# Reflection

> Have the model review its own output as a critic, then revise — catch the surface errors that a careful second read would find.

- **Category**: Agentic AI
- **Subcategory**: Verification & Reflection
- **Canonical URL**: https://designpattern.fyi/patterns/reflection/

---

## Description
**Intent**: Use a cheap extra model call to catch obvious errors before shipping the first-pass output.

**Context**: Your generation task (email draft, function, press release) usually has first-pass errors that a careful second read would catch: missing edge case, clumsy phrase, factual slip. Latency and cost allow at least one extra model call per output.

**Solution**: After producing an output, prompt the model (often as a critic persona) to find issues. Feed the original output + critique back into a revision step. Repeat until no new issues or max iterations hit.


## Use Cases
- One-shot generation underuses the model and a critique pass would catch errors.
- A critic prompt can identify issues meaningfully on the task's outputs.
- Stop conditions (no new issues, max iterations) can be defined.





## Trade-offs


### Advantages

- Catches surface errors cheaply — one extra call is usually enough.

- Pairs naturally with structured outputs for consistent critique format.




### Considerations & Drawbacks

- Diminishing returns after one or two passes; stop early.

- Self-reinforced confidence on wrong answers — the model can convince itself it's right.







---
**Reference**: [Original Source](https://www.agentpatternscatalog.org/patterns/reflection/)