Guide
How to Tell an AI Coding Agent What Not to Touch
Tell an AI coding agent what not to touch by naming protected files, generated code, public contracts, data migrations and style-only areas before it edits. Non-goals are not negative detail. They are the guardrails that keep the diff reviewable.
What is the working pattern for AI coding agent non-goals?
- Move
- Start with a bounded task
- Use this when
- Developers and team leads trying to reduce agent overreach.
- Proof to save
- Issue, files, checks and owner are named
- Move
- Give the agent context
- Use this when
- The repo has patterns the agent must follow
- Proof to save
- Prompt cites files, errors and constraints
- Move
- Review the diff
- Use this when
- The task changes production code
- Proof to save
- Changed files, test output and risks are visible
| Move | Use this when | Proof to save |
|---|---|---|
| Start with a bounded task | Developers and team leads trying to reduce agent overreach. | Issue, files, checks and owner are named |
| Give the agent context | The repo has patterns the agent must follow | Prompt cites files, errors and constraints |
| Review the diff | The task changes production code | Changed files, test output and risks are visible |
A good AI coding workflow is specific enough to review and small enough to recover.
Interactive diagram. Use Tab to move through hotspots or use the step controls when shown.
Use this loop when the change is larger than autocomplete and smaller than a full project rewrite.
Interactive diagram. Use Tab to move through hotspots or use the step controls when shown.
Open each stage to see what a reviewer should be able to inspect.
The public guide connects to lessons, recall and readiness checks inside Learn Cursor.
How should a team run AI coding agent non-goals?
- 1Pick one real backlog item with a clear owner and expected result.
- 2Add only the context the agent needs: files, failing output, constraints and done state.
- 3Ask for a plan before code when the task touches more than one file.
- 4Run checks that match the risk: unit test, typecheck, visual pass or review checklist.
- 5Capture the prompt, diff, result and reviewer note so the workflow can be repeated.
Task, context, constraints, done state and checks.
Open the diff, read changed files and rerun the check yourself.
The guide maps non-goals to prompt fields, rules and review checks.
What should you keep after the run?
- The prompt or plan that shaped the work.
- The files changed and the reason each file changed.
- The command, screenshot or review note that proved the result.
- The rule, checklist or template you would reuse next time.
Frequently asked questions
Who is How to Tell an AI Coding Agent What Not to Touch for?
Developers and team leads trying to reduce agent overreach.
What makes this page credible?
The guide maps non-goals to prompt fields, rules and review checks.
What should I do next?
Start with one real repo task, capture the prompt and review the result before scaling the workflow.
Sources & last verified
- Cursor agent best practices
- Cursor Learn: working with agents
- Cursor Learn: context
- Cursor docs: prompting agents
Cursor ships frequently. Facts verified against primary sources on June 23, 2026.