---
# === IDENTITY ===
id: signal-library/retail-assets/distress-dossier/2026
canonical_question: "What is the auto-generated dossier template for retailers showing operational distress signals?"
aliases:
  - "retail distress dossier template"
  - "operational distress outreach package"
  - "retail distress evidence pack"
  - "auto-generated distress report"
entity_type: execution_recipe
domain: signal-library > retail > asset templates > distress dossier
region: global
jurisdiction: global
temporal_scope: 2024-2026

# === VERIFICATION ===
last_verified: 2026-03-30
confidence: 0.85
version: 1.0
first_published: 2026-03-30

# === TEMPORAL VALIDITY ===
temporal_validity:
  status: evolving
  last_breaking_change: null
  next_review: 2026-09-26
  change_sensitivity: high

# === CONSTRAINTS ===
constraints:
  - "Every claim in the dossier must be falsifiable — cite a specific source, date, and data point that a reader can independently verify within 5 minutes; unfalsifiable claims destroy credibility and expose the sender to challenge [src1]"
  - "Tone must be diagnostic, never salesy — the dossier reads like a medical report (here is what we observed, here is what it means, here are your options) not a pitch deck; recipients who feel sold to discard the dossier immediately [src2]"
  - "Maximum 2 pages plus optional appendix — executives at distressed retailers are time-constrained; dossiers exceeding 2 pages see 40-60% lower read-through rates in B2B outreach benchmarks [src3]"
  - "Industry benchmarks must cite specific studies with sample sizes — 'retailers with this pattern experience 12-18% margin erosion' requires the McKinsey/Bain/BCG source, year, and n-count; unsourced benchmarks are indistinguishable from hallucination [src4]"
  - "Personalization fields (company name, signal dates, decision-maker name/role) must be populated from enrichment data — never use placeholders like [Company Name] in delivered dossiers; partially personalized outreach performs worse than generic outreach [src5]"

# === SKIP CONDITIONS ===
skip_this_unit_if:
  - condition: "Target retailer is showing digital transformation signals (tech gap, AI readiness failure, competitive pressure) rather than operational distress"
    use_instead: "signal-library/retail-assets/transformation-dossier/2026"
  - condition: "User needs the detection rules for identifying distress signals, not the dossier template for packaging them"
    use_instead: "signal-library/retail/detection-rules/2026"
  - condition: "User needs to enrich detected signals into company profiles before generating dossiers"
    use_instead: "signal-library/retail/enrichment-mapping/2026"
  - condition: "User needs the outreach sequence that delivers the dossier, not the dossier itself"
    use_instead: "business/lead-generation/outreach-sequence-loading/2026"

# === AGENT HINTS ===
inputs_needed:
  - key: distress_type
    question: "What type of distress signals are present?"
    type: choice
    options: ["inventory/supply chain distress", "workforce distress", "financial distress", "store operations distress", "compound (multiple signal types)"]
  - key: output_format
    question: "What format should the dossier be delivered in?"
    type: choice
    options: ["PDF", "HTML email", "Google Doc", "Markdown"]
  - key: review_mode
    question: "Should dossiers be auto-delivered or queued for human review?"
    type: choice
    options: ["auto-deliver (high confidence signals only)", "human review queue (all signals)", "hybrid (auto-deliver score 8+, review 5-7)"]

# === EXECUTION METADATA ===
execution:
  required_inputs:
    - name: "Enriched company profile"
      source: "signal-library/retail/enrichment-mapping/2026"
      format: "structured data"
    - name: "Signal detection report"
      source: "signal-library/retail/detection-rules/2026"
      format: "structured data"
  outputs:
    - name: "Generated distress dossier"
      format: "PDF/HTML"
      description: "Evidence-based outreach package documenting operational distress signals, quantified impact, and recommended actions — ready for delivery or human review"
  tools_required:
    - name: "Claude/GPT API"
      purpose: "Dossier content generation from structured signal + enrichment data"
      tier: "paid"
      cost: "$0.02-0.10 per dossier"
      alternatives: ["Gemini Pro", "Llama 3 (self-hosted)"]
    - name: "PDF generation library"
      purpose: "Convert structured dossier to formatted PDF"
      tier: "free"
      cost: "$0"
      alternatives: ["Puppeteer", "WeasyPrint", "Prince XML"]
  credentials_needed:
    - service: "Claude API (Anthropic)"
      type: "API key"
      where_to_get: "https://console.anthropic.com"
      free_tier_limits: "None — pay per token"
  estimated_duration: "5-15 minutes per dossier"
  estimated_cost: "$0.02-0.10 per dossier"

