Cursor Launches Projects for Handling Long-Running, Large-Scale Coding Work

At a glance

Cursor has released Projects, a feature for handing off large tasks such as building new functions or entire apps. Projects keeps context over work that spans months and divides the work among multiple AI agents (AI programs that split up tasks themselves). It is currently in beta and is open to all users starting today.

Key points

1. 1

   Projects runs on Cursor's own cloud computers, so work continues even when the user closes their laptop.

2. 2

   An orchestrator agent (an AI that plans work and assigns it to other agents) does not write code itself. Instead, it brings finished results to the user for review.

3. 3

   Each project has shared files, so testing methods and work approaches discovered by one agent can be used by the agents that follow.

4. 4

   When a Slack channel is connected, the orchestrator agent automatically assigns work whenever a bug report comes in.

Why it matters

It shows that AI development tools are shifting toward multiple AIs working together over long periods to finish tasks.