Planning before a multi-file edit exposes dependencies and unresolved choices. A plan is valuable when it narrows the next action, not when it repeats the prompt in more words.

Inspect files → Identify dependencies → Agree criteria → Edit one slice
  1. 1Inspect files
  2. 2Identify dependencies
  3. 3Agree criteria
  4. 4Edit one slice

Work through the example

Prompt: Before editing, list the files involved, the behavior to preserve and the checks that determine completion.

One practical example

Use the prompt above on one small, named part of your app. Before accepting an edit, ask the agent to point to the source or configuration that supports its answer. If it cannot locate that context, resolve the missing input before expanding the task.

In the diagram, each arrow represents a handoff you can inspect. Keep the intermediate result rather than jumping directly to the final claim. For example, a reported finding should retain its location, and an executed check should retain its outcome. This gives the next attempt a concrete starting point and makes a misleading completion message easier to challenge.

Apply it to your project

Prompt: Before editing, list the files involved, the behavior to preserve and the checks that determine completion. Then compare the resulting diff with the original request. If it changed a neighboring concern, ask why that change was necessary. Save the result only after the relevant check has run, and record any part that remains unverified.

Evidence and limits

Planning does not itself validate implementation or guarantee lower cost.

This is an educational guide. Its presence in the series does not certify a completed client-specific lab. The series evidence record separates executed checks from exercises and blocked environments.

Inspect the source used in this lesson.

What to do next

Next: Ask the agent to search local Apple references before the web