# === DISTRIBUTION ===
canonical_source: "https://knowledgelib.io/signal-library/retail-assets/distress-dossier/2026"
suggested_citation: "Source: knowledgelib.io — AI Knowledge Library (verified 2026-03-30)"

# === RELATED UNITS ===
related_kos:
  depends_on:
    - id: "signal-library/retail/enrichment-mapping/2026"
      label: "Enriched company profiles that populate dossier personalization fields"
    - id: "signal-library/retail/detection-rules/2026"
      label: "Detection rules that produce the signal reports summarized in dossiers"
  feeds_into:
    - id: "business/lead-generation/outreach-sequence-loading/2026"
      label: "Loading and launching outreach sequences in Instantly, Lemlist, Apollo or HubSpot — list import, A/B variants, warmup and sending limits, reply tracking (generic B2B tooling, not retail-signal messaging)"
  related_to:
    - id: "signal-library/retail-assets/transformation-dossier/2026"
      label: "Companion template for digital transformation signals"
    - id: "signal-library/retail/overview/2026"
      label: "Retail signal library taxonomy and framework"
  alternative_to: []

# === SOURCES ===
sources:
  - id: src1
    title: "The State of Fashion 2025: Challenges and Opportunities in a Post-Pandemic World"
    author: McKinsey & Company
    url: https://www.mckinsey.com/industries/retail/our-insights/state-of-fashion
    type: industry_report
    published: 2025-01-15
    reliability: authoritative
  - id: src2
    title: "B2B Buying Behavior: How Executives Evaluate Unsolicited Outreach"
    author: Gartner
    url: https://www.gartner.com/en/sales/insights/b2b-buying-journey
    type: industry_report
    published: 2025-03-01
    reliability: authoritative
  - id: src3
    title: "Optimal Content Length for B2B Executive Outreach"
    author: HBR / Corporate Executive Board
    url: https://hbr.org/2024/09/the-new-rules-of-b2b-lead-generation
    type: industry_report
    published: 2024-09-01
    reliability: high
  - id: src4
    title: "Retail Inventory Distortion: Causes, Costs, and Cures"
    author: IHL Group
    url: https://www.ihlservices.com/product/inventory-distortion/
    type: industry_report
    published: 2025-06-01
    reliability: authoritative
  - id: src5
    title: "Personalization in B2B Outreach: What Works and What Backfires"
    author: Outreach.io
    url: https://www.outreach.io/resources/blog/personalization-best-practices
    type: industry_report
    published: 2025-04-01
    reliability: high
  - id: src6
    title: "Supply Chain Disruption Impact on Retail Working Capital 2023-2025"
    author: Bain & Company
    url: https://www.bain.com/insights/retail-supply-chain-resilience/
    type: industry_report
    published: 2025-02-01
    reliability: authoritative
  - id: src7
    title: "Glassdoor Employer Rating Trends and Operational Performance Correlation"
    author: MIT Sloan Management Review
    url: https://sloanreview.mit.edu/article/employee-satisfaction-and-firm-performance/
    type: academic_paper
    published: 2024-11-01
    reliability: authoritative
---

# Distress Dossier Template

## Purpose

This recipe generates a personalized, evidence-based dossier for retailers showing operational distress signals — inventory write-downs, supply chain disruption, workforce instability, or financial deterioration. The output is a 2-page document that names specific signals with dates, quantifies business impact using industry benchmarks, and offers 3 graduated action options — ready for delivery to the decision-maker identified during enrichment. [src1, src2]

