How much context to put in an AI prompt

Stop the back-and-forth. Put every fact the model needs into the first message.

The problem

Missing context is the #1 cause of multi-turn 'context setting'. The model asks clarifying questions, you answer, repeat. Each round costs time and tokens.

The fix

Add a CONTEXT block: who the audience is, what inputs/data the model has, and what success looks like. If a fact would change the answer, it belongs in the prompt.

Try it

Add enough context (audience, inputs, goal) to make this one-shot. Aim for 70+.

56structure

Target: 70. Keep working the prompt. The score moves as you type.

Context: Front-load all context the model needs: inputs, audience, goal, and constraints, so it can answer in one shot.
Constraints: State limits and do/don't rules, e.g. "Keep it under 200 words. Do not invent APIs."
Output format: Specify the exact shape, e.g. "Return JSON: { title, steps[] }" or "Use a markdown table.".

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.