Adversarial review (cross-model review)
Asking a second AI model, or a fresh agent, to find what is wrong with a change before a person reviews it, instead of asking the author to check itself.
A model reviewing its own work in the same context tends to agree with itself. A reviewer with a different model, a clean context and an explicit brief to break the change catches more: missed edge cases, security gaps, drift from the project’s conventions. It works like an LLM judge aimed at code. It filters work before a person looks at it; it does not replace that person, and its findings still need checking because reviewers invent problems too.
Related terms
- LLM as judge: Using a model with a rubric to grade another model’s output.
- Coding agent: An agent that reads a repository, edits files, runs commands and tests, and opens pull requests.
- Evals: A repeatable test set that scores an AI feature, so changes can be measured instead of guessed.
- Human in the loop: A person approves, edits or rejects the agent’s action before it takes effect.
