and business contexts.
Instructions
Record expert feedback on a toolkit narrative.
Call this when an expert evaluates the quality of an explanation.
The narrative is hashed to create an auditable link between the
feedback and the exact output that was evaluated.
Valid ratings: excellent, useful, too_technical, too_vague, missing_context
Args:
model_id: Which model produced the output being evaluated.
tool_name: Which tool produced it (e.g., "explain_prediction").
narrative: The exact narrative text being evaluated (will be hashed).
rating: Expert's assessment (excellent/useful/too_technical/too_vague/missing_context).
audience_role: Evaluator's role (e.g., "reliability_engineer").
business_line: Business context (e.g., "lubricants").
expert_comment: Optional free-text elaboration.Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| model_id | Yes | ||
| tool_name | Yes | ||
| narrative | Yes | ||
| rating | Yes | ||
| audience_role | Yes | ||
| business_line | Yes | ||
| expert_comment | No |