## Prerequisites
<!-- Agents: verify ALL prerequisites before executing. Missing prerequisites = failed execution. -->

- [ ] **Enriched company profile** available from `signal-library/retail/enrichment-mapping/2026` — [Retail Signal Enrichment Mapping](/signal-library/retail/enrichment-mapping/2026)
- [ ] **Signal detection report** with scored signals available from `signal-library/retail/detection-rules/2026` — [Retail Detection Rules](/signal-library/retail/detection-rules/2026)
- [ ] **Decision-maker contact** (name, title, email/LinkedIn) from enrichment output
- [ ] **Claude or GPT API key** — from [Anthropic Console](https://console.anthropic.com) or [OpenAI Platform](https://platform.openai.com)
- [ ] **PDF generation tool** — Puppeteer, WeasyPrint, or equivalent (free)

## Constraints
<!-- Hard rules. Agents: enforce throughout execution. Violating these = broken output or legal risk. -->

- Every claim must be falsifiable. Each data point in the dossier requires a specific source, date, and verifiable figure. A recipient must be able to fact-check any claim within 5 minutes. Unfalsifiable claims destroy credibility. [src1]
- Diagnostic tone only. The dossier reads like a medical report: observation, interpretation, options. Never use phrases like "we can help you," "our solution," "schedule a demo," or "limited-time offer." [src2]
- Maximum 2 pages plus optional appendix. Distressed retailer executives operate under time pressure. Dossiers exceeding 2 pages see 40-60% lower read-through rates. [src3]
- All industry benchmarks must cite the study, year, and sample size. "Retailers with this pattern experience 12-18% margin erosion" must reference the specific McKinsey/Bain/IHL report. [src4]
- All personalization fields must be populated. Never deliver a dossier with placeholder text like [Company Name] or [Signal Date]. Partially personalized outreach performs worse than generic outreach. [src5]

## Tool Selection Decision

<!-- Agent selects the right tool path based on user inputs. -->

```
Which path?
├── Output format = PDF AND review mode = auto-deliver
│   └── PATH A: Automated PDF — Claude API + WeasyPrint + email delivery
├── Output format = PDF AND review mode = human review
│   └── PATH B: Reviewed PDF — Claude API + WeasyPrint + review queue
├── Output format = HTML email AND review mode = auto-deliver
│   └── PATH C: Automated HTML — Claude API + HTML template + email API
└── Output format = Markdown AND review mode = human review
    └── PATH D: Draft Markdown — Claude API + Markdown output + review queue
```

| Path | Tools | Cost | Speed | Output Quality |
|------|-------|------|-------|---------------|
| A: Automated PDF | Claude API + WeasyPrint | $0.02-0.10/dossier | 2-5 min | High — but requires confidence threshold (score 8+) |
| B: Reviewed PDF | Claude API + WeasyPrint | $0.02-0.10/dossier | 5-15 min (includes review) | Excellent — human catches edge cases |
| C: Automated HTML | Claude API + HTML template | $0.02-0.08/dossier | 1-3 min | High — inline rendering, no attachment friction |
| D: Draft Markdown | Claude API | $0.02-0.05/dossier | 1-2 min | Good — fastest for review-heavy workflows |

## Execution Flow

### Step 1: Assemble Input Data

**Duration**: 1-2 minutes per dossier
**Tool**: Python/Node.js script

Collect all required inputs from the enrichment and detection pipeline outputs into a single structured context object for the LLM.

```json
{
  "company": {
    "name": "Acme Retail Corp",
    "domain": "acmeretail.com",
    "hq_city": "Dallas",
    "hq_state": "TX",
    "employee_count": 4200,
    "annual_revenue": "$380M",
    "store_count": 145,
    "primary_category": "apparel"
  },
  "decision_maker": {
    "name": "Sarah Chen",
    "title": "VP Supply Chain",
    "priority": "P1"
  },
  "signals": [
    {
      "type": "inventory_distress",
      "source": "SEC 10-Q Filing (Q3 2025)",
      "date": "2025-11-15",
      "data_point": "$45M inventory write-down, DIO increased from 95 to 132 days",
      "context": "Write-down concentrated in seasonal apparel categories"
    },
    {
      "type": "workforce_distress",
      "source": "LinkedIn Jobs + Indeed",
      "date": "2025-12-01 to 2025-12-30",
      "data_point": "6 urgent supply chain roles posted in 30 days (3x normal rate)",
      "context": "Titles include 'VP Supply Chain Planning' and 'Director Inventory Management'"
    },
    {
      "type": "employee_sentiment",
      "source": "Glassdoor",
      "date": "2025-Q4",
      "data_point": "Supply chain team ratings dropped 0.8 points (3.8 to 3.0)",
      "context": "Reviews mention 'constant firefighting' and 'leadership turnover'"
    }
  ],
  "composite_score": 7.8,
  "signal_cluster": "inventory_supply_chain_compound"
}
```

