AI code review applies large language models to analyze pull requests and code changes, automatically surfacing bugs, security vulnerabilities, style violations, and logic errors before merge. These platforms integrate directly into Git workflows, commenting inline on diffs and suggesting fixes or improvements that developers can accept with a click. Core capabilities span static analysis, security scanning, test coverage assessment, and best-practice enforcement. The category has rapidly evolved from rule-based linters and pattern matchers into context-aware LLM reviewers that understand business logic, API contracts, and cross-file dependencies. Modern systems learn repository conventions, prioritize high-signal findings to reduce noise, and increasingly function as collaborative teammates rather than gate-keeping checkers, shifting code quality left while preserving developer velocity.