The same idea, said four different ways.

Twenty-five techniques for getting real work out of an AI assistant — each one rewritten for ChatGPT, Claude, Gemini and Perplexity, because the four do not reward the same habits. Copy any prompt and use it today.

What most people type

Write something about the benefits of exercise.

What gets you something usable

Write an 800-word article on the benefits of exercise for busy professionals in their 30s and 40s living in urban India. Cover three benefits: stress reduction, better sleep, and sustained energy through a long workday. Keep the tone encouraging and practical, not clinical. End with three things the reader can start this week without a gym.

32lessons
4platforms
384prompts to copy
Freeno sign-up

Part One — the principles

Twenty-five techniques for writing a prompt that works the first time. Each opens on ChatGPT — switch tool at the top of any lesson.

  1. 01 The Principle of the Definite Chief Aim A prompt gets you what you actually asked for, so the useful skill is naming the exact thing you want: the decision you are making, by when, with what numbers, and what you will do with the answer.
  2. 02 The Blueprint of Creation Instead of describing what you want and hoping the shape comes out right, hand over the empty shape itself - the sections, the row names, the table columns - and say what goes in each slot.
  3. 03 The Power of Organized Knowledge The model knows a great deal about the world and nothing at all about your situation, so generic advice is the only honest thing it can give you until you supply the facts.
  4. 04 The Law of the Master Persona Telling the model who to be changes what it notices.
  5. 05 The Secret of Silent Suggestion Instead of describing the output you want, show two or three finished examples and let the model work out the pattern.
  6. 06 The Erection of Mental Fences A delimiter is a visible boundary - a row of dashes, a fenced block, an XML tag - drawn around the material you pasted in, so the model can tell your raw material apart from your orders.
  7. 07 The Virtue of Persistent Effort Your first prompt is a hypothesis, not a finished article.
  8. 08 The Discipline of Precise Limitation Constraints are not a cage; they are the banks that turn a flood into power.
  9. 09 The Ladder of Logical Progression Split the job into named stages and ask to see the working at each one.
  10. 10 Commence with the End in Mind Describe the finished thing before you ask for it, and put that description last.
  11. 11 The Art of the Open Question A closed question asks for a yes or a no, and a yes or a no is all you get.
  12. 12 The Council of Invisible Counselors A single answer, however well written, is one point of view - and usually the most agreeable one.
  13. 13 The Search for Absolute Truth These machines state a falsehood in exactly the same confident voice they use for a fact, because they have no way of telling the two apart.
  14. 14 The Transmutation of Form The information you need often already exists - in a twenty-page circular, in forty WhatsApp messages, in the doctor's scrawl on a prescription pad - but it is in the wrong shape for the person who has to act on it.
  15. 15 The Power of the Negative Command Most people describe only what they want, and then spend three rounds removing what they did not.
  16. 16 The Seed of a New Idea Do not ask for the perfect name.
  17. 17 The Language of Simplicity A hesitant request earns a hesitant answer. "I was sort of hoping you could maybe give me an idea of the main points" invites a wander; "Summarise this in three bullet points" commands a result. Keep your fine language for the thing you want written - the instructions themselves should be short sentences, strong verbs, exact counts and exact formats. This is not the mark of a simple mind. It is the mark of someone who has decided what they want.
  18. 18 The Principle of Controlled Imagination Creative work needs two things at once.
  19. 19 The Elimination of Mental Static A prompt is a signal, and typing in a hurry puts static on it.
  20. 20 The Strategic Use of Temperature Some jobs have one right answer and some have a hundred.
  21. 21 The Master's Review Two reviews make the difference between a gamble and a plan.
  22. 22 The Chain of Thought A big task thrown at the machine in one piece comes back as a plausible blur: everything mentioned, nothing checkable.
  23. 23 The Reversal of Perspective When an answer comes back strangely off-target, the usual reaction is to type the same request again, louder.
  24. 24 The Treasure of Specificity The machine cannot read your mind, so every detail you leave out it fills in with the average of everything it has seen - and the average is what makes an answer sound like it was written for nobody.
  25. 25 The Formation of the Master Mind This is the chapter that gathers up all the others.

Part Two — the method

Where the real work happens. Looping, chaining, memory, files and voice, research agents, and using all of it safely.

  1. 26 The Law of the Loop Prompt, Read, Refine — The first prompt is the opening move, not the whole game.
  2. 27 The Unbroken Chain Prompt Chaining — Instead of asking for the whole job in one prompt, break it into a short sequence - research, outline, draft, polish, translate - where each step's output becomes the next step's input, and you inspect it before passing it on.
  3. 28 The Mirror of Self-Critique Reflection Loops — Build the checking into the prompt itself.
  4. 29 The Gift of Living Memory Projects, Gems & GPTs — Standing context is a prompt that never sleeps.
  5. 30 The Senses of the Machine Files, Images & Voice — These assistants can now look at a photograph, read a document, work through a sheet of figures and listen to your voice - so stop labouring to describe what you could simply show.
  6. 31 The Tireless Apprentice Agents & Research — An agentic or deep-research mode does not answer one question - it takes an errand and runs several steps by itself: planning, searching, reading, comparing, drafting.
  7. 32 The Guardian's Oath Safe & Wise Use — Safety is a habit inside each prompt, not a warning at the end of the book.