IntermediateMulti-Agent SystemsFree prompt

Run an Adversarial Reviewer Agent Over Another Agent's Output

Set up a critic agent that stress-tests a generator agent's work against explicit criteria before anything ships.

Catch errors, hallucinations, and missed requirements automatically by pairing a maker agent with a skeptical reviewer agent.

critic agentreviewverificationqualityadversarial

At a glance

Access

Free prompt

Open to copy — no account or payment needed.

Prompt objective

Catch errors, hallucinations, and missed requirements automatically by pairing a maker agent with a skeptical reviewer agent.

Real use case

A code-generation agent ships plausible-looking but subtly broken functions. The team adds a reviewer agent that must find issues or explicitly sign off before a PR is opened.

Customize these fields first

CODE / PLAN / COPY / ANALYSISPASTE THE OUTPUT FROM THE GENERATOR AGENTLIST CRITERIAPASTE RELEVANT CONTEXT / SPEC

Replace the placeholders with your own context before you run the prompt. That usually improves the first output more than adding more instructions later.

Prompt

Act as an adversarial reviewer agent. Your job is to find what is wrong with the artifact below before it is accepted — not to be polite.

Artifact type: [CODE / PLAN / COPY / ANALYSIS]
Artifact:
[PASTE THE OUTPUT FROM THE GENERATOR AGENT]
Acceptance criteria it must meet:
[LIST CRITERIA]
Context it must stay consistent with:
[PASTE RELEVANT CONTEXT / SPEC]

Review process:
1. Restate the acceptance criteria as a checklist.
2. Go criterion by criterion: PASS / FAIL / UNSURE, each with a one-line reason and a pointer to the exact part of the artifact.
3. Separately list: factual claims that are unverifiable, assumptions made silently, and edge cases not handled.
4. Assign a verdict: APPROVE, APPROVE WITH FIXES, or REJECT.
5. If not APPROVE, give the smallest set of concrete changes that would make it pass.

Do not rewrite the whole artifact. Be specific and cite evidence. If something is genuinely fine, say so plainly.

Open directly in an AI — the text is pre-filled:

How to use this prompt

  1. 1Replace the key placeholders first: CODE / PLAN / COPY / ANALYSIS, PASTE THE OUTPUT FROM THE GENERATOR AGENT, LIST CRITERIA, PASTE RELEVANT CONTEXT / SPEC.
  2. 2Replace any bracketed placeholders like [this] with your own context.
  3. 3Add extra background information when you want more tailored results.
  4. 4Combine multiple prompts in one conversation when you need a richer output.
  5. 5Save your best-performing prompts so they are easy to reuse later.

Next best step

Open the guide first, then branch only if you still need more.

A guide for technical builders choosing between prompts, coding workflows, and agent-based implementation.

If this prompt is close but not quite right, generate variants next. If the job is recurring, move into the course library after the guide.

Related prompts

View all

Explore other prompt categories

Move sideways into adjacent libraries when the current category is not the full answer.

Every prompt here is free. The course teaches the thinking behind them.

Copy as many prompts as you like. When you want to move from single prompts to a repeatable AI workflow, Learn AI in 30 Days walks through it, one day at a time.

Get the courseSee the 30-day curriculum first

Buy the course once ($15/$20 by length), or go all-access for $10/mo with a verifiable certificate.