Make One Small Change and Review the Diff
The first edit should be boring, reversible and easy to inspect.
Use the right surface
After this you can pick Agent or inline edit for the right job and define done.
Done means one small edit lands with a diff you understand and can undo.

Fast edits still need a boundary: accept the useful completion, then review the patch.
Use Agent or inline edit when you have one low-risk change with a clear expected result. 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
- Inline edit for selected code or Agent for a small multi-file task
- Source
- Agent overview, inline edit docs and agent best practices
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 one small edit lands with a diff you understand and can undo.
Self-check
QWhen should you reach for Agent or inline edit?
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.
- 1State the change, the files in scope and the behavior that must not change.
- 2Choose inline edit for one selected region or Agent if the task crosses files.
- 3Inspect the diff instead of trusting the summary.
- 4Run the smallest relevant check and keep the evidence with your notes.
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.
The diff matches the requested behavior and style.
Takeaway. Stop when you have proof: Only expected files changed..
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?