Lesson 15 of 2116
Self-Critique Prompts: AI as Its Own Reviewer
Asking the model to critique and revise its own output is one of the cheapest quality boosts in prompt engineering. Master the patterns and their limits.
Lesson map
What this lesson covers
Learning path
The main moves in order
- 1Why self-critique works
- 2self-critique
- 3self-consistency
- 4reflection prompting
Concept cluster
Terms to connect while reading
Section 1
Why self-critique works
Generating text and evaluating text are slightly different cognitive operations. When a model is asked to critique an answer (especially without being told it's its own answer), it can spot flaws it missed when generating. This is the foundation behind Constitutional AI and many production pipelines.
Single-prompt self-critique
A single-prompt self-critique — all three stages in one call.
Task: Write a short explanation of why inflation happens, aimed at a 9th-grade audience.
Step 1: Draft your answer in <draft> tags.
Step 2: In <critique> tags, evaluate the draft:
- Is it accurate? Flag any oversimplifications.
- Is it level-appropriate? Point out any jargon.
- Is it complete? Name one thing missing.
Step 3: In <final> tags, rewrite the draft fixing the issues raised.
Only the <final> block will be shown to the student.This works because Claude will genuinely evaluate its own draft when asked. The <final> block is almost always better than the <draft>, often markedly so. The cost is extra tokens (1.5-2x) for significantly higher quality.
Separate-turn self-critique
The AI has no idea it's critiquing itself. This sometimes produces harsher, better critique than self-aware critique.
TURN 1:
Write a resignation letter. (no mention of critique)
TURN 2:
You are a no-nonsense HR consultant. The letter below was written by an employee. Identify the five biggest problems and rewrite it.
<letter>
{RESPONSE_FROM_TURN_1}
</letter>Self-consistency via sampling
A related technique: generate N answers at temperature > 0, then use the model (or majority vote) to pick the best. On reasoning tasks, 5 samples with majority vote on the final answer dramatically outperforms a single sample.
Self-consistency with majority voting.
# Pseudocode
answers = []
for i in range(5):
answer = model.complete(prompt, temperature=0.7)
answers.append(extract_final_answer(answer))
best = majority_vote(answers) # or ask a judge modelLimits of self-critique
- If the model is wrong in a systematic way, its critique will be wrong too.
- Self-critique can INCREASE verbosity without improving substance — watch for that.
- On factual accuracy, self-critique helps less than retrieval. The model can't fact-check what it doesn't know.
- Sycophancy: models sometimes praise their own drafts. Neutral critique framings help.
Key terms in this lesson
End-of-lesson quiz
Check what stuck
15 questions · Score saves to your progress.
Tutor
Curious about “Self-Critique Prompts: AI as Its Own Reviewer”?
Ask anything about this lesson. I’ll answer using just what you’re reading — short, friendly, grounded.
Progress saved locally in this browser. Sign in to sync across devices.
Related lessons
Keep going
Creators · 38 min
Anthropic's Prompt Engineering Patterns
Anthropic publishes detailed prompt engineering guidance. Master the core patterns — Be Direct, Let Claude Think, and Chain Complex Prompts — to write production-grade prompts.
Creators · 36 min
Prefill Attacks and Defenses
An attacker can inject text that looks like part of the AI's own response, tricking it into behaviors it would otherwise refuse. Understand the attack vector and how to defend.
Creators · 40 min
Multi-Turn Reasoning: Agents That Think Across Steps
Some problems need more than one prompt. Learn how to design multi-turn reasoning flows — reflection, critique, retry — that give you AI which actually solves hard problems.