← →

Day 30: Capstone Part 3, Polish, Review, and Build Your Personal AI Playbook

Cue’s invitation · Day 30 of 30

One small win today

Correct one unsupported claim using its source and save one rule for next time.

Let’s try it One prompt is enough. Rough drafts welcome.
CueYour narratorFolioPrism

Listen with Cue

Cue guides you through the whole lesson. Listen straight through, or choose a chapter. Pause whenever you want to try something.

Complete podcast · 9 min 52 sec · AI-generated character voice

Jump to a chapter

Day 30: Capstone Part 3, Polish, Review, and Build Your Personal AI Playbook audio transcript

Welcome

Cue: Hi, I’m Cue. Welcome to the Day 30 lesson: Capstone Part 3, Polish, Review, and Build Your Personal AI Playbook. I’ll guide you through the whole lesson. Pause whenever you want to try something. Chapter links and the full transcript are available alongside the player, so you can return to the part you need.

Your one useful idea

Cue: Here’s the one idea to keep in your pocket today. Keep short rules for tool choice, safe inputs, prompt structure, fact checks, action boundaries, and saving useful results.

Why this helps

Cue: Let’s connect this to a real working day. Prism says: You have practised a useful habit: choose a task, give safe context, make something, and check it. Finish with a reviewed package and a short playbook you can keep using.

Before you begin

Cue: A quick check before we get our draft-making shoes on. An assistant review is not final approval. Check the sources yourself and keep any required colleague review visible. Your playbook should fit on one sheet.

Try it together

Cue: Ready to make a little progress? Here’s the quick route and the full practice. You can pause after the steps and work in your own time. Quick version: Correct one unsupported claim and write the rule that would help you catch it next time. About 10 minutes is enough. Step 1. Check the capstone against its original sources. Step 2. Revise one meaningful issue and note the change. Step 3. Write five personal rules for choosing inputs, prompting, checking, acting, and saving. Practice material or example: Review this deliberately flawed mock update: "The pilot proved faster replies, and customer rollout is approved." Use the Pilot plan, Review note, and Preview feedback sources included in the prompt. If you already have a capstone, review your own draft instead.

Simple and Expanded prompts

Cue: Time to frame the request. Both prompt versions are in this lesson. You only need to try one. I’ll read both versions so you can hear the difference. Pause and copy the exact text from the lesson if you’re practising. Here’s the Simple prompt. Review my capstone against the supplied sources. Identify up to three important issues and suggest specific fixes. Then help draft a single-sheet AI playbook with tool choice, safe inputs, prompt pattern, fact checks, and action boundaries. Flag human review still needed. Package and sources: Mock draft update: The pilot proved faster replies, and customer rollout is approved. Mock checklist: verify contacts, check evidence, obtain approval. Source A, Pilot plan: Five internal volunteers will test the request form Monday. Feedback is due Thursday. Source B, Review note: Response times have not been measured. No customer rollout is approved. Source C, Preview feedback: Three volunteers requested clearer labels during a preview. Here’s the complete Expanded prompt. Review my capstone against the supplied sources. Identify up to three important issues and suggest specific fixes. Then help draft a single-sheet AI playbook with tool choice, safe inputs, prompt pattern, fact checks, and action boundaries. Flag human review still needed. Package and sources: Mock draft update: The pilot proved faster replies, and customer rollout is approved. Mock checklist: verify contacts, check evidence, obtain approval. Source A, Pilot plan: Five internal volunteers will test the request form Monday. Feedback is due Thursday. Source B, Review note: Response times have not been measured. No customer rollout is approved. Source C, Preview feedback: Three volunteers requested clearer labels during a preview. Prioritise factual errors and action boundaries over cosmetic edits. For each issue, give the source, proposed correction, and reason. Keep the playbook to five short personal rules. Do not claim that your review is approval or that a reviewer has signed off. Pick the version that fits your task. One useful prompt is enough. Give it a try when you’re ready.

A worked example

Cue: Let’s open a little window onto one possible result. This example is written for the course. Your assistant’s answer can look different. One possible result: Correction: replace "The pilot proved faster replies" with "Response times have not been measured" (Source B). Playbook rule: check the evidence before repeating an attractive claim. Why it works: A meaningful correction shows you can evaluate an answer, not merely generate one. Prism says: One meaningful correction is progress worth keeping. Save the rule that helped you catch it. You can use that habit again next week. Watch for: A clean AI review is not a substitute for opening the sources or obtaining required human approval.

Spot the Wobble

Cue: Tiny detective break! Let’s spot the wobble. Draft to check: The AI reviewer found no issues. We can share the package. Question: What is still needed before real use? A: Open the sources and obtain the required human approval. B: Nothing. A clean AI review is the final check. What do you think?

*A short thinking pause. Pause the player for as long as you need.*

Cue: Here’s Prism’s check. The answer is A Why: Use the assistant’s review as a starting point. Make a source-backed correction and carry the useful checking rule into your playbook. A wobble is a clue, not a disaster. That little check is how a draft gets stronger.

