My best prompt is 12 words long.
It’s the last line of any prompt I use with AI to start a session.
For the first few months I was working with AI I wrote my prompts the 2024/2025 way. The most complex prompts had sections: CONTEXT, OBJECTIVE, ROLE & EXPERTISE, INPUT PARAMETERS, METHODOLOGY, OUTPUT SPECIFICATIONS. One of my longest ran 2,198 words. This form of prompting is Prompt Engineering. The method, write a giant brief, front-load every requirement, hit enter, hope. The gaps I never thought to mention got filled with confident guesses, and the rework landed back on me.
Early in 2026 I kicked off a new project in a fresh session and ended the kickoff with one line:
Ask me questions 1 at a time until you are 95% certain
What happened next was the whole lesson.
It asked one question. Then it waited. I answered. It asked the next one. Each answer sharpened the next question.
It kept asking until it had what it needed, said so, and started. My answers became the spec. Nothing got built on a guess.
Why one at a time matters, for both of us. I’m a visual person and my brain overloads with a wall of questions.1 So asking me questions one at a time allows me to place all my focus on the answer. In doing so I learn far more about how AI interprets my input so I become better at providing context the next time. The added bonus is I give AI the permission to ask for clarity with a goal, 95%, limiting the amount of guessing.
The answers become the spec. The spec becomes the work. The work stops surprising you.
This started as an experiment. Now it runs on everything.
In April I used it in a few sessions. By late May it was in almost every one, several a day.
So I stopped typing it. I encoded it in three places.
A voice shortcut. I say three words, “Ask 1 95,” and the twelve appear.
My standing account instructions, read before every chat:
ALWAYS ask me questions 1 at a time until you are 95% certain of the information/recommendations you provide.
And the file my AI reads about how I think:
Ask clarifying questions. Bring alternate perspectives. Test my reasoning.
It stopped being a prompt I remember to use. It became the default mode of every conversation I have with AI.
How would your AI’s output change if it interviewed you first?
How would you change?
This is Part 4 of Thinking With AI, a multipart series where I chart my 1000+ hour journey from AI Consumer to AI Architect. Every part gives you a practical prompt, tip, or trick you put to work immediately, and builds the me-file your AI reads at the start of every session.
Part 1, My AI Called Me Gary - the 5 output checks and the first section of your ‘me’ file
Part 2, The Explorer Stopped Getting Paid - the pitfall of information hoarding, and what happens when AI assumes a core part of your identity
Part 3, I Gave My AI a Map of My Weaknesses - name your patterns out loud and your AI catches them before you do
If you are new to the series, start with Part 1, where my AI called me Gary and taught me the fifth check I run on every output.
Working memory holds about four items at once, per Cowan, 2001, so use the space wisely.