**Verify**: All required fields populated — company name, at least 1 decision-maker, at least 2 signals with source+date+data_point.
**If failed**: If fewer than 2 signals, the dossier lacks sufficient evidence. Return to detection pipeline and lower threshold, or flag company for monitoring rather than outreach.

### Step 2: Generate Executive Summary

**Duration**: 1-2 minutes
**Tool**: Claude/GPT API

Generate a 1-paragraph executive summary that names specific signals with dates and hooks the reader with quantified impact.

```
SYSTEM PROMPT:
You are a retail operations analyst writing a diagnostic briefing.
Tone: clinical, evidence-based, diagnostic. Never salesy.
Format: Single paragraph, 3-5 sentences.
Structure: Name 2-3 specific signals with dates → state what the pattern
typically costs using industry benchmarks → close with "Here's what that
pattern costs in [specific metric]."

CONSTRAINTS:
- Every number must come from the input data or cited benchmarks
- Do not speculate beyond what the signals support
- Do not suggest any product, service, or company
- Write for a VP/C-suite reader who has 30 seconds

USER PROMPT:
Generate an executive summary for the following distress signals:
{input_data as JSON}

Industry benchmark to cite: Retailers with compound inventory + workforce
distress signals experience 12-18% margin erosion within 2 quarters
(McKinsey State of Fashion 2025, n=127 retailers).
```

**Expected output**: 1 paragraph, 60-100 words. Example: "In Q3 2025, Acme Retail Corp disclosed $45M in inventory write-downs with days-inventory-outstanding rising from 95 to 132. In the following 30 days, 6 urgent supply chain roles appeared on LinkedIn and Indeed — 3x the normal hiring rate — including VP Supply Chain Planning. Glassdoor supply chain team ratings dropped 0.8 points in Q4. Among the 127 retailers McKinsey tracked with this compound pattern, 12-18% margin erosion followed within 2 quarters."
**Verify**: Summary contains at least 2 specific data points with dates from the input signals. No promotional language detected.
**If failed**: If the LLM output contains phrases like "we recommend," "our team," or "schedule a call," regenerate with stricter system prompt constraints.

### Step 3: Generate Evidence Pack

**Duration**: 2-3 minutes
**Tool**: Claude/GPT API

Generate one evidence entry per signal with source, date, data point, and context interpretation — all falsifiable.

```
SYSTEM PROMPT:
You are a forensic analyst documenting observable evidence.
Format each signal as:

**Signal: {signal_type}**
- Source: {exact source name and document/page}
- Date: {exact date or date range}
- Data Point: {specific number or metric}
- Context: {1-2 sentence interpretation of what this means operationally}
- Verification: {how a reader can independently confirm this data point}

CONSTRAINTS:
- Only state what is directly observable from the source
- Context interpretation must be conservative (e.g., "consistent with" not
  "proves")
- Every entry must include a verification path
```

**Verify**: Each signal entry has all 5 fields populated. Verification paths are actionable (e.g., "Search SEC EDGAR for CIK 0001234567, Form 10-Q, filed 2025-11-15").
**If failed**: If any signal lacks a verification path, the data source was likely inferred rather than observed. Remove the signal or flag it as "unverified — requires manual confirmation."

