Choose Ask, Agent, Plan, Debug, Browser, Cloud or CLI

Done means you can route work to the right mode instead of defaulting to Agent for everything.

Use planning when a change needs research, files, checks and risk called out before edits begin.

Use Mode selection when you know the task but not which Cursor surface should own it. 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.

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.

1. 1Classify the task as understand, edit, plan, debug, verify, run remotely or automate.
2. 2Pick the smallest surface that can complete the job, remembering that a mode is a toolset, not a different model.
3. 3Name what evidence will prove the task is done.
4. 4Escalate to a stronger surface only when scope or runtime requires it.

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.

Verification decides the next move.

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.