Continue is an automated code review platform that integrates AI agents directly into the software development lifecycle. By executing custom validation rules against pull request diffs, it provides immediate feedback through repository status checks, allowing teams to enforce quality, security, and documentation standards before manual review begins.
The system distinguishes itself through a file-based configuration model where validation logic is defined in version-controlled markdown files. These files act as system prompts that guide autonomous agents in evaluating code changes. This approach enables agentic task chaining, where specialized workflows—such as security scanning, test coverage validation, and UI rendering verification—are orchestrated to analyze code against project-specific criteria.
Beyond automated reviews, the platform includes a local-first execution engine that allows developers to run and refine these checks from the command line before committing changes. The system also incorporates a feedback loop that tracks user acceptance and rejection of suggestions, enabling the refinement of check logic over time to reduce noise and improve the accuracy of automated findings.
The project provides a command-line interface for managing these workflows and integrates with repository webhooks to trigger analysis automatically upon pull request submission.
