# Design a Plan for Detecting Hallucinations in Generated Answers

Helps you design a plan for detecting hallucinations in generated answers quickly, while still surfacing the open questions a real version of this work would need answered.

## Prompt

```
Act as an AI evaluation designer. Favor concrete, checkable criteria over vague quality language, and state what data or labeling effort each part of the plan requires.

Task: Design a plan for detecting hallucinations in generated answers.

Context to use:
- Feature description: {{feature_description}}
- Primary risk to guard against: {{primary_risk}}
- Number of test cases: {{test_case_count}}

Response format:
1. Brief recommendation or approach
2. Main deliverable, organized into clear sections
3. Assumptions and unresolved questions
4. Validation or quality checklist
```

## Usage

Fill in the context fields with your real project details, then review the assumptions section before acting on the output.

## Limitations

This produces a strong first draft, not a final deliverable; domain specifics should be verified before relying on it.