Expanding our long-running agents research preview

Summary

Cursor has expanded its long-running agents research preview to all Ultra, Teams, and Enterprise users. The preview targets autonomous work on ambitious projects, using a custom harness designed to address frontier models’ failures on long-horizon tasks. Long-running agents propose a plan for approval before execution and use multiple agents to check work and maintain follow-through. Reported examples include runtimes of 36, 30, and 25 hours, while initial results showed substantially larger PRs with merge rates comparable to other agents. Internal examples include a Rust migration and custom kernels for video rendering, a 10,000-line network-policy PR, and secure sudo prompting for Cursor CLI; the company says agents can now deliver working solutions after hours or days, though safer production deployment and collaboration across agents remain active areas.

Takeaways

1. 1

   The research preview is available to all Ultra, Teams, and Enterprise users at cursor.com/agents.

2. 2

   Example long-running tasks included building a chat platform in 36 hours, implementing a mobile app in 30 hours, and refactoring authentication and RBAC in 25 hours.

3. 3

   Internal uses included migrating a video renderer to Rust with custom kernels, creating a 10,000-line network-policy pull request, and implementing secure sudo password prompting in Cursor CLI.