Stop role-playing your prompts: what works on modern AI

You can stop telling the AI it is a “world-class expert”, and you can stop adding “think step by step” to everything. With today’s capable models, those tricks barely move the needle. What actually helps is boring and effective: a clear goal, the real context, the output format you want, a few constraints, and maybe a couple of examples.

The reason is simple. The newer reasoning models already work things through internally before they answer. Tools like Claude with extended thinking, Google’s Gemini thinking models, and OpenAI’s reasoning models do the “step by step” part on their own. So asking for it again is like reminding a chef to use the oven.

Why did role-play prompts ever work?

Back in 2023, models were weaker and more literal. Telling one “you are a senior copywriter with 20 years of experience” nudged it toward a more careful style, because it did not have a strong default. Threatening it, bribing it with imaginary tips, or chanting “think step by step” sometimes squeezed out slightly better answers.

Models have moved on. The defaults are much stronger now, so the nudge is mostly noise. You are spending words on theatre instead of on the thing that matters: telling the model what you actually want.

So what works now?

Here is the short version. Swap the theatre for substance.

Start with the goal

Say plainly what you want and who it is for. “Write a friendly two-line reply declining this meeting” beats “act as an executive assistant” every time. The model does not need a costume. It needs a target.

Give it real context

This is the biggest lever. Paste the email you are replying to. Drop in the messy notes. Tell it the audience, the tone, and anything it cannot guess. A model with the actual details will outperform any clever phrasing.

Name the output format

Ask for a table, three bullet points, a tweet, a 100-word summary, whatever you need. If you do not say, you get the model’s default, and then you waste a round asking it to reshape things.

Add constraints and a couple of examples

Constraints are guardrails: “no jargon”, “under 80 words”, “British spelling”. Examples are even stronger. Show one or two samples of the style you like, and the model will match them better than any description could.

What about the small, fast models?

Fair caveat. Some smaller or older non-reasoning models still benefit from a little structure, like a short “here is how to approach this” nudge. So if you are using a lightweight model on your phone or a cheap tier, a bit of scaffolding can help. But for the capable frontier models most people reach for, clarity beats ceremony.

The real skill is iterating

Your first prompt is a draft, not a spell. Read the answer, tell the model exactly what is off (“too formal, cut the intro, keep the second point”), and let it revise. That back-and-forth is where good results come from. I dug into that habit in prompting is editing, not incantation, and broke down the parts of a solid prompt in the anatomy of a good prompt.

So next time you open Claude or any modern assistant, skip the role-play. Tell it the goal, hand it the context, name the format, and refine from there. Plain and direct wins now.