Code Review

Code Review is part of Vercel Agent. It provides Sandbox-validated suggestions on your pull requests as one capability within the broader Vercel Agent.

It generates patches and runs them in secure sandboxes with your real builds, tests, and linters to validate fixes before suggesting them. Only validated suggestions that pass these checks appear in your PR, allowing you to apply specific code changes with one click.

To enable code reviews for your repositories, navigate to the Agent of the dashboard.

1. Click Enable to turn on Vercel Agent.
2. Under Repositories, choose which repositories to review:
   • All repositories (default)
   • Public only
   • Private only
3. Under Review Draft PRs, select whether to:
   • Skip draft PRs (default)
   • Review draft PRs
4. Click Save to confirm your settings.

Once you've set up Code Review, it will automatically review pull requests in repositories connected to your Vercel projects.

Code Review runs automatically when:

• A pull request is created
• A batch of commits is pushed to an open PR
• A draft PR is created, if you've enabled draft reviews in your settings

When triggered, Code Review analyzes all human-readable files in your codebase, including:

• Source code files (JavaScript, TypeScript, Python, etc.)
• Test files
• Configuration files (package.json, YAML files, etc.)
• Documentation (markdown files, README files)
• Comments within code

The AI uses your entire codebase as context to understand how your changes fit into the larger system.

Code Review then generates patches, runs them in secure sandboxes, and executes your real builds, tests, and linters. Only validated suggestions that pass these checks appear in your PR.

Beyond automatic reviews, you can interact with Vercel Agent on demand by mentioning @vercel in any pull request comment. Vercel Agent will read your comment and either generate a suggested fix (which you can review and apply) or reply to your question in the same thread.

Comment @vercel followed by your request:

• @vercel run a review runs a full code review
• @vercel fix the type errors implements and commits a fix
• @vercel why is this failing? investigates the issue

Replies appear in the same comment thread.

Code Review automatically detects and applies coding guidelines from your repository. When guidelines are found, they're used during review to ensure feedback aligns with your project's conventions.

Code Review looks for these files in priority order (highest to lowest):

When multiple guideline files exist in the same directory, the highest-priority file is used.

• Hierarchical: Guidelines from parent directories are inherited. A CLAUDE.md at the root applies to all files, while a src/components/CLAUDE.md adds additional context for that directory.
• Scoped: Guidelines only affect files within their directory subtree. A guideline in src/ won't apply to files in lib/.
• Nested references: Guidelines can reference other files using @import "file.md" or relative markdown links. Referenced files are automatically included as context.
• Size limit: Guidelines are capped at 50 KB total.

Guidelines should focus on project-specific conventions that help the reviewer understand your codebase:

• Code style preferences not enforced by linters
• Architecture patterns and design decisions
• Common pitfalls specific to your project
• Testing requirements and patterns

Guidelines are treated as context, not instructions. The reviewer's core behavior (identifying bugs, security issues, and performance problems) takes precedence over any conflicting guideline content.

Check out Managing Reviews for details on how to customize which repositories get reviewed and monitor your review metrics and spending.

Code Review uses provider inference at the underlying token rate with no markup, plus the Vercel Token Rate of $0.25 per million tokens. The cost varies based on the complexity of the changes and the amount of code Vercel Agent analyzes.

See Vercel Agent pricing for complete rates and cost-tracking information.

Code Review never trains on customer code if your Vercel team's data preferences setting is "off" or you are on an Enterprise plan.