CheckedMake content

A practical method for your work

Critic Loop Pattern

Separate creation from critique so the model stops polishing its first draft blindly.

Start with this template →View original source ↗
Original sourceAnthropic: chain complex promptsChecked 2026-07-07
Use this whenWriting · Product copy · Design QA
You will getA reusable way to start the work

Core idea

Instead of asking for a perfect answer once, make the model draft, critique against criteria, then revise only the highest-impact issues.

Why it works

Chaining makes each step simpler. Critique before revision also exposes tradeoffs that a one-shot prompt often hides.

Weak

Make this better.

Better

Step 1: draft. Step 2: critique using clarity, evidence, specificity. Step 3: revise only the top 3 issues. Step 4: list what you intentionally did not change.

Customize it

Draft targetCritique rubricRevision limitNon-change note

Working template

Goal: [what I am trying to accomplish] Context: [background, audience, constraints] Use this pattern: Critic Loop Pattern Variables: Draft target, Critique rubric, Revision limit, Non-change note Return: [exact output format] Before finalizing: state limits and one improvement

Operating recipe

  1. Start with the weak version so you know what problem you are fixing.
  2. Add the missing variables instead of making the instruction longer randomly.
  3. Ask the model to follow the output contract exactly once.
  4. Review the first answer against the checklist below.
  5. Save the improved version as your reusable pattern.

Quality checklist

  • Did I give the model the real goal, not just the task?
  • Did I define the output shape before asking for the answer?
  • Did I include examples, constraints, or a quality bar?
  • Did I ask for limits, uncertainty, or failure cases?
  • Can I reuse this as a pattern next time?

Model notes

Claude

Strong for long context, critique, and structured writing. Give it clear sections and examples.

ChatGPT

Strong for fast iteration and everyday templates. Be explicit about output format and assumptions.

Limits

For factual work, critique is not verification. You still need sources or tools.

Read next

Context Pack PatternGive AI the work environment before asking for serious output.Role + Rubric PatternGet better critique by defining the judge and the scoring criteria.Ask Before Answer PatternUse clarification only when missing context changes the answer.
Free downloads

Turn this into a reusable workflow.

Get the Prompt Debugging Checklist and Solo Builder AI Setup Pack as language-specific .md files.

Open free downloadsBack to library →