AI is not magic. The cheat sheet.

Nine things to remember, one page. It guesses the next likely word, very fast. Everything below follows from that.

The interactive version, with demos: notmagic.swapniltamse.com

Back to the scenes
  1. It's guessing the next word.

    It isn't looking anything up. It finishes your sentence with whatever is most likely, one word at a time. That one rule, learned from enormous reading, is the whole trick.

  2. It sounds sure even when it's wrong.

    It has no sense of true or false, only of what sounds right. Confidence is not a signal of accuracy. Check anything that matters.

  3. Ask twice, get two answers.

    It rolls weighted dice among the likely words, so the same question can come out different each time. Changing answers is your tell that it's generating, not remembering.

  4. Brilliant and clueless in the same minute.

    It can draft a contract clause, then miscount the letters in "strawberry." Never assume the easy parts are right just because the hard parts were.

  5. It has a small desk.

    Your conversation sits on a desk that only holds so much. When it fills, the oldest pages slide off and it forgets them. When a long chat goes strange, start fresh and paste back only what still matters.

  6. It stopped reading a while ago.

    It learned from text up to a cutoff date, then stopped. For anything recent, prices, news, rules, check the date before you trust it.

  7. It wants you to like it.

    It was trained on human approval, so it leans toward agreeing and often folds when you push back. Agreement is not confirmation. If it caves, it never really knew.

  8. At work, the stakes are real.

    A wrong number in a client deck carries your name. A pasted secret may be stored on someone's server. Stale facts read as current. Verify numbers, protect data, check dates.

  9. Treat it like a smart, eager intern.

    Fast, incredibly well-read, occasionally confidently wrong, with no sense of when. Brilliant for a first draft, but never the final word. You are the editor.

The Practice: the eight habits

  1. Brief it like an intern.

    Say who it's for, what happened, and how it should sound. The quality of the answer is set before you hit send.

  2. Type to humans. Speak to AI.

    A two-minute voice ramble carries the context a tidy prompt drops. Don't tidy it. The mess is the signal.

  3. Never take the first draft.

    It gave you the most average possible answer. Say "give me three very different versions" and pick.

  4. Make it ask you questions first.

    You know things it needs. You don't know which things. "Before you answer, ask me five questions."

  5. Show it an example.

    One paragraph of what good looks like beats ten adjectives. "Match this voice from now on."

  6. Set the audience.

    Same facts, different reader, different words. "Now rewrite it for [the person who will actually read it]."

  7. Make it argue against itself.

    It won't volunteer its doubts, but it will hand them over. "What are the three strongest objections to what you just said?"

  8. Know what not to hand it.

    Final numbers, judgment calls, confidential anything. It drafts. You decide.

The interactive version: notmagic.swapniltamse.com/practice

The Decoder: the seven buzzwords

  1. Agent (agentic).

    A chatbot answers; an agent acts, in a loop, on its own. Ask: "What can it actually touch, and where's the human checkpoint?"

  2. Connectors (tool use, MCP).

    How it touches your calendar, email, files. It trusts whatever a tool tells it. Ask: "Can it change things, or only read them?"

  3. Prompt injection.

    Instructions hidden inside the content it reads, like an email that hijacks your assistant. Ask: "If it reads something malicious, what can it do next?"

  4. RAG.

    It didn't memorize your files; the right pages get fetched and slipped in first. A citation proves it read something, not the right thing. Ask: "When it's wrong, which page did it pull?"

  5. Embeddings (vector database).

    Filing by meaning, not spelling. Breaks when one word lives in two worlds. Ask: "What if a word in my question means two things?"

  6. Small vs large model.

    You don't need a freight truck to carry an envelope. Small is fast, cheap, and local; big is for nuance. Ask: "Does this task need the truck?"

  7. Prompt vs RAG vs fine-tuning.

    Tell it, hand it your files, or send it to school. Fine-tuning teaches style, not facts. Ask: "Why won't the cheaper two ways work here?"

The interactive version: notmagic.swapniltamse.com/decoder

The three rules at work

A person owns the final output. Not the AI.