FAQs
General Questions
How accurate is CodeRabbit?
CodeRabbit demonstrates high accuracy in code reviews based on early adoption results. While 100% accuracy isn't guaranteed due to AI's evolving nature, our technology continuously improves through:
- Regular model updates
- Enhanced pattern recognition
- Growing language support
- Refined code analysis
Language Support
CodeRabbit works with all programming languages, with varying proficiency based on:
- Language popularity
- Available training data
- Community usage patterns
Data Security
- Code Storage
- Training Data
- No persistent code storage
- Temporary cloning during review only
- Complete data isolation
- Immediate disposal post-review
- Uses only public datasets
- No proprietary code usage
- Private repositories excluded
Organization Management
Switch between organizations easily:
- Click organization name (top-left corner)
- Select desired organization
- Access organization-specific settings
Comparison with Other Tools
Code reviews remain essential, whether the code is written by a human or a bot. This is mainly because the perspective of the reviewer differs from that of the code generator, whether human or machine. This distinction is precisely why human peer reviews have been effective for so long. While AI-powered code-generation tools like GitHub Copilot hold immense potential, it's important to recognize that these generators are still in their early stages and may not be equipped to auto-generate meaningful code for moderately complex applications.
vs AI Code Generators
- Provides review perspective different from code generation
- Complements tools like GitHub Copilot
- Focuses on code quality and best practices
vs Traditional Review Tools
- Context-aware feedback
- Actionable suggestions
- Direct commit capabilities
- AI-powered intent understanding
Usage and Configuration
When Does CodeRabbit Review PRs?
- ✅ New PRs: Automatic review when created
- ✅ New Commits: Automatic review when pushed to any PR
- ⚡ Older PRs: Use
@coderabbitai review
to trigger manually
Customization Options
- Language Settings: Configure review language in repository settings
- Review Rules: Customize via Review Instructions
- Branch Selection: Default branch reviews enabled by default (configurable)