Anthropic made Code Review, the multi-agent pull-request review system for Claude Code, generally available to Claude Team and Enterprise organizations on October 15, 2026, and paired the launch with a promotional offer of at least $10,000 in review credits for eligible Enterprise organizations.
What Changed for General Availability
Anthropic said it used the research preview to make Code Review faster, better at finding the bugs that matter, and easier to tune to each repository. According to the company, most reviews now finish about 3x faster than during the preview, with typical review time moving from roughly 20 minutes to 6–10 minutes. Anthropic said findings now state the problem, what triggers it, and the fix in a few sentences, and administrators can assign each repository a Quick, Standard, or Deep review level so routine codebases get a quick pass while the most critical ones get a deep review.
The company said preview users told it the system was catching real issues before a human reviewer looked at a pull request, but that they wanted reviews that were quieter, sized to each change, and faster. Anthropic also runs Code Review on its own pull requests, which it said showed where reviews slow its engineers down.
To enable Code Review, an administrator turns it on in Claude Code settings, installs the Claude GitHub App, and selects repositories. Once enabled, reviews run automatically on new pull requests, with no configuration required from developers.
How Code Reviews Work
According to Anthropic’s Code Review documentation, each review runs on Anthropic infrastructure in four stages: several agents examine the diff and surrounding code in parallel to find issues, a verification step checks candidate findings against the code and filters out false positives, the remaining findings are deduplicated and ranked by severity, and the results post to the pull request.
Each review leaves inline comments on the lines concerned, a summary, and a check run named Claude Code Review listing the findings. The check run never concludes as a failure, and a review never approves or blocks the pull request, so the merge decision stays with the team. When a review finds nothing, the check run reports that no issues were found, and Claude posts the same note on the pull request.
By default, Code Review focuses on correctness – bugs that would break production rather than formatting preferences or missing test coverage. Repositories can tune what gets flagged with REVIEW.md and CLAUDE.md guidance files, and the documentation states that REVIEW.md is read from the base or default branch, never from the pull request’s own changes. Code Review selects which Claude models reviews run on, admin settings offer no model choice, and a more thorough review level costs more.
Each repository can run reviews once when a pull request opens, after every push, or only on request, and anyone with write access can start one by commenting @claude review. Drafts and forks are excluded from automatic reviews. Reviews run in a managed environment with read-only repository access, work from reading the diff and surrounding code without building or running it, and do not run in self-hosted environments.
The service requires a Team or Enterprise plan and repositories hosted on GitHub, including GitHub Enterprise Server and GitHub Enterprise Cloud with data residency. It is unavailable to organizations with Zero Data Retention enabled or the HIPAA configuration applied, is not covered under Anthropic’s Business Associate Agreement, and is not yet available to organizations using customer-managed encryption keys. A Claude organization is required even when developers use Claude Code through Amazon Bedrock, Google Cloud’s Agent Platform, or Microsoft Foundry. The documentation cautions that Code Review uses AI and may miss bugs, security vulnerabilities, or other issues, and that a review with no findings does not mean code is error-free or secure.
Research Preview and Reported Internal Results
Anthropic introduced Code Review as a research preview for Team and Enterprise plans on March 9, 2026, describing a system that dispatches a team of agents on every pull request and that it ran on nearly every internal pull request. The company said code output per engineer had grown 200% over the prior year and that code review had become a bottleneck. Before Code Review, Anthropic reported, 16% of its pull requests received substantive review comments, compared with 54% after deployment.
On internal pull requests with more than 1,000 lines changed, Anthropic said 84% received findings averaging 7.5 issues, while pull requests under 50 lines dropped to 31% and averaged 0.5 issues, and engineers marked less than 1% of findings incorrect. The company also said early-access usage surfaced a latent type-mismatch bug in TrueNAS’s open-source middleware that had been silently wiping the ZFS encryption key cache on every sync, a pre-existing issue in adjacent code that a pull request happened to touch.
During the preview, reviews were billed on token usage and generally averaged $15–25 per review, scaling with pull-request size and complexity, and administrators had monthly organization caps, repository-level controls, and an analytics dashboard tracking reviewed pull requests, acceptance rate, and review costs.
Promotional Credits for Enterprise Organizations
Eligible paid Claude Enterprise organizations can claim between $10,000 and $50,000 in Code Review credits, with the amount set at the moment of the claim based on the organization’s active Claude Code seats, according to the Claude Help Center’s offer terms. An Owner or Primary Owner claims once from the Code Review section of organization settings; the claim cannot be undone or repeated, and it starts a 30-day period in which reviews are paid from the credits first, ending when the 30 days pass or the amount is used up, whichever comes first. The claim window opened October 15, 2026 and closes at 23:59 UTC on January 15, 2027, and the help center advises setting up Code Review on repositories before claiming, because the 30 days run from the claim whether or not reviews are running.
The offer excludes organizations billed through a reseller, organizations that have connected a GitHub Enterprise Server or data-residency instance, trials and lapsed subscriptions, Team, Pro, Max, and Free plans, organizations that claimed Anthropic’s earlier free Code Review offer, and organizations that cannot use Code Review, such as those with zero data retention. Each finished review’s actual cost at list prices is drawn from the credits first; reviews that fail or stop because of a problem on Anthropic’s side are not billed and do not count, while reviews stopped by a new push or by the organization count for what they cost until they stopped. While credits remain, reviews can run even at a $0 spend limit. The credits do not cover the self-hosted GitHub Action, Code Review on GitHub Enterprise Server, the /code-review or /ultrareview commands, or any other Claude usage. Organizations that do not claim by the January 15, 2027 deadline receive no credits, and reviews are billed as usual.
Credit: Source link
