Prompt: Diagnose why something is not sticking (UP-Context, Learning)

1 day ago

5 min read

An abstract channel in blue blocked at one point by a single compact red form.

In this Prompting Publication

What this prompt does

This prompt does one job: it finds out why your learning has stalled. It scores the five usual causes against your situation, names the one most likely responsible, and gives you a test that would prove it wrong.

UP-Context prerequisites

Required layers: USER-PERSONA, FULL-CONTEXT, AI-PROFILE-ROLE-EXPERTISE and AI-EXACT-TASK. The FULL-CONTEXT layer carries your actual routine: the prompt diagnoses what you do, not what you intend to do, so an honest description of a real week decides whether the verdict is worth anything.

Where it runs

Execution environment: Chatbot. Run it when progress stops, not on a schedule. It is the prompt to reach for before any increase in effort.

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 STALL DIAGNOSTIC #USER-PERSONA: I am the person who is stuck. 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 as a learner: what you are trying to learn, how you have been studying it, and for how long it has felt stuck.] #FULL-CONTEXT: what I have actually been doing. 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 your current routine in plain terms: how often you study, what you do in a session, whether you test yourself, and when you saw the last real improvement.] #AI-PROFILE-ROLE-EXPERTISE: you are a learning diagnostician. You know the five usual causes of a stall, and you do not accept "I need to study more" as a cause. Effort is the one thing the person has already tried. #AI-EXACT-TASK: diagnose why my learning has stalled, in four parts: 1. THE SUSPECTS. Score each of the five usual causes from 1 to 5 for my situation, and give the one observable sign that pointed to each score: ENCODING (I never understood it in the first place), RETRIEVAL (I reread instead of recalling), SPACING (I never revisited it), PRACTICE TYPE (I practise the easy kind instead of the kind the goal asks for), REST (I never consolidated it). 2. THE VERDICT. Name the ONE cause most likely responsible, and say plainly why it beats the others in my case. 3. THE TEST. One experiment I can run this week that would prove or disprove your verdict, with the result that would mean you were wrong. 4. THE CHANGE. The single change to my routine that follows from the verdict, stated so precisely that I could do it tomorrow. #AUDIENCE: me, discouraged and short of time. Do not tell me to work harder. Tell me what to do differently. #EXPECTED-FORMAT: four numbered sections with the exact titles above. Section 1 is a five-row list, one per cause, with the score and the sign. Sections 2 and 4 are short paragraphs. Section 3 is three lines: the experiment, what I do, what it would show. #EXAMPLES: if I describe a past stall that turned out to be a different cause, treat it as evidence about my habits, not as a template. RULES 1. Rank effort last as an explanation. If the other four causes do not fit, say so before falling back on it. 2. Where my description does not contain the evidence for a verdict, ask the one question that would settle it. 3. Never recommend a change that costs more time than my current routine. The fix must be a different activity, not a bigger one. 4. If the goal itself is unclear, say that no diagnosis is possible until the goal is named, and stop. 5. End with the one sign that will tell me, in two weeks, whether this diagnosis was right.

PROMPT ENDS HERE

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

Five boxes: encoding, retrieval, spacing, practice type, rest, with retrieval outlined in red and marked start here.

What to change for your situation

Describe the last two weeks honestly, including what you skipped. The verdict is only as good as that description. If you have been stuck before and found out why, say so: it steers the ranking.

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 8.3, band Strong: time 8, quantity 6, quality 9, skill 9. Humics: Creativity Neutral, Critical Thinking Friendly, Social Authenticity Friendly, value +3. Imposture risk Low: the prompt demands a falsifying test for its own verdict and refuses effort as an explanation.