/decision-tree-explorer

Decision Tree Explorer

Explore decision branches with probability weighting, expected value analysis, and scenario-based optimization.

Instructions

You are tasked with creating a comprehensive decision tree analysis to explore complex decision scenarios and optimize choice outcomes. Follow this systematic approach: **$ARGUMENTS**

1. Prerequisites Assessment

**Critical Decision Context Validation:**

• **Decision Scope**: What specific decision(s) need to be made?
• **Stakeholders**: Who will be affected by and involved in this decision?
• **Time Constraints**: What are the decision deadlines and implementation timelines?
• **Success Criteria**: How will you measure decision success or failure?
• **Resource Constraints**: What limitations affect available options?

**If any context is unclear, guide systematically:**

Missing Decision Scope:
"I need clarity on the decision you're analyzing. Please specify:
- Primary Decision: The main choice you need to make
- Decision Level: Strategic, tactical, or operational
- Decision Type: Go/no-go, resource allocation, priority ranking, or option selection
- Alternative Options: What choices are you considering?

Examples:
- Strategic: 'Should we enter the European market next year?'
- Investment: 'Which of 3 product features should we build first?'
- Operational: 'Should we migrate to microservices or improve the monolith?'
- Crisis: 'How should we respond to the new competitor launch?'"

Missing Success Criteria:
"How will you evaluate if this decision was successful?
- Financial Metrics: Revenue impact, cost savings, ROI targets
- Strategic Metrics: Market share, competitive position, capability building
- Operational Metrics: Efficiency gains, quality improvements, risk reduction
- Timeline Metrics: Speed to market, implementation time, payback period"

Missing Resource Context:
"What constraints limit your decision options?
- Budget: Available investment capital and operating funds
- Time: Implementation deadlines and resource availability windows
- Capabilities: Team skills, technology infrastructure, operational capacity
- Regulatory: Compliance requirements and approval processes"

2. Decision Architecture Mapping

**Structure the decision systematically:**

Decision Hierarchy

• Primary decision point and core question
• Secondary decisions that follow from primary choice
• Tertiary decisions and implementation details
• Decision dependencies and sequencing requirements
• Option combinations and interaction effects

Stakeholder Impact Analysis

• Decision makers and approval authorities
• Implementation teams and resource owners
• Customers and end users affected
• External partners and dependencies
• Competitive landscape implications

Constraint Identification

• Hard constraints (cannot be violated)
• Soft constraints (preferences and trade-offs)
• Temporal constraints (timing and sequencing)
• Resource constraints (budget, capacity, capabilities)
• Regulatory and compliance constraints

3. Option Generation and Structuring

**Systematically identify and organize decision alternatives:**

Comprehensive Option Development

• Direct approaches to achieving the goal
• Hybrid solutions combining multiple approaches
• Phased approaches with incremental implementation
• Alternative goals that might better serve needs
• "Do nothing" baseline for comparison

Option Categorization

• Quick wins vs. long-term strategic moves
• High-risk/high-reward vs. safe/incremental options
• Resource-intensive vs. lean approaches
• Internal development vs. external partnerships
• Proven approaches vs. innovative experiments

Option Feasibility Assessment

For each option, evaluate:
- Technical Feasibility: Can this actually be implemented?
- Economic Feasibility: Do benefits justify costs?
- Operational Feasibility: Do we have capability to execute?
- Timeline Feasibility: Can this be done in available time?
- Political Feasibility: Will stakeholders support this?

Feasibility Scoring (1-10 scale):
Option: [name]
- Technical: [score] - [reasoning]
- Economic: [score] - [reasoning]
- Operational: [score] - [reasoning]
- Timeline: [score] - [reasoning]
- Political: [score] - [reasoning]
Overall Feasibility: [average score]

4. Probability Assessment Framework

**Apply systematic probability estimation:**

Base Rate Analysis

• Historical success rates for similar decisions
• Industry benchmarks and comparative data
• Expert judgment and domain knowledge
• Market research and customer validation data
• Internal capability assessment and track record

Scenario Probability Weighting

• Best case scenario probabilities (optimistic outcomes)
• Most likely scenario probabilities (base case expectations)
• Worst case scenario probabilities (pessimistic outcomes)
• Black swan event probabilities (extreme scenarios)
• Competitive response probabilities

Probability Calibration Methods

Use multiple estimation approaches:

1. Historical Data Analysis:
   - Similar past decisions and outcomes
   - Success/failure rates in comparable situations
   - Market adoption patterns for similar offerings

2. Expert Consultation:
   - Domain expert probability estimates
   - Cross-functional team input and perspectives
   - External advisor and consultant insights

3. Market Validation:
   - Customer research and feedback
   - Competitive analysis and market dynamics
   - Regulatory and environmental factor assessment

4. Monte Carlo Simulation:
   - Run multiple probability scenarios
   - Test sensitivity to assumption changes
   - Generate confidence intervals for estimates

5. Expected Value Calculation

**Quantify decision outcomes systematically:**

Outcome Quantification

• Financial returns and cost implications
• Strategic value and competitive advantages
• Risk reduction and option value creation
• Time savings and efficiency improvements
• Learning value and capability building

##