### Step 4: Generate Impact Analysis

**Duration**: 1-2 minutes
**Tool**: Claude/GPT API

Quantify business impact using industry benchmarks with full citation.

```
SYSTEM PROMPT:
You are a retail strategy analyst quantifying operational risk.
Structure:
1. Name the pattern observed (compound signal cluster type)
2. State the industry benchmark with full citation (study name, author,
   year, sample size)
3. Apply the benchmark range to the target company's known financials
4. State the implied working capital / margin impact in dollar terms

CONSTRAINTS:
- Only use benchmarks from the provided reference data
- Show the math: "At $380M revenue, 12-18% margin erosion = $45.6M-$68.4M
  annual impact"
- State the time horizon explicitly (e.g., "within 2 quarters")
- Include a confidence qualifier (e.g., "based on companies with similar
  revenue and signal profile")

BENCHMARK REFERENCES:
- Inventory distress: 12-18% margin erosion within 2 quarters (McKinsey
  State of Fashion 2025, n=127) [src1]
- Supply chain disruption: 3-5% revenue loss per quarter of sustained
  disruption (Bain Retail Supply Chain 2025, n=89) [src6]
- Workforce instability: Companies with >0.5pt Glassdoor drop and elevated
  hiring show 2x turnover cost in affected function within 6 months
  (MIT Sloan 2024, n=214) [src7]
- Inventory write-down: Average DIO above 120 days correlates with 15-22%
  higher carrying costs (IHL Group 2025, n=350 retailers) [src4]
```

**Verify**: Impact analysis includes at least 1 dollar-denominated impact figure derived from company revenue + benchmark range. Full citation present for every benchmark used.
**If failed**: If no dollar figure can be calculated (e.g., revenue data missing from enrichment), state the benchmark range as a percentage and note "revenue data unavailable for dollar conversion."

### Step 5: Generate Recommended Actions

**Duration**: 1 minute
**Tool**: Claude/GPT API

Generate 3 graduated options from lightweight to comprehensive.

```
SYSTEM PROMPT:
You are presenting options to a busy executive. Three options, graduated
by commitment level:

Option 1 (Low commitment): Free, 30-minute diagnostic. What the executive
gets: verbal walkthrough of the signal pattern and what peers have done.
No obligation.

Option 2 (Medium commitment): Paid assessment ($X range). What the
executive gets: full supply chain diagnostic with specific recommendations
and implementation timeline. Duration and deliverables specified.

Option 3 (No action): Do-nothing trajectory modeling. What happens if
these patterns continue for 2 more quarters based on benchmark data.
Not a threat — a projection.

CONSTRAINTS:
- Option 1 must be genuinely free and low-friction
- Option 2 must state a specific price range, duration, and deliverable
- Option 3 must be factual projection, not fear-mongering
- Never use "limited time," "exclusive," or urgency language
```

**Verify**: All 3 options present. Option 1 is genuinely no-cost. Option 3 cites a benchmark. No urgency language detected.
**If failed**: If the LLM injects urgency language, strip it and regenerate Option 3 only with emphasis on "factual projection."

### Step 6: Assemble and Format Dossier

**Duration**: 1-3 minutes
**Tool**: PDF generation (WeasyPrint/Puppeteer) or HTML template

Assemble generated sections into the final dossier format.

```python
# dossier_assembly.py
from datetime import datetime

def assemble_dossier(company, decision_maker, exec_summary, evidence_pack,
                     impact_analysis, recommended_actions, signals):
    """Assemble dossier sections into final document structure."""
    dossier = {
        "metadata": {
            "generated_at": datetime.now().isoformat(),
            "company": company["name"],
            "recipient": f"{decision_maker['name']}, {decision_maker['title']}",
            "signal_count": len(signals),
            "composite_score": signals[0].get("composite_score", "N/A"),
            "dossier_type": "distress"
        },
        "sections": [
            {
                "title": "Executive Summary",
                "content": exec_summary,
                "page": 1
            },
            {
                "title": "Evidence Pack",
                "content": evidence_pack,
                "page": 1
            },
            {
                "title": "Impact Analysis",
                "content": impact_analysis,
                "page": 2
            },
            {
                "title": "Recommended Actions",
                "content": recommended_actions,
                "page": 2
            }
        ],
        "appendix": {
            "signal_sources": [s["source"] for s in signals],
            "methodology_note": "All signals sourced from public filings, "
                "public job boards, and public review platforms. No "
                "proprietary or confidential data used.",
            "benchmark_references": [
                "McKinsey State of Fashion 2025 (n=127)",
                "Bain Retail Supply Chain Resilience 2025 (n=89)",
                "IHL Group Inventory Distortion 2025 (n=350)",
                "MIT Sloan Employee Satisfaction Study 2024 (n=214)"
            ]
        }
    }
    return dossier
```

