Prompt: Learn under a deadline (UP-Context, Learning)

1 day ago

5 min read

An abstract stack of blue slabs compressed toward the right, one red slab at the edge.

In this Prompting Publication

What this prompt does

This prompt does one job: it turns a fixed deadline and limited hours into a plan that can survive. It cuts the material first, plans backwards from the date, and protects the last two days for retrieval.

UP-Context prerequisites

Required layers: USER-PERSONA, FULL-CONTEXT, AI-PROFILE-ROLE-EXPERTISE, AI-EXACT-TASK and AUDIENCE. The USER-PERSONA layer carries your real available hours and your sleep: both are inputs, not constraints to negotiate later.

Where it runs

Execution environment: Project. Keep it in a project as the deadline approaches so the plan can be re-cut when a week goes wrong.

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 DEADLINE PLAN #USER-PERSONA: I am the person facing the deadline. 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 your situation: what the deadline is, what is being tested, and how many hours in total you can give it between now and then.] #FULL-CONTEXT: the material and the requirement. If a context file is present in this project, apply it. If the layer was written as text instead, it appears after this line: [List the material that could be examined, the format of the assessment, and the standard you are being held to.] #AI-PROFILE-ROLE-EXPERTISE: you are a study strategist who plans backwards from a fixed date. You know that a compressed plan fails at exactly one point, the moment it pretends everything can be covered, and you cut before you schedule. #AI-EXACT-TASK: build a plan from today to the deadline in four stages: 1. TRIAGE. Sort the material into three lists: MUST HOLD (cannot pass without it), SHOULD HOLD (likely to be assessed), and CAN DROP (nice to have). Be aggressive: when the hours do not fit the material, say so here, before planning anything. 2. BACKWARD PLAN. Working back from the deadline, the checkpoint dates and what must be solid by each one. The last two days are reserved for retrieval, never for new material. 3. DAILY SESSIONS. What each study day does: which list it serves, whether it is first-pass learning or retrieval, and how long it takes. No day longer than ninety minutes of study without a stated break. 4. CHECKPOINTS. What I do at each checkpoint to check I am on track, and the fallback that drops the CAN DROP list without touching the others. #AUDIENCE: me, under pressure, reading this once. The plan must fit on one page and be followable without an app. #EXPECTED-FORMAT: a dated list for the backward plan; a table for the daily sessions with columns DATE, LIST SERVED, ACTIVITY, LENGTH; checkpoints and the fallback as short lists. #EXAMPLES: if I paste a plan that failed before, use it to see which stage it skipped. RULES 1. Triage before planning. Never schedule material that has not been sorted. 2. Honest hours only. Use the hours I stated, not the hours a good week would have. 3. If the requirement cannot be met in the time, say so in the first paragraph and propose what the deadline realistically allows. 4. Protect sleep in the plan. A plan that trades sleep for sessions is a plan that removes its own capacity. 5. End with the one decision I must make today to start this plan.

PROMPT ENDS HERE

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

A four-stage flow: triage, backward plan, daily sessions, checkpoints, with triage outlined in red and marked cut before you start.

What to change for your situation

State the hours you truly have, not the hours a perfect week would have. When the requirement does not fit, let the prompt say so: the realistic version it proposes is worth more than a plan that collapses.

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 8.2, band Strong: time 9, quantity 6, quality 8, skill 8. Humics: Creativity Neutral, Critical Thinking Friendly, Social Authenticity Friendly, value +3. Imposture risk Low: triage is mandatory and the prompt must state plainly when the deadline cannot hold the material.