We Ran One Prompt on 3 of Our Own Paragraphs. It Never Wrote a Word. | Edition 291

Every "write me a first draft" prompt makes the same trade: you get words fast, and you get someone else's voice. The fix we tested this week isn't a better generation prompt — it's a prompt that never generates at all.

We built an interview-style prompt that turns any chatbot into a line editor. It doesn't write new sentences. It only edits the paragraph you already wrote — cutting what's dead weight, tightening what's loose, and flagging any claim you can't actually defend. Then we ran it, live, three separate times, on three unscripted paragraphs nobody wrote to look good for this newsletter.

Major brands just took over a Times Square billboard, and every ad was built in Hightouch Ad Studio. Sweetgreen, HelloFresh, and Tripadvisor cleared the toughest room in advertising. Create, edit, and launch on-brand ads in a few clicks.

See what you can build

Why editing beats generating

Ask a model to write your paragraph and it has to invent a voice — and it reaches for the same one every time: smoother, vaguer, and instantly recognizable as AI. Ask it to edit your paragraph instead, and it has nothing to invent. It just has your sentences and a job: cut what doesn't earn its place, tighten what's loose, flag what you can't back up.

The part that actually makes this work isn't the editing instruction — it's the interview. Before the prompt touches a word, it asks who's reading, what's bothering you about the draft, which phrase is off-limits, and which claims you're not sure hold up. Skip that step and any model defaults to smoothing everything into the same beige tone. Answer it, and the model has specific, defensible reasons for every cut.

What happened when we actually ran it

Three tests, three domains: a startup update, a career-change post, and a confession about using AI to help write this very newsletter. Every run followed the same shape — five questions, one at a time, waiting for a real answer before asking the next — then a tightened paragraph, a list of what it cut and why, and a flagged list of claims that needed a source.

It kept exactly what we told it to protect: a shaky-handed table-saw confession, a three-sleepless-weekends line, an offhand note about the AI "asking harder questions" instead of writing for us. It cut the clichés and softened stats sitting around them. And when a paragraph carried a stat someone admitted was made up, the prompt didn't invent a source or quietly delete the number — it named exactly what proof would be needed before the claim could stand.

None of this needed a smarter model. We ran it on a mainstream, current chatbot, and it worked because the prompt does the hard part before generation ever starts: it asks, it waits, and it only touches what's actually broken.

The full breakdown on the site has all three before/after pairs — pick a paragraph, see the actual cuts and flags, with reasons — plus the exact prompt, ready to interview your own draft.

Read the full breakdown and get the prompt on aisupersimplified.com →

— The AI Super Simplified team

AI will eliminate 300 million jobs in the next 5 years.

Yours doesn't have to be one of them.

Here's how to future-proof your career:

Start learning AI now