**Output files**:
- `distress_dossier_{company_slug}_{timestamp}.pdf` — Formatted 2-page dossier ready for delivery
- `distress_dossier_{company_slug}_{timestamp}.json` — Structured dossier data for programmatic processing
- `dossier_qa_checklist_{company_slug}.json` — Quality assurance results from verification checks

**Verify**: PDF renders correctly at 2 pages or fewer. All personalization fields populated (no placeholder text). All source citations present.
**If failed**: If PDF exceeds 2 pages, reduce evidence pack to top 2 signals by relevance score and regenerate.

## Output Schema

<!-- Exact format of the deliverable. Downstream agents reference this schema. -->

```json
{
  "output_type": "distress_dossier",
  "format": "PDF + JSON",
  "sections": [
    {"name": "executive_summary", "type": "string", "description": "1-paragraph hook with specific signals, dates, and benchmark impact", "required": true},
    {"name": "evidence_pack", "type": "array", "description": "Array of signal entries, each with source/date/data_point/context/verification", "required": true},
    {"name": "impact_analysis", "type": "string", "description": "Quantified business impact with dollar figures and benchmark citations", "required": true},
    {"name": "recommended_actions", "type": "array", "description": "3 graduated options (free diagnostic, paid assessment, do-nothing projection)", "required": true},
    {"name": "appendix", "type": "object", "description": "Signal sources, methodology note, benchmark references", "required": false}
  ],
  "personalization_fields": [
    {"name": "company_name", "type": "string", "required": true},
    {"name": "decision_maker_name", "type": "string", "required": true},
    {"name": "decision_maker_title", "type": "string", "required": true},
    {"name": "signal_dates", "type": "array", "required": true},
    {"name": "signal_data_points", "type": "array", "required": true}
  ],
  "expected_page_count": "2 + optional appendix",
  "sort_order": "sections in fixed order: summary, evidence, impact, actions",
  "deduplication_key": "company_name + generated_at"
}
```

## Quality Benchmarks

<!-- How to evaluate if the output is good enough. -->

| Quality Metric | Minimum Acceptable | Good | Excellent |
|---------------|-------------------|------|-----------|
| Falsifiability rate (claims with verifiable source) | > 80% of claims | > 90% | 100% |
| Personalization completeness | All required fields populated | + industry-specific context | + competitor references |
| Benchmark citation accuracy | 1 cited benchmark with source | 2-3 benchmarks with n-counts | All benchmarks with full citation |
| Tone compliance (no promotional language) | No "we/our/schedule" detected | + no superlatives or urgency | + reads as independent analyst report |
| Page length | 2 pages or fewer | 1.5-2 pages | 1.5 pages + focused appendix |
| Signal-to-noise ratio | 2+ signals with evidence | 3+ signals, all falsifiable | 3+ signals + trend analysis |

**If below minimum**: Regenerate the failing section with stricter system prompt constraints. If falsifiability rate is below 80%, audit each claim against the input data and remove any that lack a specific source.

## Error Handling

<!-- Common failures and recovery actions. -->

| Error | Likely Cause | Recovery Action |
|-------|-------------|----------------|
| LLM generates promotional language | System prompt not restrictive enough | Add explicit negative examples to system prompt: "NEVER write: 'we can help', 'our solution', 'schedule a demo'" |
| Impact analysis lacks dollar figures | Revenue data missing from enrichment | Use percentage-only impact with note "revenue data unavailable"; flag company for manual revenue lookup |
| Evidence pack has unverifiable claims | LLM hallucinated data points not in input | Cross-check every data point against input JSON; remove any claim not traceable to input signals |
| PDF exceeds 2 pages | Too many signals or verbose generation | Limit evidence pack to top 2 signals by composite score; reduce executive summary to 3 sentences |
| Personalization fields contain placeholders | Enrichment data incomplete | Do not generate dossier — return to enrichment pipeline (Step 4) to fill gaps |
| LLM refuses to generate impact projections | Safety filter triggered by financial predictions | Reframe as "industry benchmark range" rather than "prediction"; cite the study explicitly |
| Benchmark data is outdated | Source study older than 2 years | Flag benchmark as "based on {year} data" and note "recalibration recommended"; check for newer edition |

