2 min lesson
Practice long-running Cloud Agent work
Practice long-running Cloud Agent work on one real case. Check the result before moving on.
Step 1 of 2
Work through one real case until you can decide when long-running capability fits and scope a governed cloud task. Check whether the task has a definition of done the agent can verify without you. Confirm the team Long-Running Agents capability and cost warning were reviewed before launch. Make sure a human still owns review of the branch, PR and artifacts. Avoid using long-running capacity on short tasks where a normal run is faster. Keep the evidence with the result.
Set the boundary for long-running Cloud Agents
0:30 · narratedRead this demo as text
- The real control is called Long-Running Agents. It is team-scoped, and the product warns these runs can last many hours and cost hundreds of dollars.
- Then launch from cursor dot com slash agents with a repository, measurable done criteria, and a review owner. There is no user-facing Grind button in this build — long-running is a governed Cloud Agent workflow.
Practice next: Write measurable done criteria and a spend boundary before assigning a long-running cloud task.
Simulated Cursor 3.12 (macOS, light) — beta educational reconstruction, not the real product.
Learn more
Full explanation