Due Diligence Report Format

All specialist agents must output their analysis in this standardized JSON format. This enables automated synthesis by the Deal Lead agent.

Standard Report Structure

{
  "metadata": {
    "agent": "dd-{specialist}",
    "company": "Company Name",
    "analysis_date": "2024-01-15T10:30:00Z",
    "version": "1.0"
  },

  "executive_summary": {
    "headline": "One-sentence assessment",
    "recommendation": "POSITIVE | NEUTRAL | NEGATIVE | CRITICAL",
    "confidence": "HIGH | MEDIUM | LOW",
    "key_findings": [
      "Finding 1",
      "Finding 2",
      "Finding 3"
    ]
  },

  "risk_assessment": {
    "overall_score": 35,
    "category_scores": {
      "category_name": {
        "score": 30,
        "weight": 0.25,
        "rationale": "Brief explanation"
      }
    },
    "red_flags": [
      {
        "severity": "HIGH | MEDIUM | LOW",
        "description": "Description of the red flag",
        "evidence": "Supporting evidence",
        "mitigation": "Possible mitigation or none"
      }
    ],
    "green_flags": [
      {
        "description": "Positive indicator",
        "evidence": "Supporting evidence"
      }
    ]
  },

  "detailed_analysis": {
    "section_name": {
      "findings": "Detailed analysis text",
      "data": {},
      "sources": ["S1", "S2"]
    }
  },

  "sources": [
    {
      "id": "S1",
      "name": "Source name",
      "url": "URL",
      "tier": 1,
      "access_date": "2024-01-15"
    }
  ],

  "verification_summary": {
    "total_claims": 15,
    "verified": 10,
    "partially_verified": 3,
    "unverified": 1,
    "contradicted": 1
  },

  "follow_up_items": [
    {
      "priority": "HIGH | MEDIUM | LOW",
      "description": "Item requiring further investigation",
      "assigned_to": "dd-{specialist} or HUMAN"
    }
  ]
}

Risk Scoring

Use a 0-100 scale where:

• 0-20: Minimal risk (green light)
• 21-35: Low risk (proceed with standard diligence)
• 36-50: Moderate risk (proceed with caution)
• 51-70: High risk (significant concerns)
• 71-100: Critical risk (major red flags)

File Naming Convention

Save your report to the shared folder as:

/shared-out/{your-domain}-analysis/{company_name}_{date}.json

Example:

/shared-out/founder-analysis/acme_corp_2024-01-15.json

Markdown Summary

In addition to JSON, create a human-readable summary:

/shared-out/{your-domain}-analysis/{company_name}_{date}_summary.md

This should include:

• Executive summary (2-3 paragraphs)
• Key findings (bullet points)
• Risk assessment visualization
• Recommended actions

Risk Scoring Methodology

As the Deal Lead, you synthesize reports from 9 specialist agents into a single investment risk score. This methodology ensures consistent, defensible scoring.

Scoring Weights

Total: 100%

Calculation Formula

Overall Risk Score = Σ (specialist_score × weight)

Example:

Founder: 25 × 0.20 = 5.0
Tech:    40 × 0.15 = 6.0
BizModel: 30 × 0.15 = 4.5
Traction: 35 × 0.15 = 5.25
Market:   20 × 0.15 = 3.0
Competitor: 45 × 0.10 = 4.5
Compliance: 15 × 0.05 = 0.75
CapTable:  25 × 0.03 = 0.75
Legal:     30 × 0.02 = 0.6
--------------------------------
Overall Risk Score: 30.35

Risk Score Interpretation

Adjustment Factors

Apply these modifiers to the calculated score:

Positive Adjustments (reduce score)

• Repeat founder with successful exit: -5
• Strategic fit with portfolio: -3
• Strong reference checks: -2
• Clear competitive moat: -3

Negative Adjustments (increase score)

• Missing key team member: +5
• Unverified core claims: +10
• Regulatory uncertainty: +5
• Customer concentration >50%: +5
• Burn rate concern: +3

Output Format

{
  "risk_scoring": {
    "weighted_scores": {
      "founder": {"raw": 25, "weight": 0.20, "weighted": 5.0},
      "tech": {"raw": 40, "weight": 0.15, "weighted": 6.0}
    },
    "base_score": 30.35,
    "adjustments": [
      {"factor": "Repeat founder with exit", "adjustment": -5}
    ],
    "final_score": 25.35,
    "rating": "Invest",
    "recommendation": "Proceed with investment, standard terms"
  }
}

Red Flag Escalation

If ANY specialist reports a score >80 in their domain, flag for manual review regardless of overall score. Single-domain critical risks can be deal-breakers.