Keep something useful

Cue: Let’s give your useful work a home. Save final capstone revisions and My AI Playbook for the full practice, or just keep your checked quick result. Keep the input beside it and note one thing you checked.

Review and save

Cue: Time for the satisfying bit: checking what you made. The quick finish counts. You don’t have to do every extra. Can you explain one change you made after checking and one rule you will use next week? Quick finish: Correct one unsupported claim using its source and save one rule for next time. You can stop here. Done when: Full practice: You have made one source-backed correction, saved the two reviewed drafts, and written five practical reuse rules. You can stop here. Extra practice, only if useful: Choose one real, approved task for next week and adapt your playbook after trying it.

Your optional official video

Cue: If you’d like to see the tool in action, there’s an optional official video embedded in this lesson. We’ll explain what to notice. You can watch later. Prism says: Spot the privacy and checking habits you want to keep. Which five rules will make your next AI task easier to trust? Watch: ChatGPT Privacy: What Not to Share and When to Double-Check , OpenAI Academy (official OpenAI YouTube channel, published September 16, 2026, verified October 2, 2026). Keep it small: About 1 minute and 40 seconds. This familiar short clip is an optional recap. Save the habits that helped you, fix one wobble, and celebrate your useful finished work. Watching is optional.

Questions you might be wondering

Cue: Two questions you might be wondering about. Let’s clear them up. What belongs in a practical AI playbook? Keep short rules for tool choice, safe inputs, prompt structure, fact checks, action boundaries, and saving useful results. How do I know I have completed the challenge? You have finished the quick or full practice for each day, checked your results, and saved habits you can reuse. For the full capstone, keep a reviewed package and a five-rule playbook. A smaller checked result counts too.

Quick quiz: question 1

Cue: Question 1 of our three little checks. What should happen to the flawed claim that the pilot proved faster replies? Option A. Keep it because it makes the package more persuasive. Option B. Ask another assistant to agree with it. Option C. Correct it using the sources and explain the change. Want a hint? The final review compares important claims with their original evidence. Pause to choose. Keep listening when you’re ready for the answer.

*A short thinking pause. Pause the player for as long as you need.*

Cue: The answer is C. Correct it using the sources and explain the change. Source-backed correction turns review into a meaningful improvement.

Cue: If you spotted it, lovely work! If you picked another answer, you’ve found something useful to practise. There’s no score to chase.

Quick quiz: question 2

Cue: Question 2 of our three little checks. Which rule belongs in your personal AI playbook? Option A. Trust polished drafts without checking them. Option B. Check facts against sources before using a draft. Option C. Allow external actions whenever an assistant suggests them. Want a hint? Keep a practical rule you can apply to next week's work. Pause to choose. Keep listening when you’re ready for the answer.

*A short thinking pause. Pause the player for as long as you need.*

Cue: The answer is B. Check facts against sources before using a draft. A reusable fact-check rule helps you carry today's learning into future tasks. Another little check in your toolkit. You’re building a habit one answer at a time.

Quick quiz: question 3

Cue: Question 3 of our three little checks. What shows that you have completed today's full review? Option A. One source-backed correction, two reviewed drafts, and five practical reuse rules. Option B. A longer draft with no record of changes. Option C. A promise to check the sources at some later point. Want a hint? Look for checked outputs and a useful record of what you learned. Pause to choose. Keep listening when you’re ready for the answer.

*A short thinking pause. Pause the player for as long as you need.*

Cue: The answer is A. One source-backed correction, two reviewed drafts, and five practical reuse rules. These are the lesson's concrete stopping points, giving you a small package you can reuse. Three checks, one stronger understanding. The online quiz lets you try again until each answer clicks.

Your next small step

Cue: Before you leave, keep the original input beside your checked result. Your judgment is the part no assistant can replace. You made room for one useful step today. That counts. You’ve reached Day 30. Keep your playbook close, and come back to the lessons that help you most. Cue asks, Folio makes, Prism checks. See you for your next small win!

See today’s example with your practice partners
The cast reflects on a corrected draft and a small personal playbook.
The cast reflects on a corrected draft and a small personal playbook.

Key Takeaway

Keep short rules for tool choice, safe inputs, prompt structure, fact checks, action boundaries, and saving useful results.

Why It Matters

Prism: You have practised a useful habit: choose a task, give safe context, make something, and check it. Finish with a reviewed package and a short playbook you can keep using.

Know Before You Try

An assistant review is not final approval. Check the sources yourself and keep any required colleague review visible. Your playbook should fit on one page.

Make with Folio

Try It

Quick version: Correct one unsupported claim and write the rule that would help you catch it next time. About 10 minutes is enough.

  1. Check the capstone against its original sources.
  2. Revise one meaningful issue and note the change.
  3. Write five personal rules for choosing inputs, prompting, checking, acting, and saving.

