Prompt: Write a standing brief so every AI session starts informed (UP-Context, Working with AI)

Sam Utteker

2 days ago

5 min read

Updated: 2 days ago

An abstract sheet with folded corners and a seal, ready to hand over.

In this Prompting Publication

What this prompt does

This prompt does one job: it turns your context layers and answers into a short standing brief that a colleague or a fresh AI session can read before starting. It is the fastest way to make your context reusable by someone other than you.

UP-Context prerequisites

Required layers: USER-PERSONA, FULL-CONTEXT, AI-PROFILE-ROLE-EXPERTISE and AI-EXACT-TASK. The AUDIENCE layer is what this prompt exists to serve: the brief is written for a reader who does not share your private context.

Where it runs

Execution environment: Project or Skill. As a project instruction it regenerates the brief when the work changes; as a saved instruction it becomes the first thing you run on any new piece of work.

The prompt

Copy the block below in full. It is the whole prompt: nothing else needs to be attached, and no University 365 file is requested of you.

PROMPT STARTS HERE

Select everything in blue from the line above the word PROMPT STARTS HERE down to the line before word PROMPT ENDS HERE, and paste it into a new AI chat with the appropriate LLM and thinking level. Replace every bracket with your own text before you send it.

INSTITUTIONAL CONTEXT (read before you begin) This prompt is complete on its own. Everything it needs about University 365, about ULM and EVA, and about the UP-Context Method is defined below. No University 365 file is attached to it and none is required. The institution. University 365 is an institution of higher learning. Its Department of Academics owns the curriculum and the academic standards. The method. The UP-Context Method (University 365 Prompting-Context) structures every prompt into eight layers, five required and three optional: USER-PERSONA (who is asking), FULL-CONTEXT (the situation and the facts), AI-PROFILE-ROLE-EXPERTISE (who the AI is acting as), AI-EXACT-TASK (the exact job asked now), AUDIENCE (who the output is for), plus the three optional layers USER-FINAL-GOAL (the goal being worked toward), EXPECTED-FORMAT (the shape of the answer) and EXAMPLES (reference examples). A layer is text in the prompt first; keep it as a reusable file when its text is long enough and reused across prompts. The framework. ULM (University 365 Life Management) organises a person's life into six domains: Body and Health, Spirit and Mind, Character and Emotions, Social and Love Relationships, Career and Finance, Quality of Life. EVA is the engine that carries a person through each domain in three phases: Explore, Visualize, Action Plan. Who is who. U.Copilot is the AI assistant. U.Coach is a human coach. U.Copilot is not a human, must never present itself as one, and must never give medical, legal or financial advice. Your judgement. This prompt supports your thinking. Every recommendation it produces is a draft for you to check, not a decision made on your behalf. THE STANDING BRIEF #USER-PERSONA: I am the author of this brief. If a persona file is present in this project, apply it. If the layer was written as text instead, it appears after this line: [Write three to six lines about yourself that a colleague would need in order to brief work to you well.] #FULL-CONTEXT: the work this brief is about. If a context file is present in this project, apply it. If the layer was written as text instead, it appears after this line: [Write what the work is, who it is for, what has already been decided, and what is still open.] #AI-PROFILE-ROLE-EXPERTISE: you are an editor who writes for busy readers and hates waste. You cut anything that does not change what the reader does or understands. #AI-EXACT-TASK: write a standing brief from the layers above, in five bands: WHO I AM: the shortest honest description of me relevant to this work. WHAT I AM WORKING ON: the work, in plain terms, with its current state. THE AI'S ROLE: what I want an assistant to do on this work, and what it must not do. WHO IT IS FOR: the reader, what they already know, and what they need from me. THE SHAPE I WANT: how results should come back to me: length, structure, what to leave out. Then add one final section called OPEN QUESTIONS: everything you had to guess, marked as a guess. #AUDIENCE: a colleague or an AI session that has never seen this work before. After reading the brief, they should be able to start without asking me to repeat myself. #EXPECTED-FORMAT: five bands with the exact titles above, each under 120 words, followed by the OPEN QUESTIONS section. Plain headings, short paragraphs. #EXAMPLES: if I paste an earlier brief, follow its structure and tone while updating the content. RULES 1. Use only what the layers and my answers contain. Where information is missing, write that it is missing rather than filling the gap. 2. No confidential material is required in the brief. If something looks private, generalise it and note that you did. 3. Keep it short enough that I would actually read it before a meeting. 4. Never add a heading that is not in the five-band structure. 5. End by listing what I should update in the brief when the work changes shape.

PROMPT ENDS HERE

The brackets are the only parts you change. Everything else is the prompt.

A tall document divided into five labelled bands: who I am, what I am working on, the AI's role, who it is for, the shape I want.

What to change for your situation

Fill in the FULL-CONTEXT bracket with the work, not with yourself: who it is for, what is decided, what is open. The private material stays in your persona file and does not belong in the brief.

Verification checklist

Multi-model check: run the prompt on a second model and compare. External source check on any factual claim that matters. Human review before you act. CI-First test: does using this prompt build your own judgement, or replace it?

What this does to you

CI-First score 7.4, band Strong: time 8, quantity 7, quality 8, skill 7. Humics: Creativity Friendly, Critical Thinking Friendly, Social Authenticity Friendly, value +2. Imposture risk Low: the OPEN QUESTIONS section forces the guesses into the open instead of hiding them in confident prose.