Features
Human-in-the-loop approval – review, edit, and approve AI comments before publishing
Multi-model AI – runs Claude, Gemini, and GPT in parallel, smart-merges findings
Deep Review (Agent Mode) – AI explores full codebase, runs linter, checks tests
Full project context – examines related files, imports, dependencies
Jira integration – reads ticket context, verifies acceptance criteria against diff
Security scanning – 20+ built-in rules + AI security pass (SQLi, XSS, secrets)
Confidence scoring – each finding rated 0-100%, filter low-confidence noise
Code quality scores – 6-category assessment: design, clarity, error handling, complexity, testability, production readiness
Review Profiles – named configurations for models, API keys, prompts, rules
.gitautoreview.md config file – team-wide rules versioned in git
BYOK (Bring Your Own Key) – code goes directly to your AI provider, zero storage
VS Code extension – native editor integration
GitHub (Cloud & Enterprise) support
GitLab (Cloud & Self-Managed) support
Bitbucket (Cloud, Server & Data Center) support
Cross-repo review (v2.4) detects breaking changes across repositories
Mined rules auto-learn from codebase patterns and PR history
Skill governance for managing AI-assisted development
Agentic PR code review with full codebase context
Self-learning rules system that evolves with your codebase
Real-time IDE code review (VSCode, JetBrains)
Pre-PR review skills (shift-left)
Context engine: codebase, PR history, business requirements
Risk dashboard for tracking findings and resolution rates
Audit trail and compliance logging
SSO/SAML and audit logs (Enterprise)
On-premises and air-gapped deployment (Enterprise)
BYOK (bring your own LLM keys)
CLI tool for full codebase intelligence
Gerrit support (Enterprise)
