How to define the task in an AI prompt

The heaviest-weighted thing the scorer looks for, and the one most prompts fumble: an explicit action.

Why it scores highest

Task clarity carries more weight than any other dimension. A model that cannot tell what action to perform will pick one for you, usually the blandest reading. 'Help me with my landing page' could mean write it, audit it, redesign it, or debug its CSS. Four different jobs, one sentence.

How to do it

Lead with one imperative verb and its object: refactor this function, draft this email, classify these tickets. One primary verb, not three. A prompt that asks to 'research, summarise and then design' is three prompts wearing a trenchcoat. Split them.

The test

Read only your first eight words. If someone could carry out the wrong job from them, the verb is missing or buried. Move it to the front.

Try it

Rewrite this so it names one explicit action. Aim for a score of 55+.

44structure

Target: 55. Keep working the prompt. The score moves as you type.

Role / persona: Open with a persona, e.g. "You are a senior backend engineer."
Task clarity: Lead with one explicit action verb and object, e.g. "Refactor this function to…".
Constraints: State limits and do/don't rules, e.g. "Keep it under 200 words. Do not invent APIs."

Now put it to work: score a prompt you actually use on the desk and see whether this part is one it was missing. This is one of seven parts. To see all of them already in place, the templates are the finished shape; to practise on something new, the daily drill posts one brief a day.