Glossary / Prompting & Context

Prompt Framework

A repeatable shape for giving AI the context it needs for all questions and tasks.

Updated July 2, 2026

A prompt framework is a repeatable shape for giving AI the context it needs. We teach one called CRIT: context, role, interview, task. Context is the background, role is who the AI should act as, interview means it asks questions when it needs more, and task is the actual job. The prompt is still yours; the framework gives it a better frame.

An intake form at a doctor’s office does the same job. The form doesn’t diagnose you. It makes sure the doctor gets the basics in a consistent order: who you are, what’s happening, what history matters, and what question needs an answer.

Why you care

AI quality often reflects delegation quality. Most bad prompts fail for missing normal delegation details: who this is for, what you’re producing, what good looks like. Instead of “write me a client email,” a framework gets you to real delegation: here’s the client situation, act like a careful account manager, ask up to three questions, then draft. The interview piece teaches you when you haven’t given enough context yet. Keep it light (twelve required fields and nobody uses it), and turn it into a skill if you run it often.