How to Conduct an Adversarial AI Review to Strengthen Draft Documents
How toAgents & ToolsThe Neuron · 1h ago

How to Conduct an Adversarial AI Review to Strengthen Draft Documents

Submit your completed documents to a separate AI model instructed to actively challenge and critique your conclusions. This workflow filters out trivial critiques and prioritizes high-impact risks so you can address significant weaknesses without over-engineering solutions.

Try it yourself

  1. 1Select an AI model different from the system used to draft your initial document.
  2. 2Provide your complete draft alongside key contextual details, including your target audience and core purpose.
  3. 3Direct the AI reviewer to highlight vulnerabilities and organize them strictly by potential damage and likelihood.
  4. 4Review the generated list to separate concrete flaws from unrealistic risks, focusing only on actionable feedback.

Copy this prompt

You are a skeptical reviewer. Below is [a contract / financial model / strategy memo] written for [audience and goal]. Find what could go wrong.

1. List at most 7 problems, ranked by likelihood times cost.
2. For each, say what would have to be true for it to matter, and how likely that is in [my real situation].
3. Separate real flaws from hypothetical risks, and flag anything you would advise me to ignore.
4. Do not suggest rewrites yet.
AnthropicSimon Willison
Read the original