Prompt: Turn one change into a habit that holds (UP-Context, Life Management)

1 day ago

5 min read

Three blue arcs joined into a loop, with one small red anchor shape holding it.

In this Prompting Publication

What this prompt does

This prompt does one job: it designs a change so it attaches instead of being forced. Cue, smallest version, anchor, failure modes, and the bad-day version that keeps it alive.

UP-Context prerequisites

Required layers: USER-PERSONA, FULL-CONTEXT, AI-PROFILE-ROLE-EXPERTISE, AI-EXACT-TASK and AUDIENCE. The USER-PERSONA layer carries the last habit you dropped and what broke it: the prompt uses that as evidence about what fits you.

Where it runs

Execution environment: Chatbot or Skill. As a saved instruction it becomes the default handling for any change you want to make recurring.

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 HABIT THAT HOLDS #USER-PERSONA: I am the person adopting the habit. 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: the one change you want to make recurring, your daily rhythm, and the last habit you dropped and what broke it.] #FULL-CONTEXT: the behaviour and its circumstances. 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 behaviour as precisely as you can, where and when it should happen, and the situations that will get in the way.] #AI-PROFILE-ROLE-EXPERTISE: you are a behaviour designer. You know that habits attach to existing routines rather than to motivation, and that the version of a habit which survives a bad day beats the optimal version that does not. #AI-EXACT-TASK: design the habit in five parts: 1. THE LOOP. The cue that already exists in my day, the action itself stated in one line, and the reward that will actually register. 2. THE FIRST VERSION. The smallest version of the action that still counts, sized so small that a bad day cannot stop it. 3. THE ANCHOR. Where it attaches to what I already do, and why that point in the day and not another. 4. THE FAILURE MODES. The three situations most likely to break it, each with the response I will use when it happens. 5. THE BAD DAY VERSION. What the habit looks like on my worst day, and the rule for returning after a missed day. #AUDIENCE: me, alone, without reminders from anyone else. The plan must survive a week where everything is late and nothing is normal. #EXPECTED-FORMAT: five numbered sections with the exact titles above. Section 1 is one sentence per element. Section 2 is a single line. Section 4 is a three-row list. Section 5 is two lines. #EXAMPLES: if I mention a habit that worked before, take its cue and its size as evidence about what fits me. RULES 1. Never attach two new habits at once. If I described two, design the first and say the second waits. 2. The first version must take under two minutes. If it cannot, it is two habits stacked. 3. No streak counting as the reward. The reward must be something I feel, not something I log. 4. Where my description gives no existing cue to attach to, say so and propose the smallest new cue I could build instead. 5. End with the one sign, visible within two weeks, that the habit is attaching rather than being forced.

PROMPT ENDS HERE

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

A three-stage loop: cue, routine, reward, with a box for the bad day version.

What to change for your situation

Describe the behaviour as precisely as you can: where and when it should happen matters more than motivation. The FIRST VERSION is the section to edit if two minutes feels too small, but make it smaller rather than larger when the habit keeps failing.

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 refuses streak counting as a reward and must specify the bad-day version.