True Potential Council — Detailed Prompts & Scoring

Task(subagent_type="general-purpose", prompt="""
Use council-orchestrator to run True Potential Council review:

Company: {company_name}
Prior Analysis: {phase_2_analysis_results}

=== COUNCIL MEMBER 1: DEFENSIBILITY JUDGE (Weight: 0.35) ===

Assess moat depth and durability by answering:

1. PRIMARY MOAT TYPE: What is the company's primary defensibility mechanism?
   - Network Effects (direct, indirect, data network)
   - Switching Costs (technical, workflow, data lock-in)
   - Scale Economies (cost advantages, supply side)
   - Brand/Trust (reputation, certification, compliance)
   - Proprietary Technology (patents, trade secrets, unique algorithms)

2. REPLICATION TIMELINE: How long would it take a well-funded competitor to replicate?
   - <6 months = No moat
   - 6-18 months = Weak moat
   - 18-36 months = Moderate moat
   - 36+ months = Strong moat

3. COMPOUNDING ADVANTAGE: Does the moat strengthen over time?
   - Each customer makes product better? (data flywheel)
   - Each year of operation increases barrier? (regulatory, network)
   - Does usage create lock-in? (workflow dependency)

4. PROPRIETARY ASSETS: What unique assets does the company own?
   - Unique data sets
   - Exclusive partnerships
   - Regulatory approvals
   - Patent portfolio

5. UNBUNDLING RISK: Can a focused competitor attack one vertical?
   - Is the product a bundle that can be picked apart?
   - Are there vulnerable features that are "good enough" to unbundle?

DEFENSIBILITY SCORING:
- 5 = Multi-layered moat (2+ strong mechanisms, compounding)
- 4 = Strong single moat (one dominant, durable mechanism)
- 3 = Moderate moat (one mechanism, moderate durability)
- 2 = Weak moat (replicable within 12 months)
- 1 = No moat (commodity, easily replicated)

=== COUNCIL MEMBER 2: MARKET VELOCITY JUDGE (Weight: 0.35) ===

Assess market timing and momentum by answering:

1. SECULAR TAILWINDS: What macro trends accelerate adoption?
   - Regulatory changes (mandates, compliance requirements)
   - Demographic shifts (aging, remote work, urbanization)
   - Technology shifts (AI, cloud, mobile penetration)
   - Economic shifts (cost pressures, labor shortages)

2. POTENTIAL HEADWINDS: What could slow or reverse momentum?
   - Regulatory backlash
   - Economic downturn sensitivity
   - Technology platform risk
   - Market consolidation

3. BUYER BEHAVIOR SHIFTS: Is the target buyer actively changing?
   - Are budgets shifting to this category?
   - Is there urgency to adopt?
   - What triggers the buying decision?

4. ADOPTION CURVE POSITION: Where is the market?
   - Innovators (<2.5%) = High risk, high upside
   - Early Adopters (2.5-16%) = Optimal timing
   - Early Majority (16-50%) = Competition entering
   - Late Majority (50-84%) = Commoditization risk

5. VELOCITY BENCHMARKS: Compare to similar markets
   - How fast did comparable solutions scale?
   - What's the realistic adoption timeline?

MARKET VELOCITY SCORING:
- 5 = Strong tailwinds + optimal timing (early adopter phase, multiple tailwinds)
- 4 = Clear tailwinds (single strong tailwind, good timing)
- 3 = Mixed signals (tailwinds present but headwinds exist)
- 2 = Headwinds present (timing challenges, market friction)
- 1 = Poor timing (late to market or premature)

=== COUNCIL MEMBER 3: EXPANSION JUDGE (Weight: 0.30) ===

Assess wedge-to-platform potential by answering:

1. INITIAL WEDGE CLARITY: How focused is the entry point?
   - Is there a clear, narrow problem being solved?
   - Is the wedge defensible on its own?
   - Can they win the wedge before expanding?

2. ADJACENT PROBLEMS: What natural expansions exist?
   - What other problems does the customer have?
   - What data/relationships enable new products?
   - What's the logical next product?

3. EXPANSION LEVERAGE: What assets transfer to expansion?
   - Customer relationships
   - Data assets
   - Distribution channels
   - Technical infrastructure
   - Brand/trust

4. TAM EXPANSION MATH: Quantify the expansion opportunity
   - Initial wedge TAM: $X
   - First expansion TAM: $Y
   - Full platform TAM: $Z
   - Timeline to each stage

5. TEAM EXPANSION CAPABILITY: Can this team execute expansion?
   - Have founders done multi-product before?
   - Is the org designed for expansion?
   - Do they have the capital for expansion?

WEDGE TYPE CLASSIFICATION:
- TROJAN HORSE: Small wedge enables massive platform (e.g., Slack chat -> enterprise suite)
- NATURAL EXPANSION: Wedge has clear, logical adjacencies (e.g., payroll -> HR suite)
- FORCED EXPANSION: Wedge maxes out, must pivot (risky)
- WEDGE TRAP: Wedge is the whole business (no expansion path)

EXPANSION SCORING:
- 5 = Clear platform play (Trojan Horse, 10x TAM expansion path)
- 4 = Strong expansion path (Natural Expansion, 3-5x TAM)
- 3 = 1-2 adjacencies visible (moderate expansion potential)
- 2 = Unclear expansion (forced expansion likely)
- 1 = Wedge trap (no clear path beyond initial market)

=== TRUE POTENTIAL SCORE CALCULATION ===

TPS = ((D x 0.35) + (V x 0.35) + (E x 0.30)) x Alignment Multiplier

Where:
- D = Defensibility Score (1-5)
- V = Market Velocity Score (1-5)
- E = Expansion Score (1-5)

Alignment Multiplier:
- All judges within 1 point of each other: 1.1x (high confidence)
- Two judges align, one diverges: 1.0x (moderate confidence)
- All judges diverge (>1 point spread): 0.9x (low confidence, needs investigation)

=== OUTPUT FORMAT ===

TRUE POTENTIAL ASSESSMENT:
|- Defensibility: [Score]/5 - [Key Finding]
|- Market Velocity: [Score]/5 - [Key Finding]
|- Expansion: [Score]/5 - [Key Finding]
|- Alignment: [High/Moderate/Low]
|- TRUE POTENTIAL SCORE: [X.X]/5
|- Wedge Classification: [Type]

TAM CALIBRATION:
|- Stated TAM: $[X]B
|- True Potential Adjustment: [Multiplier]
|- Calibrated TAM: $[Y]B
|- Interpretation: [High+High / High+Low / Low+High / Low+Low]
""")