Source Documentation Standards

All due diligence findings must be traceable to their sources. This enables audit trails, follow-up verification, and legal defensibility.

Source Quality Tiers

Tier 1: Primary Sources (Highest Credibility)

• SEC filings (10-K, 10-Q, S-1)
• Court documents and legal filings
• Government databases (USPTO, state registrations)
• Company's own audited financials
• Direct customer/reference interviews

Tier 2: Secondary Sources (High Credibility)

• Established data providers (Crunchbase, PitchBook, CB Insights)
• Major news outlets (WSJ, Bloomberg, TechCrunch)
• Industry analyst reports (Gartner, Forrester)
• LinkedIn profiles (for employment verification)
• Academic research and papers

Tier 3: Tertiary Sources (Use with Caution)

• Social media posts
• Blog articles
• Glassdoor reviews
• Wikipedia (only as starting point)
• Forum discussions

Citation Format

Every fact must include a source citation:

{
  "source": {
    "name": "Full source name",
    "type": "SEC_FILING | NEWS | DATA_PROVIDER | INTERVIEW | GOVERNMENT | OTHER",
    "url": "https://... (if available)",
    "access_date": "2024-01-15",
    "publication_date": "2024-01-10",
    "tier": 1,
    "excerpt": "Relevant quote or data point"
  }
}

Best Practices

DO:

• Capture URLs at time of access (pages change/disappear)
• Note the access date for all web sources
• Quote relevant passages, don't just link
• Use multiple sources for critical claims
• Prefer recent sources over older ones

DON'T:

• Cite a source you haven't actually reviewed
• Use company press releases as independent verification
• Rely on a single source for material claims
• Cite sources behind paywalls without noting limitation
• Mix up "stated by company" vs "independently verified"

Source Tracking in Output

Include a sources section in every analysis:

{
  "sources_used": [
    {
      "id": "S1",
      "name": "Crunchbase - Acme Corp Profile",
      "url": "https://crunchbase.com/...",
      "access_date": "2024-01-15",
      "tier": 2,
      "used_for": ["funding_history", "employee_count"]
    }
  ],
  "source_statistics": {
    "tier_1": 3,
    "tier_2": 8,
    "tier_3": 2,
    "total": 13
  }
}

Handling Source Conflicts

When sources disagree:

1. Note the discrepancy explicitly
2. Prefer higher-tier sources
3. Prefer more recent sources
4. Document both versions with reasoning for which to trust

Multi-Source Synthesis Methodology

As the Deal Lead, you must synthesize reports from 9 specialist agents into a coherent narrative and investment recommendation.

Synthesis Process

Step 1: Gather All Reports

Collect reports from shared folders:

/shared-out/founder-analysis/
/shared-out/market-analysis/
/shared-out/competitor-analysis/
/shared-out/tech-analysis/
/shared-out/bizmodel-analysis/
/shared-out/traction-analysis/
/shared-out/compliance-analysis/
/shared-out/captable-analysis/
/shared-out/legal-analysis/

Step 2: Extract Key Findings

From each report, extract:

• Executive summary headline
• Risk score and top 3 concerns
• Top 3 positive indicators
• Any CRITICAL or HIGH severity red flags
• Unverified claims

Step 3: Identify Patterns

Look for themes across reports:

Corroborating Evidence When multiple specialists cite the same positive or negative:

• Strong team: Founder + Tech + Traction all positive
• Market concern: Market + Competitor + BizModel all flag saturation

Contradictions When specialists disagree:

• Founder says $5M ARR, Traction finds $3M evidence
• Tech says "novel IP", Legal finds prior art

Gaps What wasn't adequately analyzed:

• Missing international market analysis
• No direct customer interviews conducted

Step 4: Build the Narrative

Structure your synthesis as:

1. The Opportunity (1 paragraph)

   • What makes this company interesting
   • Market timing and positioning

2. The Team (1 paragraph)

   • Key strengths and gaps
   • Track record and references

3. The Risk Profile (2-3 paragraphs)

   • Material risks with evidence
   • Mitigating factors
   • Unresolved questions

4. The Recommendation (1 paragraph)

   • Clear INVEST/PASS/NEGOTIATE stance
   • Conditions or terms if applicable

Output Documents

1. Investment Recommendation (JSON)

{
  "recommendation": {
    "decision": "INVEST | NEGOTIATE | PASS",
    "confidence": "HIGH | MEDIUM | LOW",
    "conditions": ["condition 1", "condition 2"],
    "suggested_terms": {
      "valuation_range": "$X-$Y",
      "check_size": "$Z",
      "special_terms": ["board seat", "pro-rata rights"]
    }
  },
  "synthesis": {
    "opportunity_thesis": "Why this could be a great investment",
    "primary_risks": ["risk 1", "risk 2", "risk 3"],
    "mitigating_factors": ["factor 1", "factor 2"],
    "open_questions": ["question 1", "question 2"]
  },
  "specialist_summary": {
    "founder": {"score": 25, "headline": "..."},
    "market": {"score": 30, "headline": "..."}
  },
  "overall_risk_score": 28.5
}

2. IC Briefing (Markdown)

Human-readable document for Investment Committee:

• 2-page executive summary
• Risk/reward matrix
• Comparable investments
• Recommended next steps

Save as: /shared-out/investment-recommendation/ic_briefing.md

Handling Incomplete Data

If any specialist report is missing or incomplete:

1. Note the gap explicitly in your synthesis
2. Adjust confidence level downward
3. Flag as follow-up item
4. Do NOT extrapolate missing analysis

Quality Checklist

Before finalizing your recommendation:

• All 9 specialist reports reviewed
• Risk score calculated with documented weights
• Contradictions identified and resolved
• Unverified claims flagged
• Conditions clearly stated
• Next steps defined

Claim Verification Methodology

When analyzing claims from pitch decks, founder statements, or company materials, follow this rigorous verification process.

Verification Levels

Assign one of these confidence levels to every claim:

Verification Process

1. Identify the Claim

Extract the specific, testable assertion:

• ❌ "We're growing fast" (vague)
• ✅ "We grew 300% YoY in 2024" (specific, testable)

2. Find Independent Sources

Never rely solely on company-provided materials. Seek:

• Public filings (SEC, state records)
• Third-party data providers (Crunchbase, PitchBook, LinkedIn)
• Press coverage (with dates)
• Customer reviews and testimonials
• Industry reports from analysts

3. Cross-Reference

Compare across sources:

• Do numbers align within reasonable variance (±10%)?
• Are timelines consistent?
• Do different sources tell the same story?

4. Document Everything

For each verified claim, record:

{
  "claim": "The specific claim text",
  "confidence": "VERIFIED | PARTIALLY VERIFIED | UNVERIFIED | CONTRADICTED",
  "sources": [
    {"name": "Source name", "url": "URL if available", "date": "YYYY-MM-DD"}
  ],
  "notes": "Any caveats or context"
}

Red Flags

Watch for these warning signs:

• Round numbers without context ("$10M ARR exactly")
• Claims that can't be independently verified
• Metrics that don't match industry standards
• Vague timeframes ("recently", "soon")
• Comparisons without clear methodology

Output Format

Include a verification summary in your analysis:

{
  "verification_summary": {
    "total_claims_analyzed": 15,
    "verified": 8,
    "partially_verified": 4,
    "unverified": 2,
    "contradicted": 1
  },
  "key_concerns": [
    "Market size claim contradicted by industry reports",
    "Founder employment dates don't match LinkedIn"
  ]
}