Critique Revision Engine
Use this to build a prompt that critiques an output before revising it.
Use case: A writer or analyst can improve a draft through explicit criteria rather than accepting the first generated answer.
Best tools
- Claude — Performs nuanced long-form critique and revision while preserving intent.
- ChatGPT — Supports rubric-based iteration and transparent change summaries.
Fill in your details
Answer the questions below. Your answers are placed into the prompt automatically.
Your filled prompt (preview)
You are my Critique→Revision Engine builder. Build a prompt that critiques an output against criteria before revising it.
========================================
PERSONAL CONTEXT (filled by me)
========================================
Type of output to improve: [OUTPUT_TYPE]
Rubric or quality criteria: [RUBRIC]
Sample output to critique: [SAMPLE_OUTPUT]
What must stay unchanged: [MUST_PRESERVE]
Goal of the revision: [REVISION_GOAL]
Audience for the revised output: [AUDIENCE]
How strict the critique should be: [STRICTNESS]
Critique-revise rounds needed: [ROUNDS]
If any field is blank or still shows brackets, list the gap, continue with labelled assumptions, and never invent unverified facts, numbers, citations, or quotes.
========================================
WORKFLOW YOU MUST FOLLOW
========================================
STEP 1 — Critique
Score [SAMPLE_OUTPUT] against [RUBRIC] at [STRICTNESS]; cite concrete issues.
STEP 2 — Preserve
List what must not change from [MUST_PRESERVE].
STEP 3 — Revise
Produce a revised version aimed at [REVISION_GOAL] for [AUDIENCE].
STEP 4 — Engine prompt
Package the critique-then-revise workflow into a reusable prompt for [ROUNDS] rounds.
========================================
OUTPUT FORMAT
========================================
Use these exact headings:
A. Critique scorecard
B. Issue list with evidence
C. Preservation constraints
D. Revised output
E. Change log
F. Reusable engine prompt
G. Stop conditions
H. Residual risks
Rules: critique before rewrite; no silent meaning changes; honour [MUST_PRESERVE].
You are my Critique→Revision Engine builder. Build a prompt that critiques an output against criteria before revising it. ======================================== PERSONAL CONTEXT (filled by me) ======================================== Type of output to improve: [OUTPUT_TYPE] Rubric or quality criteria: [RUBRIC] Sample output to critique: [SAMPLE_OUTPUT] What must stay unchanged: [MUST_PRESERVE] Goal of the revision: [REVISION_GOAL] Audience for the revised output: [AUDIENCE] How strict the critique should be: [STRICTNESS] Critique-revise rounds needed: [ROUNDS] If any field is blank or still shows brackets, list the gap, continue with labelled assumptions, and never invent unverified facts, numbers, citations, or quotes. ======================================== WORKFLOW YOU MUST FOLLOW ======================================== STEP 1 — Critique Score [SAMPLE_OUTPUT] against [RUBRIC] at [STRICTNESS]; cite concrete issues. STEP 2 — Preserve List what must not change from [MUST_PRESERVE]. STEP 3 — Revise Produce a revised version aimed at [REVISION_GOAL] for [AUDIENCE]. STEP 4 — Engine prompt Package the critique-then-revise workflow into a reusable prompt for [ROUNDS] rounds. ======================================== OUTPUT FORMAT ======================================== Use these exact headings: A. Critique scorecard B. Issue list with evidence C. Preservation constraints D. Revised output E. Change log F. Reusable engine prompt G. Stop conditions H. Residual risks Rules: critique before rewrite; no silent meaning changes; honour [MUST_PRESERVE].
Pro tip: Make the critique cite exact draft locations so revision does not become a total rewrite.
Expected output: A reusable critique-then-revise prompt with stop conditions and change tracking.