Anthropic's Code Review leaves research preview with three depth levels

Anthropic says Code Review is out of research preview for Claude Team and Enterprise organizations. It reports that most reviews now finish about 3x faster, from roughly 20 minutes during the preview to 6 to 10 minutes. Admins can set each repository to Quick, Standard (the default) or Deep review. Once an admin enables it in Claude Code settings and installs the GitHub App, reviews run automatically on new pull requests. Anthropic also says eligible Enterprise organizations can claim at least $10,000 in Code Review credits by January 15, 2027, and that credits expire 30 days after claiming.

The post gives no accuracy figures, false-positive rates or per-review prices. The speedup and its statement that it finds more of the bugs that matter are Anthropic's own statements about its own product, with no method or data attached.

Why it matters: The depth setting turns review cost into a per-repository decision. A team that already routes agent-written pull requests through review can now spend more on the repositories it cannot afford to get wrong and less on the rest. Without published detection numbers, run it against your own history of escaped bugs before trusting a tier.