The AI-Generated Code Review & Test-Coverage Gate is an adversarial reviewer for code written or heavily assisted by an AI agent. You give it a pull request, a diff, or the changed files plus their tests, and it reviews the change the way a skeptical senior engineer would. It runs five passes — coverage, silent changes, edge cases, over-confidence, and test quality — and returns a PASS / REVISE / BLOCK verdict naming the untested branches, the behavior that quietly changed, and the items that must be fixed before merge.
It exists because AI code fails differently from human code: it is fluent and plausible, so reviewers trust it more than they should, and the gaps hide in branches nobody ran and assertions nobody wrote. This gate forces the boring, specific checks that catch silent regressions and happy-path-only tests. It does not run or rewrite your code — it reasons over what you provide and hands the decision back to you.