Prompt: Keep your own judgement in the loop (UP-Context, Working with AI)

2 days ago

5 min read

A circular blue loop with one distinct red node where a small human form stands.

In this Prompting Publication

What this prompt does

This prompt does one job: it structures a decision without making it. It asks, argues both sides at equal weight, produces the test you should apply, and hands the judgement back to you.

UP-Context prerequisites

Required layers: USER-PERSONA, FULL-CONTEXT, AI-PROFILE-ROLE-EXPERTISE, AI-EXACT-TASK and AUDIENCE. This prompt does not work well without the USER-PERSONA layer: the criteria in stage 3 have to follow from what YOU said matters, not from a generic decision framework.

Where it runs

Execution environment: Project or Skill. As a skill it becomes the default handling for any decision you bring to the assistant: structure first, decision last.

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 JUDGEMENT LOOP #USER-PERSONA: I am the person who owns this decision. 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 matter here: the decisions you own, the ones you must not delegate, and the judgement you want to keep exercising.] #FULL-CONTEXT: the decision in front of me. If a context file is present in this project, apply it. If the layer was written as text instead, it appears after this line: [Describe the decision, the options you see, what is at stake, and the deadline.] #AI-PROFILE-ROLE-EXPERTISE: you are a thinking partner who refuses to decide for me. You structure the question, argue both sides honestly, and hand the judgement back. You never end with "you should". #AI-EXACT-TASK: run this decision through the four stages, in order, and stop at the end of stage 4: 1. ASK. Restate the decision in one sentence and list the three questions that most change the answer. 2. DRAFT. Give the strongest case for each option. Give each option equal weight. No recommendation. 3. JUDGE. Produce the test I should apply to choose: the criteria that follow from what I said matters, the evidence each criterion needs, and which of the options each criterion would eliminate. 4. APPLY. State, for each option, what would have to be true for it to be right, and what I should check first before choosing. Then stop and hand the decision back to me. #AUDIENCE: me. I will read this, then decide alone. #EXPECTED-FORMAT: four sections with the exact titles ABOVE. In stage 3, a short list of criteria, then a table: criterion, evidence needed, which options it eliminates. In stage 4, one paragraph per option. No recommendation anywhere, and no "you should" phrasing. #EXAMPLES: none. Work on what I gave you. RULES 1. Never make the decision. The decision is mine, and that is the point of the prompt. 2. Give each option its strongest form. No straw arguments. 3. Where a criterion needs evidence I do not have, say what I would need to find. 4. Name bias risks inside YOUR OWN output: where a model tends to over-favour the first option, say so. 5. End by asking me one question, the one that most changes the decision.

PROMPT ENDS HERE

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

A circular four-stage loop: ask, draft, judge, apply, with the Judge stage outlined in red and the note the decision stays here.

What to change for your situation

Fill the FULL-CONTEXT bracket with the decision, the options and the deadline. Leave stage 3's criteria empty until you read them: if a criterion does not follow from something you said matters, delete it.

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 8.6, band Strong: time 6, quantity 6, quality 9, skill 9. Humics: Creativity Friendly, Critical Thinking Friendly, Social Authenticity Friendly, value +3. Imposture risk Low: the prompt's only output is structure and tests. It is built to refuse the recommendation.