## Cost Breakdown

<!-- Real cost analysis so agents can warn users before execution. -->

| Component | Per Dossier | 50 Dossiers/Month | 500 Dossiers/Month |
|-----------|-----------|-------------------|---------------------|
| LLM API (Claude Sonnet) | $0.02-0.05 | $1-2.50 | $10-25 |
| LLM API (Claude Opus) | $0.05-0.10 | $2.50-5 | $25-50 |
| PDF generation (WeasyPrint) | $0 (open source) | $0 | $0 |
| PDF generation (Prince XML) | $0.01/doc (licensed) | $0.50 | $5 |
| Email delivery (SendGrid) | $0 (free tier) | $0 (up to 100/day) | $15/mo |
| **Total (Claude Sonnet + free tools)** | **$0.02-0.05** | **$1-2.50** | **$10-25** |

## Anti-Patterns

### Wrong: Leading with product pitch

Dossier opens with "Our firm specializes in retail supply chain optimization" or closes with "We'd love to schedule a demo." Result: recipient classifies the dossier as spam and never reads the evidence. Diagnostic credibility is destroyed in the first sentence. [src2]

### Correct: Lead with their data, not your capabilities

Open with specific signals the recipient will recognize ("Your Q3 10-Q disclosed $45M in inventory write-downs"). The evidence sells the conversation — not the sender.

### Wrong: Including speculative or unfalsifiable claims

Dossier states "Your supply chain is likely underperforming" or "Most retailers in your position struggle with inventory." These claims cannot be verified and sound like generic sales copy. [src1]

### Correct: Every claim cites source, date, and data point

"Your DIO increased from 95 to 132 days between Q2 and Q3 2025 (SEC 10-Q, filed 2025-11-15, page 23)." The recipient can verify this in 2 minutes.

### Wrong: Overloading with signals

Including 6-8 signals to appear thorough. Result: the dossier exceeds 2 pages, buries the key insight, and the executive stops reading after page 1. [src3]

### Correct: Top 2-3 signals that form a compound pattern

Select the 2-3 signals that together tell a coherent story. Inventory write-down + urgent supply chain hiring + declining Glassdoor scores form a narrative. Adding unrelated signals (e.g., website tech stack age) dilutes the message.

### Wrong: Generic benchmark without attribution

"Companies in your situation typically lose 15% of their margins." No source, no sample size, no year. Indistinguishable from a hallucinated claim. [src4]

### Correct: Full benchmark citation

"Among 127 retailers tracked by McKinsey (State of Fashion 2025), those showing compound inventory + workforce distress signals experienced 12-18% margin erosion within 2 quarters."

## When This Matters

Use this recipe when the signal detection pipeline has identified a retailer showing inventory, supply chain, workforce, or financial distress signals and the enrichment pipeline has resolved the signals to a specific company with decision-maker contacts. This is the asset generation step between enrichment (upstream) and outreach delivery (downstream). Without the dossier, outreach lacks the evidence-based positioning that differentiates signal-driven selling from cold outreach.

## Related Units

- [Retail Signal Enrichment Mapping](/signal-library/retail/enrichment-mapping/2026) — Upstream: produces the enriched company profiles and decision-maker contacts that populate the dossier
- [Retail Detection Rules](/signal-library/retail/detection-rules/2026) — Upstream: produces the scored signals summarized in the evidence pack
- [Transformation Dossier Template](/signal-library/retail-assets/transformation-dossier/2026) — Companion template for digital transformation signals
- [Retail Signal Library Overview](/signal-library/retail/overview/2026) — Framework and taxonomy this template operates within