Anthropic announced on October 15, 2026 that Code Review, the Claude Code feature that automatically reviews pull requests to catch bugs before human reviewers look at them, is “out of research preview and available to Claude Team and Enterprise organizations.”
Admins enable it in Claude Code settings, install the GitHub App and choose repositories; developers then get automatic reviews on new pull requests with no further configuration. Admins can set a review depth per repository: Quick, Standard (the default) or Deep.
Anthropic says “Most reviews now finish about 3x faster (~20 minutes down to 6-10 minutes)” compared with the preview, and that the reviewer finds more bugs that matter with more concise findings. As a launch promotion, eligible Enterprise organizations can claim at least $10,000 in Code Review credits by January 15, 2027; credits expire 30 days after they are claimed.
Why it matters: automated review is one of the clearest places where agent output meets an existing quality gate, and moving it to GA with configurable depth signals that labs now sell AI review as a standing part of the merge pipeline rather than an experiment.
What it does not show: the post gives no per-review price, no precision or recall numbers, and no comparison with human reviewers. The speed figures are Anthropic’s own, and the quality claim is stated without data.