A deep link can shorten a screenshot workflow when it resolves to deterministic test state. It cannot create missing data or bypass legitimate access checks.
- 1Validated URL
- 2Seeded item
- 3Destination
- 4Screenshot
Work through the example
Prompt: Add a test route to this screen using a synthetic identifier and an explicit not-found state.
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: Add a test route to this screen using a synthetic identifier and an explicit not-found state. 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
Not every screen should expose a public route; keep test hooks appropriately scoped.
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.
Related reading
- Five checks for an AI-built SwiftUI app
Use persistence, search and accessible states to make “it works” a testable claim.
What to do next
Next: Keep design tokens in one file and tell the agent it's the only source of color