Page 25 · Module 01, Think Like a Strategist · this screen continues that page
All 108 frameworksC.A.R.E Prompting
How LLMs actually think and how to work with that
The prompt
Copy & paste readyLabelsReplace these
Pro tip, from the book
If your output feels off, the problem is almost always a vague Role or missing Expectation. Fix those two before rewriting the whole prompt.
Who should run this prompt
Module role profileWho should reason through this problem? The quality of your thinking is shaped by whose lens you borrow. A strategist and a risk analyst look at the same problem and see completely different things — both useful, both necessary. Before you prompt, choose who you need in the room. These profiles give you six internal perspectives and four outside views that challenge your assumptions before you commit to them.
The roles below are who the book suggests running this prompt — this lesson’s prompt doesn’t open with a single swappable role clause, so pick one and adapt the prompt’s own wording yourself.
◆◆◆◆◆ → ◆ seniority, board level down to specialist◈ outside the organisation
How to make any role sharper
- Add years of experience: "...with 15 years in enterprise SaaS" produces different depth than just the title.
- Add what they care most about: "You care most about [X]" shapes every word of the output.
- Add their communication style: "Be direct. Flag risks first. No jargon." changes the tone entirely.
Use this when
The problem it solvesYou're new to AI and getting inconsistent, generic outputs. You want a reliable structure that makes every prompt work better from day one. LLMs respond to structure. C.A.R.E gives every prompt four layers: Context (the situation), Action (what you want done), Role (who the AI should be), Expectation (what the output should look like). Every strong prompt has all four. Most weak prompts are missing two. Context is usually the layer people skip, and it does the heaviest lifting since the AI has no idea who you are or what you need without it. Role is the fastest lever for quality, narrowing vocabulary and depth instantly. Expectation is where most prompts fail silently: if you don't state a length or format, the AI guesses one for you.
The method, in four moves
Do these in orderIdentify what you need: a decision, a draft, an analysis, or a plan.
Fill in each C.A.R.E layer before prompting even just mentally.
Start every prompt with the Role. It sets the entire tone.
State Expectation clearly: format, length, tone, and depth. A B2B SaaS founder was getting generic copy from AI. After adding Role ('Act as a direct-response copywriter who specialises in B2B SaaS') and Expectation ('3 subject lines, under 8 words, curiosity-gap style'), his open rate jumped from 18% to 31% in one send. Same brief. One C.A.R.E pass. IN PRACTICE
Where the framework comes from
Prompt Engineering community best practice — popularised 2022–2023
Pairs well with
As printed with this frameworkModule 01 — Think Like a Strategist
Learn to work with AI. Then learn to think. Both are non-negotiable.
13 frameworks, printed on pages 22–47.
When this page changes, your copy of the book does not have to.
The book prints the framework. This page keeps it — and keeps the prompt current, because prompting technique moves faster than print does. When it moves, this page is rewritten and the code in your copy keeps pointing at it. No second edition, no replacement purchase, no account.
If something here looks wrong — a prompt that does not match its framework, a figure that reads oddly — tell Raphy. That correction reaches every printed copy at once.
Copying is free. An account keeps them.
Nothing on this page is behind a login and nothing ever will be. Save any prompt to your own list, pick up on another device, and send a colleague a link with your name on it. No card, no trial, no paywall on the prompts themselves.