AI reviewer handled 110 PRs with 22-min median first comment at healthcare data firm
alex_verem · x · 2026-11-17
Tech leads at a PE-backed US healthcare data company were reviewing every pull request by hand; a team built an AI reviewer to take the first pass. By November it had reviewed 110 pull requests on their main product, with a 22-minute median wait for its first comment, and the team had fixed or closed more than half of its comments—so leads now get a first review ready when they open a PR and can focus on design and risk.
Getting there took more than flipping a switch: the customer required no delivery holdups, source code and secrets staying inside their perimeter, and predictable AI spend. So the reviewer can suggest but never block a merge, failures don't stop delivery, and it posts nothing on new repos until the team opts in.
More from coding & agent
- LangChain explains Agent vs. Deep Agent vs. Managed Deep Agent — LangChain · 2026-11-18
- Open-Source Robot Lamp Preps Skill Store: Install Physical Skills Like Apps — dee_hw · 2026-11-17
- ArisGlobal cut Bedrock inference cost bloat by caching shared prompt prefixes first — AWS ML Blog · 2026-11-17
- Turning a Support Inbox Into an MCP Server So Claude Code Handles It Directly — Crazy-Mountain6125 · 2026-11-17
- Humans& Launches 744B-Param Collaborator Model Ampersand on Vercel AI Gateway — ericzelikman · 2026-11-17
- Programming tools are shifting from file-centric IDEs to spec- and voice-driven agent workflows — bendee983 · 2026-11-17