중대 의사결정 프레임워크

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.

중요한 인생 및 비즈니스 의사결정을 돕는 구조화된 사고 도구인 'Pivot' 시스템을 구축하세요.
단순한 장단점 목록과 다르게, 단순 출력물보다 구조화된 분석 절차에 가치를 둡니다.
주요 기능:
- 의사결정 입력: 선택지, 제약 조건(시간, 비용, 관계, 의무), 핵심 가치 3가지, 현재 기울어진 의견, 마감일 입력
- 필수 명확화 질문: 사용자가 가진 숨겨진 전제와 트레이드오프를 밝혀내는 5가지 핵심 질문 생성 및 사용자 답변 필수화
- 6가지 분석 프레임:
  (1) 기대 가치 - 각 옵션의 확률 가중 결과
  (2) 후회 최소화 - 80세가 되었을 때 가장 후회가 적을 선택
  (3) 가치 일관성 - 밝힌 가치와 가장 부합하는 선택지와 근거
  (4) 가역성 지수 - 잘못된 선택일 경우 얼마나 쉽게 되돌릴 수 있는지
  (5) 2차 파급 효과 - 6개월 및 3년 후 일어날 일들
  (6) 친구를 위한 조언 - 신뢰하는 친구가 동일한 상황일 때 해줄 조언
- 악마의 변호인 브리핑: 사용자의 현재 경향성에 대해 강력하게 반대하는 별도 분석 제공
- 의사결정 기록: 전체 분석과 최종 결정을 저장하고 90일, 1년 후 실제 결과를 업데이트하도록 구성

• 활용단순 질문 외에도 자신만의 핵심 가치 3가지를 명확히 전제하고 질문하면 더 정교한 분석이 가능합니다.
• 활용악마의 변호인 분석 단계를 통해 본인이 미처 보지 못한 맹점과 위험 요소를 발견해 보세요.

출처 · prompts.chat · High-Stakes Decision Support System — 원문은 출처에 게시된 그대로이며, 권리는 원작자에게 있습니다.

텍스트 결과

Gemini로 실행한 결과입니다. 입력 항목에는 국내 환경의 예시값을 적용했습니다(AI 생성 — 사실 확인 필요).

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: OpenAI API (GPT-4o) 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, OpenAI API (GPT-4o) with one carefully crafted prompt per analytical frame, localStorage. Focused, serious design — no gamification, no encouragement. This handles real decisions.

{
  "id": "dec_12345",
  "createdAt": "2024-05-20",
  "intake": { "options": [], "constraints": {}, "values": [], "leaning": "", "deadline": "" },
  "clarifyingQA": [{ "q": "", "a": "" }],
  "frames": { "expectedValue": "", "regretMin": "", "valuesCoherence": "", "reversibility": "", "secondOrder": "", "adviceToFriend": "" },
  "devilsAdvocate": "",
  "finalDecision": "",
  "reviews": { "day90": null, "year1": null }
}

개선안

원문과 같은 언어로 보완한 프롬프트입니다. 점수는 명확성 · 구체성 · 출력 형식 · 재사용성 기준의 AI 평가입니다.

Act as a Senior AI Architect. Build "Pivot", a structured high-stakes decision support system for major life and business decisions.

Stack: React, [LLM API], localStorage.
UI/Tone: Focused, serious, zero gamification. Value lies in the analytical process over superficial advice.

System Pipeline:
1. Decision Intake: Collect user options, constraints (time/money/obligations), top 3 values, current leaning, and deadline.
2. Clarifying Phase: Call [LLM API] to generate exactly 5 targeted questions uncovering hidden assumptions. User must answer all 5 before proceeding.
3. Six Analytical Frames (Execute as separate [LLM API] calls, shown in tabs):
   - Expected Value: Probability-weighted outcomes per option.
   - Regret Minimization: Long-term age-80 perspective.
   - Values Coherence: Alignment with top 3 values + specific evidence.
   - Reversibility Index: Reversibility score (1-10) and undo protocol.
   - Second-Order Effects: 6-month and 3-year indirect consequences.
   - Advice to a Friend: Objective third-person recommendation.
4. Devil's Advocate Brief: Generate a strong counter-argument challenging user's leaning post-frame analysis.
5. Decision Record: Save structured state to localStorage; schedule 90-day & 1-year outcome review prompts.

Output Requirement: Enforce strict JSON output format for each API call: {"frame_id": "...", "key_analysis": "...", "tradeoffs": [...], "score": 0}.