Prompting

Build and Verify the First Useful Slice

Use the course brief and prompt to build, test, and preserve one narrow working slice.

Build stage · Module 8 of 15

Outcome for this lesson

Use the brief and prompt to build one narrow working slice, test it, and save a recoverable version.

Bring forward: Bring the build brief, prompt package, and acceptance tests from Modules 6–7.

Produce: A working thin slice with a version label, test record, known-limit note, and screenshot or demonstration.

0 of 15 core modules complete

Progress is saved on this browser. Create a free membership to sync across devices.

Recommended prerequisite: complete Module 7, “Convert the Brief into a Testable Build Prompt,” and bring its artifact. You may still use this page as a reference.

Build stage

Build the next result

Planning becomes useful only when it produces a verified result. Build the smallest end-to-end journey, inspect what changed, and preserve a version you can recover.

Your result for this module

A working thin slice with a version label, test record, known-limit note, and screenshot or demonstration.

Continuous case study

Worked example: Tracker version 0.1

Version 0.1 only adds an inquiry and displays it after refresh. Editing, reminders, analytics, and automation remain out of scope. The test record covers a normal entry, blank name, invalid date, duplicate entry, keyboard flow, refresh, and small screen.

Do the work

  1. Build one vertical slice

    Choose the smallest journey that crosses the interface, rules, storage, and visible result.

  2. Inspect before expanding

    Review changed files, data storage, external calls, permissions, assumptions, and deviations from the brief.

  3. Run the acceptance tests

    Record the input, expected result, observed result, environment, and evidence for ordinary and edge paths.

  4. Save the working version

    Use a named version or dated recoverable copy. Record known limits before the next change.

Copy-and-complete template

Create your module artifact

Version or dated copy:

Journey demonstrated:

Changed files or components:

Tests and results:

Evidence reference:

Known limits:

Rollback location:

Keep sensitive information, passwords, API keys, payment data, and private customer details out of course notes and AI prompts.

Quality gate

Check the result before the quiz

  • One useful journey works end to end.
  • The build matches the brief’s boundary.
  • Test results are recorded, not merely claimed.
  • A known working version can be restored.

How this moves the project forward

Module 9 applies accessibility tests to this working slice while changes are still inexpensive.

Evidence checkpoint and lesson summary

Confirm the artifact, then answer the key questions

The questions cover a core idea, a realistic decision, and evidence from the lesson. Incorrect answers identify concepts to review; they are not a complete measure of your experience or ability.

Artifact checkpoint

This is an honest self-check. Do not enter private data here; keep the artifact in your own approved workspace.

1. Which slice should be built first for the course example?
2. What evidence should accompany an AI-generated change?
3. Which build record is sufficient for this module?

Confirm the artifact and answer all three questions correctly to unlock the recommended next step.

About the author

Son Kim

Son Kim writes from first-hand experience as a blind AI user. He tests vibe-coding tools, models, plugins, connected hardware, and everyday AI workflows to document what improves accessibility, independence, productivity, earning opportunities, problem-solving, and quality of life—and what still requires human judgment.

Read the full author background

Review the editorial, correction, advertising, and affiliate standards