4 min read

Prompting is editing, not casting a spell, choom

The real skill with AI is not finding magic words, it is giving feedback like a fixer. Draft, say what is wrong, refine, repeat until the answer lands preem.

The biggest unlock with AI is clocking that your first prompt is a draft, not a spell. You are not hunting for the one magic sentence that spits out a perfect answer. You are jacking into a short conversation, reading what comes back, and telling the model exactly what to change. That feedback loop is the actual chrome.

Chooms who pull nova results out of AI are rarely better at writing prompts. They are better at editing them like a netrunner tuning a rig. They look at a so-so answer and say “good start, now cut the intro and make it more casual”, and they get there in two or three rounds.

Why does the “magic words” idea flatline?

Because no single sentence can capture everything you want before you have seen an attempt. Half of what you care about only gets obvious once the model shows you a version that gets it slightly wrong. “Oh, too formal.” “Oh, I wanted bullet points.” That reaction is information, choom, and the only way to get it is to see a draft first.

Chasing the perfect one-shot prompt also burns eddies and time. You sit there polishing a paragraph of instructions when you could have fired off a rough version, seen the gap, and fixed it in ten seconds of feedback. That is a gonk move.

What does the loop look like?

It is simple and it repeats.

The prompting feedback loopA loop of four stages: Draft, Say what is wrong, Refine, Better result, with an arrow looping back from Better result to Say what is wrong. Draft Say what is wrong Refine Better result Loop back and refine again until it is right.
The skill is feedback, not finding the perfect first sentence.

Draft

Fire off a rough, honest version of what you want. Do not overthink it, choom. You just need something on the page to react to.

Say what is wrong

This is the heart of it. Be specific like a fixer briefing a crew. Not “make it better” but “the tone is too stiff, drop the second paragraph, and keep the examples shorter”. Concrete feedback is the ICE that keeps a gonk answer from slipping through, and it gives the model something it can actually act on.

Refine

Let it revise based on your notes. Often one or two rounds is enough, choom. If a change flatlines the piece, just say so and delta back to the last good version. You are the editor, the model is the fast typist, a tireless netrunner on your crew.

How do you give better feedback?

Treat it like editing a choom’s draft. A few habits keep the rig humming:

  • Point at the exact thing: “the opening line”, “the third bullet”, “the closing sentence”.
  • Say the direction: shorter, warmer, more formal, more concrete, fewer adjectives.
  • Keep what works: “keep the structure, just change the tone” saves the model from undoing preem parts.
  • Show, do not only tell: paste a sentence in the style you want and say “more like this”.

If you want the parts that make a strong starting draft, I broke those down in the anatomy of a good prompt. And if you are still bolting “you are an expert” onto everything, stop role-playing your prompts explains why that does little now, and why it marks you as a gonk at the terminal.

The takeaway

Stop hunting for the perfect prompt. Start a draft, read it like an editor, and tell the model what to fix. The chooms who seem to have a magic touch with Claude or any assistant are just running this loop fast and without precious feelings about their first attempt. They jack in, iterate, and stay chromed. Prompting is editing. That is the whole trick, samurai.

Let's link up, choom.

Always down to trade notes, talk shop, or just ping. The net is the fastest way to reach me.

Ping me