← Back to catalog
LoopEngineering↓ 0

Adversarial Review Loop

Has a second, independent model review every change before merge, requiring two reviewers to agree.

Loops are usage routines — there is no install command. See how to run it just below.

This loop implements a change and then hands the diff to a reviewer from a different model family that argues against it on purpose.

The cycle is: build, cross-review with a different model, fix every blocking finding and review again, until the builder and the outside reviewer agree or the round cap is hit.

The idea is simple: an agent should not grade its own homework.

With two different models in play, neither can rubber-stamp itself, and code only lands when both genuinely sign off.

When to use

  • On security, auth, or data-sensitive changes.
  • When you want more rigor than a single review can give.
  • To stop the agent from approving its own work.

How to use

Run the loop asking it to build, review adversarially with a different model, fix the findings, and land it only when both sides report no blocking issues.