Blog
Research notes.
Writing about AI code review the way we build it: claims dated, sources linked, competitors compared on the record, publishing fewer claims and keeping them accurate.
Evidence has to link back
Public AI review examples should resolve to the source repository, the reviewed pull request state, and the check-run records behind the claim.
The gate is separate from the review
Postil keeps advisory findings and the branch-protection verdict separate: postil/review explains, while postil/gate carries the required merge decision.
Four AI code review benchmarks, four home-team winners
Greptile scored 82% on its own benchmark and 45% when a rival re-ran it. Why vendor code-review benchmarks can't be trusted at face value, and a five-point test for spotting a rigged one.
AI code review pricing in 2026: what a 20-developer team actually pays
Four vendors changed pricing models in ninety days. We run the same 20-developer team through seven tools, assumptions stated, arithmetic shown, every price sourced.
Best AI code review tools in 2026: an evidence-first comparison
CodeRabbit, Qodo, Macroscope, Greptile, Copilot, Bugbot, and Postil, compared on noise, merge gating, self-hosting, data handling, and a pricing landscape that changed four times in ninety days. Every claim sourced.
Self-hosted AI code review without the 500-seat enterprise gate
CodeRabbit gates self-hosting behind 500 seats; most rivals don't offer it at all. Run an Apache-2.0 reviewer locally with Ollama, with no seat fees or license cost.
Why GitHub Copilot can't block your merge (and how a real AI merge gate works)
Branch protection blocks on required status checks that conclude failure, not on review comments or neutral checks. Copilot posts a Comment, Claude Code review concludes neutral, and Macroscope defaults neutral unless configured to fail.
Where does your code actually go? A data-flow audit of AI code review tools
AI reviewers differ less on what they find than on where your code goes, who keeps it, and whether it trains a model. A class-by-class audit of retention, training, and inference location.
The silence rate: an ongoing AI code review metric
GitHub published a one-off Copilot silence figure. Postil makes silence rate an ongoing per-organization metric: how often the tool says nothing.