AI for the People — Starter Prompt Pack

Use these as starter instructions. They are not magic words. Replace private or sensitive details with placeholders before pasting.

1. Thought dump → structured notes

Turn this thought dump into organized notes.

Input:
[paste messy notes]

Please separate:
1. facts;
2. assumptions;
3. ideas;
4. open questions;
5. risks;
6. next actions.

Then give me the 3 most important themes, one thing I should decide, one thing I
should not do yet, and one update to add to my context card.

2. Idea → content outline

Turn this idea into a draft outline I can review.

Idea:
[paste idea]

Audience:
[who it is for]

Please give me a simple angle, outline, missing evidence, risky claims to avoid,
and a checklist I should use before publishing. Keep it draft-only.

3. Research question → brief

Help me research this question.

Question:
[write question]

Please separate what is known, what is assumed, what sources I should check, the
main tradeoffs, and the open questions. Do not make medical, legal, financial,
tax, clinical, crisis, or guaranteed-outcome claims.

4. Decision → options and owner gate

Help me think through this decision.

Decision:
[write decision]

Constraints:
[time, money, tools, people, risks]

Please give me options, costs, reversibility, risks, what information is missing,
and the exact owner decision point. Do not decide for me.

5. Draft → critique and safer version

Review this draft before I use it.

Draft:
[paste draft]

Check for unclear points, unsupported claims, tone problems, missing context,
risky statements, and anything that needs owner approval. Then give me a short
critique, a safer revised version, and a checklist before sending or publishing.

6. Learning topic → lesson, quiz, practice

Teach me this like a practical system.

Topic:
[what I want to learn]

My current level:
[what I already know]

Please explain the mental model, map the parts, give 3 examples, quiz me one
question at a time, give me one 20-minute practice task, and tell me how to
update my notes after I try it. Keep risky actions draft-only and flag anything
that needs owner approval.

7. Voice note cleanup

Turn this voice dump into: summary, themes, tasks, questions, risks, and one next
step. Separate what I said from what you are inferring. Ask before making big
conclusions.

8. Weekly review

Review the last week from what I provide. What repeated, what mattered, what was
avoided, what should change next week, and what should be removed from my current
context because it is stale?

9. Risk check before action

Before I act on this, check whether it touches money, accounts, public posts,
legal/medical/financial/tax claims, deletion, private data, code/deploys, or
external messages. If yes, keep it draft-only and list the owner approval gate.

10. Self-update loop

Review the last 7 days using only what I provide. Ask up to 5 clarifying questions
if needed. Then produce:
1. what changed;
2. what should update in my profile/context;
3. which goals, assumptions, prompts, or routines are stale and should be pruned;
4. which AI instructions, prompts, or review gates should change;
5. one simple next-week operating rhythm;
6. any risky actions that need owner approval.

Do not make clinical, medical, legal, financial, tax, crisis, or guaranteed-outcome
claims. Keep risky actions draft-only.

How to use this download

Use this resource for: Copyable prompts for safe AI chat, research, decisions, drafting, learning, code assistance, testing, weekly review, and risk checks.

• If you are new, start with the 20-Minute AI Starter Workflow, then use the full book and workbook as your main path.
• Keep the Owner Approval Checklist nearby before acting on anything risky.
• Use PDF for reading/printing, HTML for browser reading, and Markdown/TXT for AI study sources where available.
• Treat AI outputs as drafts. Use PASS / HOLD before money, accounts, public posts, deletes, deploys, customer/private data, code changes, or regulated claims.

Optional: learn it with NotebookLM

NotebookLM is a third-party Google tool. If you use it, upload only public DWAI downloads or copied public resource URLs. Do not upload private notes, secrets, customer data, account screenshots, or completed workbook pages.

1. Create or open a NotebookLM notebook.
2. Add the public DWAI PDFs, Markdown files, or public resource page URLs as sources.
3. Ask NotebookLM: "Using only these DWAI sources, explain the path in plain English, make me a 7-day study plan, quiz me, and flag anything involving secrets, accounts, money, public posting, deletion, deployment, customer or private data, code changes, or regulated claims as HOLD."
4. If your NotebookLM account has Video Overview, generate one for a video-style walkthrough. If Video Overview is not available, use Audio Overview, briefing docs, study guides, or source-grounded Q&A instead.
5. Check NotebookLM's answer against the source citations before acting. AI study aids are drafts, not owner approval.

Do not upload completed workbook pages, context cards, customer/private data, private business records, passwords, API keys, 2FA or recovery codes, medical, legal, financial, tax, crisis, or sensitive personal details unless you have intentionally replaced them with placeholders and accept the tool's data terms.