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.
Choosing a code review model
A one-point detection gap between GPT-5.6 Luna and GLM-5.2 hides larger differences in gate decisions, output failures, cost and run-to-run variance. What each benchmark number measures, and which one to weight least.
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.
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.