Blog
Engineering insights, product updates, and lessons learned.
Fable 5 Rewrites 50M Lines in a Day. Who Reviews It?
Stripe's AI migration exposes a critical truth: AI writes code faster than humans can safely review it. Here's what that means for your team.
4 Git Hosts, 1 Review Blind Spot They All Share
GitHub, GitLab, Bitbucket, or Gitea? See what really separates them—and why all four miss the same critical review blind spot.
Opus 4.8 Got More Honest. Your Reviewer Should Too.
Discover how Claude Opus 4.8's self-honesty improvements transform AI code review when paired with full-codebase context.
Change One Util. Break 23 Packages. Diff Hides It.
Discover how monorepo blast radius silently breaks production apps—and how codebase-aware code review catches what diffs miss.
Engineers Pick the Smaller PR. AI Ones Wait 5x Longer.
Engineers avoid AI-generated PRs 5x longer than human ones. Here's why context gaps are killing your cycle time—and how to fix it.
What Adding GitLab Support Taught Us About Code Review
Shipping GitLab support revealed surprising complexity: SHA-anchored comments, discussion-based reviews, and unexpected demand for self-hosted, air-gapped deployments.
Your Team's Rules Live in Three Heads. AI Has None.
Catch costly PR mistakes before they happen. Learn how codified team standards in AI code review cut onboarding time and hidden productivity losses.
AI Made Your PRs 33% Bigger. Reviews Got Worse.
AI made PRs 33% bigger, dropping bug detection from 87% to 28%. Here's how to fix code reviews before they break your production deploys.
Your Team Is Ignoring AI Review Comments
AI code review tools hallucinate 29-45% of the time. Learn why most teams ignore them and how calibrated severity levels fix the "cry wolf" problem.
Every /clear Costs You Tokens. Stop Re-Exploring.
Claude Code teams save 40-60% on redundant file reads by using Octopus Review's semantic indexing to skip expensive codebase re-discovery after /clear