ModelRefs / Reflection — Prompt Pattern
Reflection — Prompt Pattern
Have the model critique and revise its own answer before returning it. Two-pass prompt: (1) draft answer, (2) critique against criteria, (3) revise.
Overview
Two-pass prompt: (1) draft answer, (2) critique against criteria, (3) revise. Cheaper than self-consistency on long-form tasks.
When to use it: Long-form output where quality matters more than latency.
Pattern details
| Pattern class | reasoning |
|---|---|
| Difficulty | intermediate |
| Also known as | self-critique, self-refine |
| Last reviewed | 2026-06-07 |
Known failure modes
- Loop converges to identical text — Critique surfaces nothing new. Mitigation: Inject explicit rubric and forbid generic feedback.
When not to use it
- Iterating > 3 rounds (diminishing returns).
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Reflection — Prompt Pattern.
Frequently asked questions
When should I use the Reflection prompt pattern?
Long-form output where quality matters more than latency.
What are common failure modes of Reflection?
Loop converges to identical text
Does Reflection work across models?
Yes when the anatomy is preserved — see model compatibility matrix on the pattern page.