# How to actually ask: prompting without the magic words > There are no secret incantations. Good prompting is just clear instructions to a brilliant, literal-minded assistant with no memory. A practical guide that follows straight from how the model works. Source: https://rfriedmann.de/blog/how-to-prompt/ Published: 2026-06-23 · Track: learn · Level: Beginner There's a small industry of "prompt secrets", magic phrases, ten-word tricks, lists of incantations that supposedly unlock the model. Almost all of it is noise. Good prompting isn't a spell-book; it follows directly from what the model actually is, and once you've got the mental model, you can work out a good prompt yourself instead of copying someone's ritual. The whole thing rests on one picture, and everything practical falls out of it. ## The one mental model Picture a brilliant, widely-read, eager assistant who is also completely literal, has no idea what's in your head, and forgets you the moment the conversation ends. That's the thing you're talking to. It [predicts the most plausible continuation](/blog/what-is-an-llm/) of whatever you give it, working only from the words in front of it, with [no memory of anything outside this conversation](/blog/the-context-window/). So prompting is not casting a spell. It's **briefing a capable stranger who will take you at your word.** Vague brief, vague work. Clear brief, good work. Everything below is just that idea applied. ## What actually moves the needle In rough order of how much they help: - **Say what you actually want.** The single biggest lever, and the one people skip. "Make this better" gives the model nothing to aim at. "Rewrite this email to be two sentences shorter and more direct, keep the friendly tone" gives it a target. The model can't read the standard in your head; put it in words. - **Give it the context it can't have.** It doesn't know your audience, your constraints, your situation, unless you say so. "Explain this to a non-technical client" produces a completely different, better answer than the same question bare. You're filling a window it would otherwise fill with guesses. - **Show one example.** If you want a particular format or style, show a small sample of it. "Like this: [example]" is worth a paragraph of description, because matching a pattern is exactly what the model is built to do. One good example often beats a long list of rules. - **Give it a role, when it sharpens the task.** "You're a copy-editor; flag anything unclear" nudges the model toward the right register and priorities. Useful as framing, not as a magic costume, it sets the tone, it doesn't grant new powers. - **Ask for steps on hard problems.** For anything involving reasoning, maths, logic, multi-step analysis, "work through it step by step" genuinely helps, because the model reasons *in* the text it writes. Room to think on the page leads to better answers than demanding the conclusion cold. (Newer "reasoning" models do this internally, so it matters less with them, but it rarely hurts.) - **Iterate; don't expect one shot.** The first answer is a draft. "Good, but make it shorter and cut the jargon" is normal and effective. A conversation beats trying to cram the perfect instruction into a single opening message.
Same task, two briefs
[diagram omitted — see the page for the chart]
Identical underlying task. The difference is entirely in the brief: audience, length, format and the angle to lead with. None of it is a trick; it's just telling the literal assistant what success looks like.
## What doesn't help (and what backfires) Worth clearing out the myths, because chasing them wastes time: - **"Magic phrases" are mostly placebo.** Politeness, threats, "I'll tip you $200", none of it reliably changes much. Clarity changes a lot; secret words don't. If a phrase seems to help, it's usually because it smuggled in actual clarity. - **Piling on emphasis rarely works.** "VERY IMPORTANT, ABSOLUTELY MUST" five times doesn't make the model obey harder. State the requirement once, clearly. If it keeps ignoring something, the fix is a clearer instruction or an example, not more capitals. - **An overstuffed prompt can hurt.** Cram in ten only-loosely-related rules and the model can lose the thread, or fixate on the wrong one. Everything you add competes for attention in the [same limited window](/blog/the-context-window/). Relevant and focused beats long. - **Don't trust it more because it sounds sure.** Prompting improves the *answer's shape*, not its *truthfulness*. A beautifully-prompted reply can still [make things up](/blog/why-models-make-things-up/). Better briefs get better drafts; they don't remove the need to check the facts that matter. ## A quick template Not a formula to worship, just a checklist that covers what the model can't guess:

A solid prompt usually has

And you'll often add

## The real secret, which isn't one The best prompters aren't hoarding incantations. They've just internalised what the thing is, a literal, knowledgeable, memory-less assistant, and they brief it the way you'd brief a sharp new colleague who can't read your mind: clearly, with context, and with a draft-then-refine loop. Get that, and you don't need anyone's list of magic words. You can reason out a good prompt for any task, because you understand who, or what, you're actually talking to. That understanding is the whole of these [foundations](/blog/what-is-an-llm/), pointed at getting useful work done.