Decision Framework Builder

The Prompt

You are a decision analyst and strategic advisor. Your job is to structure a complex choice into a clear, scored framework — not a generic pros-and-cons list, but a framework that surfaces the criteria that matter for this specific decision, scores each option honestly, and produces a defensible recommendation.

DECISION QUESTION: {{decision_question}}
OPTIONS: {{options}}
CONSTRAINTS: {{constraints}}
VALUES OR PRIORITIES: {{values_or_priorities}}

Return exactly:
1) Decision framing check
   - refined decision question
   - what is ambiguous or missing
2) Hard constraints vs preference criteria
   - separate pass/fail requirements from scored dimensions
3) Evaluation criteria
   - 5 to 8 criteria with short rationale
4) Scored options table
   - option
   - criterion scores
   - short note per option
   - flag any hard-constraint failure
5) Recommendation with confidence
   - recommendation
   - confidence level
   - what the table still does not capture
6) Key assumptions
   - assumptions the recommendation depends on
7) What would change the recommendation
   - 3 specific facts or events
8) Next steps to reduce uncertainty
   - 2 to 3 targeted actions

Rules:
- Do not invent options not listed in the `OPTIONS` block.
- If the inputs blur several decisions together, split them before scoring.
- If key information is missing, say so explicitly instead of pretending the scores are fully grounded.
- Separate empirical uncertainty from values disagreement.
- Give a recommendation even if the data is mixed; use confidence level to express uncertainty.
- Distinguish evidence-backed scores from judgment-based scores when the inputs are uneven.

When to Use

Use this prompt when a decision involves more than two meaningful criteria and a simple pros-and-cons list would obscure the tradeoffs. Most useful when decision-makers have partially different priorities or when options each excel on different dimensions.

Good for:

• Product roadmap prioritization and build vs. buy choices
• Technology or vendor selection
• Hiring decisions where candidates have different strengths
• Career moves with multiple competing factors
• Any decision where someone will later ask “how did we land here?”

Variables

Variable	Description	Examples
decision_question	The specific choice to be made, ideally one choice rather than several bundled together	”Which database should we use for the analytics pipeline?”, “Should we hire a contractor or full-time engineer?”
options	The real alternatives under consideration	”PostgreSQL, ClickHouse, BigQuery”, “Contractor via agency / Full-time hire / Extend current engineer’s scope”
constraints	Hard limits any valid option must satisfy	”Must be under $2k/month, must integrate with our Kubernetes setup, production-ready in 6 weeks”
values_or_priorities	What matters most to the decision-makers and where tradeoffs should lean	”We prioritize long-term maintainability over short-term speed. Cost is a concern but not the primary driver.”

Tips & Variations

• Include the status quo as an option whenever “keep current approach” is a real choice. Otherwise the model may recommend change too easily.
• Put true hard constraints in constraints, not in values_or_priorities. Mixing them blurs pass/fail rules with preferences.
• If the first output feels shallow, the usual fix is better options or clearer constraints, not asking for “more analysis.”
• For team alignment, run the same prompt with different stakeholder values and compare where the recommendation changes.
• If the decision is high stakes, ask for one extra table that lists which criteria are strongly evidenced and which are still mostly assumption-driven.

Example Output

Decision framing check: The original question bundles provider choice and data-warehouse choice. Score the infrastructure decision first, then the warehouse decision separately if needed.

Recommendation: Choose AWS with medium confidence because team familiarity and delivery speed outweigh the lock-in cost under the current 6-week constraint.

What would change it: A revised cost ceiling, stronger portability requirement, or an extra month of delivery time.