AI code reviews by Vercel Agent now in Public Beta
Not a pilot. Vercel just shipped AI code reviews across all Pro and Enterprise teams—with validated patches generated in sandbox before they hit your PR.
Why it matters
Vercel Agent moves from general capability to deployed developer workflow. Code review automation at scale reduces friction in the inner loop for thousands of teams; signals how AI agents are penetrating core infrastructure rather than staying in assistants.
The key facts
7 to knowPublic beta launch for all Pro and Enterprise teams
Usage-based pricing with $100 Vercel Agent credit
Codebase-aware reviews across correctness, security, performance
Proposed patches validated in Vercel Sandboxes before PR submission
Support for Next.js, React, Nuxt, Svelte, TypeScript, Python, Go
In-dashboard observability: files read, review time, cost metrics
Configuration options: review all, public, or private repos; skip drafts
Go to the source
Vercel Blogvercel.com
Publisher excerpt: Vercel Agent can now conduct code reviews, with validated suggestions that address issues across correctness, security, and performance. These reviews are fully codebase-aware, looking beyond the diff to any relevant files. Proposed patches are generated and validated in Vercel Sandboxes before…