Skip to main content
Prompts Pivot High-Stakes Decision Support Builder

developer planning developer risk: low

Pivot High-Stakes Decision Support Builder

Instructs building a web app called 'Pivot', a structured tool for major life and business decisions, with features including decision intake, mandatory clarifying questions via LL…

PROMPT 

Build a high-stakes decision support system called "Pivot" — a structured thinking tool for major life and business decisions.
This is distinct from a simple pros/cons list. The value is in the structured analytical process, not the output document.
Core features:
- Decision intake: user describes the decision (what they're choosing between), their constraints (time, money, relationships, obligations), their stated values (top 3), their current leaning, and their deadline
- Mandatory clarifying questions: [LLM API] generates 5 questions designed to surface hidden assumptions and unstated trade-offs in the user's specific decision. User must answer all 5 before proceeding. The quality of these questions is the quality of the product
- Six analytical frames (each run as a separate API call, shown in tabs):
  (1) Expected value — probability-weighted outcomes under each option  (2) Regret minimization — which option you're least likely to regret at age 80  (3) Values coherence — which option is most consistent with stated values, with specific evidence  (4) Reversibility index — how easily each option can be undone if it's wrong  (5) Second-order effects — what follows from each option in 6 months and 3 years  (6) Advice to a friend — if a trusted friend described this exact situation, what would you tell them?
- Devil's advocate brief: a separate analysis arguing as strongly as possible against the user's current leaning — shown after the 6 frames
- Decision record: stored with all analysis and the final decision made. User updates with actual outcome at 90 days and 1 year

Stack: React, [LLM API] with one carefully crafted prompt per analytical frame, localStorage. Focused, serious design — no gamification, no encouragement. This handles real decisions.

EXPECTED OUTPUT

Format
code
Constraints
  • React app
  • localStorage
  • LLM API integration
  • tabs for analytical frames

SUCCESS CRITERIA

  • Implement decision intake with constraints values leaning and deadline
  • Generate 5 mandatory clarifying questions
  • Provide six analytical frames as separate API calls in tabs
  • Include devil's advocate brief
  • Store decision record with outcomes
  • Use React LLM API and localStorage stack

FAILURE MODES

  • Simplifying to pros/cons list
  • Generating low-quality clarifying questions
  • Combining analytical frames into one call
  • Adding gamification or encouragement
  • Failing to separate frames into tabs

CAVEATS

Dependencies
  • LLM API
  • React
  • localStorage
Missing context
  • Specific LLM provider (e.g., OpenAI, Anthropic) and model.
  • Detailed React component hierarchy or wireframes.
  • Handling of multiple decisions in localStorage.
  • Form validation and user flow for answering clarifying questions.
Ambiguities
  • [LLM API] is an undefined placeholder.
  • Exact prompts for the six analytical frames and devil's advocate are not provided.
  • UI implementation details for tabs and forms are vague.

QUALITY

OVERALL
0.75
CLARITY
0.95
SPECIFICITY
0.90
REUSABILITY
0.20
COMPLETENESS
0.85

IMPROVEMENT SUGGESTIONS

  • Replace [LLM API] with a specific service like 'OpenAI GPT-4o' and provide API key handling instructions.
  • Include example prompts for each of the six analytical frames and the devil's advocate.
  • Add a section with UI mockups or detailed descriptions of screens (e.g., intake form fields, tab layout).
  • Specify data schema for localStorage decision records and update mechanisms.

USAGE

Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.

MORE FOR DEVELOPER