Skip to content

Claude Code Review leaves preview, now reviews PRs 3x faster

Team and Enterprise admins can enable automated pull request reviews with Quick, Standard or Deep levels per repo, and Enterprise customers can claim $10,000 in credits before 15 January 2027.

Source: Anthropic

Anthropic moved Code Review for Claude Code out of research preview on 15 October, making it generally available for Claude Team and Enterprise plans. Reviews now finish in roughly 6 to 10 minutes, about three times faster than the 20 minutes typical during preview.

An admin enables it from Claude Code settings, installs the GitHub App, and picks which repositories get automated reviews on new pull requests. Each repo can be set to Quick, Standard, or Deep, and Anthropic says the findings now state the problem, what triggers it and the fix in a few sentences rather than a longer writeup. Eligible Claude Enterprise organisations can claim at least $10,000 in Code Review credits, but only if they do it by 15 January 2027; the credits themselves expire 30 days after being claimed.

Claude Code settings → Code Review → install GitHub App → select repos → choose Quick / Standard / Deep

Why it matters: this sits alongside GitHub’s own Copilot code review and AI Scan, so teams already paying for Claude Team or Enterprise get a third automated reviewer with no extra procurement. The per-repo depth setting matters more than it looks: Quick for high-volume repos, Deep for anything touching payments or auth.

The caveat: it is Team and Enterprise only. Pro and free users don’t get it.

Share

Related reading

ML for Web Devs

Tokens, context windows, and why your bill is what it is

The unit of billing for language models is not the request or the word. Once you understand tokens and how a context window fills up, the invoice stops being a surprise.

ML for Web Devs

RAG is just search with extra steps

Retrieval-augmented generation gets written up like an architecture. It is a search query, a string concatenation and one API call, and the search query is the part that decides whether it works.

ML for Web Devs

A prompt is a spec, so write it like one

Prompt engineering has very little to do with magic words. It is the same skill as writing a clear ticket for a capable contractor who will not ask you any questions.

More from The Wire

All briefs

GitHub Copilot retires six AI models today

Gemini 3.7 Flash, GPT-5.5, GPT-5.4, GPT-5.4 mini, GPT-5 mini and Grok 4.5 stop working across Copilot Chat, inline edits, agent mode and completions from today.

via GitHub