Cloud Agent Basics
Cloud Agents are remote workers with their own environment, branch and cost.
Use the right surface
After this you can pick Cloud Agents for the right job and define done.
Done means you can choose local Agent, worktree, Cloud Agent or cloud subagent deliberately.
Cloud agents help when work needs isolation, artifacts, handoff or parallel execution.
Use Cloud AgentsAgents that run in a Cursor-managed virtual machine, check out the repo, do the work and open a pull request, then shut down, with no load on your laptop. when a task can run in the background or needs a remote environment. Keep the boundary narrow.
Start small. Name the job, attach the context that proves the point and decide what evidence would make the output trustworthy.
Read the loop before touching the controls. The first beat frames the work, the second uses Cursor, the third checks the result and the fourth leaves a handoff someone else can inspect.
Interactive diagram. Tab through its regions; each focused region shows its detail in the panel below.
Run this loop in a real repo.
- Entry point
- Agents Window, web, integrations or Slack cloud-agent entry points
- Source
- Cloud AgentsAgents that run in a Cursor-managed virtual machine, check out the repo, do the work and open a pull request, then shut down, with no load on your laptop. docs
Use the source as the product reference.
Ask Cursor for an output you can inspect.
If the output cannot be checked, narrow the task before you continue.
A good run leaves a file, setting, screenshot, command result or written claim you can verify.
Takeaway. Done means you can choose local Agent, worktree, Cloud Agent or cloud subagent deliberately.
Self-check
QWhen should you reach for Cloud AgentsAgents that run in a Cursor-managed virtual machine, check out the repo, do the work and open a pull request, then shut down, with no load on your laptop.?
Run it
After this you can do the task with clear scope and one proof point.
Treat this as a short practice loop, not a product tour. The task should be small enough that you can inspect the result without trusting the summary.
- 1Classify whether the task needs local state or can run remotely: route it async when its output is artifact-verifiable, and stay foreground when the work is fuzzier and needs your decisions.
- 2Confirm repository access and branch strategy.
- 3Give setup, verification and PR expectations.
- 4Review the cloud output before merging locally.
The exercise is complete only when the proof matches the requested outcome. If the proof is weak, reduce the scope or fix the context instead of adding more instructions.
Keep the task small enough to review.
You can explain the lifecycle: a cloud agent runs in an isolated VM, opens a PR, then tears down.
Takeaway. Stop when you have proof: The cloud agent has repository and environment access..
Self-check
QWhich habit makes this workflow safe to use on a real project?
Check it
After this you can find the first failed check before changing tools.
Verification decides the next move.
Interactive diagram. Tab through its regions; each focused region shows its detail in the panel below.
Pick a row to see what to look for.
Use the first failure signal as the next prompt. Broad retries usually make the run noisier; a narrow retry gives Cursor a concrete repair target.
No proof means more checking.
Use a real repo or admin setting. Save the prompt, context and proof.
Takeaway. If it fails, find the first failed check.
Self-check
QThe workflow failed. What is the best first move?