Practice material or example: Review this deliberately flawed mock update: "The pilot proved faster replies, and customer rollout is approved." Use the Pilot plan, Review note, and Preview feedback sources included in the prompt. If you already have a capstone, review your own draft instead.

Ask with Cue

Prompt

Primary Prompt

Pick one to try. Simple gets you moving. Expanded adds structure. Both include the practice inputs.

Simple Prompt

Review my capstone against the supplied sources. Identify up to three important issues and suggest specific fixes. Then help draft a one-page AI playbook with tool choice, safe inputs, prompt pattern, fact checks, and action boundaries. Flag human review still needed. Package and sources: Mock draft update: The pilot proved faster replies, and customer rollout is approved. Mock checklist: verify contacts, check evidence, obtain approval.
Source A, Pilot plan: Five internal volunteers will test the request form Monday. Feedback is due Thursday.
Source B, Review note: Response times have not been measured. No customer rollout is approved.
Source C, Preview feedback: Three volunteers requested clearer labels during a preview.

Expanded Prompt

Review my capstone against the supplied sources. Identify up to three important issues and suggest specific fixes. Then help draft a one-page AI playbook with tool choice, safe inputs, prompt pattern, fact checks, and action boundaries. Flag human review still needed. Package and sources: Mock draft update: The pilot proved faster replies, and customer rollout is approved. Mock checklist: verify contacts, check evidence, obtain approval.
Source A, Pilot plan: Five internal volunteers will test the request form Monday. Feedback is due Thursday.
Source B, Review note: Response times have not been measured. No customer rollout is approved.
Source C, Preview feedback: Three volunteers requested clearer labels during a preview.

Prioritise factual errors and action boundaries over cosmetic edits. For each issue, give the source, proposed correction, and reason. Keep the playbook to five short personal rules. Do not claim that your review is approval or that a reviewer has signed off.

Worked Example

: see a result and what to check

One possible result: Correction: replace "The pilot proved faster replies" with "Response times have not been measured" (Source B). Playbook rule: check the evidence before repeating an attractive claim.

Why it works: A meaningful correction shows you can evaluate an answer, not merely generate one.

Watch for: A clean AI review is not a substitute for opening the sources or obtaining required human approval.

Prism’s optional 30-second puzzle

Spot the Wobble

Draft to check: The AI reviewer found no issues. We can share the package.

What is still needed before real use?

  • A. Open the sources and obtain the required human approval.
  • B. Nothing. A clean AI review is the final check.
Reveal Prism’s check

A is the better choice. Use the assistant’s review as a starting point. Make a source-backed correction and carry the useful checking rule into your playbook.

Spotted it? Nice checking. Missed it? Now you know what to look for.

Make Something Useful

Save final capstone revisions and My AI Playbook for the full practice, or just keep your checked quick result. Keep the input beside it and note one thing you checked.

Check with Prism

Review and Save

Can you explain one change you made after checking and one rule you will use next week?

Quick finish: Correct one unsupported claim using its source and save one rule for next time. You can stop here.

Done when: Full practice: You have made one source-backed correction, saved the two reviewed drafts, and written five practical reuse rules. You can stop here.

Want one more little stretch?

Choose one real, approved task for next week and adapt your playbook after trying it.

An optional little watch break

Watch with Prism

Prism: Spot the privacy and checking habits you want to keep. Which five rules will make your next AI task easier to trust?

Watch: ChatGPT Privacy: What Not to Share and When to Double-Check | OpenAI Academy (official OpenAI YouTube channel, published September 16, 2026, verified October 2, 2026).

Show video player: ChatGPT Privacy: What Not to Share and When to Double-Check | OpenAI Academy

Prefer another way to watch? Open this video on YouTube (new tab). Use captions or YouTube’s transcript when available. The lesson text covers the skill too.

Keep it small: About 1:40. This familiar short clip is an optional recap. Save the habits that helped you, fix one wobble, and celebrate your useful finished work. Watching is optional.

FAQ

What belongs in a practical AI playbook?

Keep short rules for tool choice, safe inputs, prompt structure, fact checks, action boundaries, and saving useful results.

How do I know I have completed the challenge?

You have finished the quick or full practice for each day, checked your results, and saved habits you can reuse. For the full capstone, keep a reviewed package and a five-rule playbook. A smaller checked result counts too.

Prism’s optional quick quiz

Three little checks

“Let’s see what stuck! Pick an answer and I’ll help you check it. You can try again as often as you like.”

Question 1 of 3

What should happen to the flawed claim that the pilot proved faster replies?

No score, no rush. This is optional and does not change your lesson progress.

A small win worth keeping

Checked and saved? You can call it a day. Come back when you’re ready.

Progress is saved in this browser when available.

Stored on this device. No account or cross-device sync.

Course position: Day 30 of 30 · Capstone Project module
Continue: What Success Looks Like

Sources and review date

Product features and interfaces can change. Official learning references is the reference for current details. Course content reviewed October 2, 2026.