Automated testing

Cursor has launched Cursor 2.0 featuring a multi-agent interface and its new Composer coding model. Composer, designed for rapid, agent-driven coding, reportedly operates up to four times faster than comparable models. The platform utilizes codebase-wide semantic search for accurate code suggestions. Cursor 2.0’s agent-centric workflow allows parallel execution of AI agents and supports an “ensemble” approach using multiple models for enhanced code quality. The update also includes features for streamlined code review and automated testing via a native browser tool, aiming to improve developer efficiency.