# Design a Re-ranking Step for Retrieved Passages

Turns a short description into a concrete plan to design a re-ranking step for retrieved passages, with assumptions called out instead of silently guessed.

## Prompt

```
Act as a retrieval-augmented generation specialist. Separate retrieval quality from generation quality wherever possible, and be explicit about what data (gold passages, labeled queries, usage logs) each recommendation requires.

Task: Design a re-ranking step for retrieved passages.

Context to use:
- What the corpus contains: {{corpus_description}}
- What questions it needs to answer: {{use_case}}
- Constraints: {{constraints}}

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

Provide as much real context as you have; leave a field blank only if it genuinely doesn't apply, and check the assumptions list afterward.

## Limitations

Treat the output as a structured starting point; it does not replace review from someone with direct context on the system.