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

# === VERIFICATION ===
last_verified: 2026-03-31
confidence: 0.85
version: 1.0
first_published: 2026-03-31

# === TEMPORAL VALIDITY ===
temporal_validity:
  status: evolving
  last_breaking_change: null
  next_review: 2026-09-27
  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 technology audit (here is the gap we measured, here is what it costs, here are your options) not a pitch deck; recipients who feel sold to discard the dossier immediately [src2]"
  - "Maximum 2 pages plus optional scorecard appendix — retail executives evaluating digital transformation 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 without AI commerce see 15-25% lower conversion' requires the Forrester/Gartner source, year, and n-count; unsourced benchmarks are indistinguishable from hallucination [src4]"
  - "Personalization fields (company name, tech stack findings, 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 operational distress signals (inventory write-downs, workforce instability, financial deterioration) rather than digital transformation gaps"
    use_instead: "signal-library/retail-assets/distress-dossier/2026"
  - condition: "User needs the detection rules for identifying transformation 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: transformation_type
    question: "What type of transformation signals are present?"
    type: choice
    options: ["digital gap (outdated tech stack)", "AI readiness failure (no AI commerce capabilities)", "competitive pressure (competitors ahead on digital)", "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 transformation dossier"
      format: "PDF/HTML"
      description: "Evidence-based outreach package documenting digital transformation gaps, AI readiness scoring, competitive positioning, 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: "Google PageSpeed Insights API"
      purpose: "Core Web Vitals scoring for target and competitor sites"
      tier: "free"
      cost: "$0"
      alternatives: ["WebPageTest API", "Lighthouse CLI"]
    - 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"
    - service: "Google PageSpeed Insights API"
      type: "API key"
      where_to_get: "https://developers.google.com/speed/docs/insights/v5/get-started"
      free_tier_limits: "400 queries/100 seconds"
  estimated_duration: "10-20 minutes per dossier"
  estimated_cost: "$0.02-0.10 per dossier (LLM cost; PageSpeed API is free)"

# === DISTRIBUTION ===
canonical_source: "https://knowledgelib.io/signal-library/retail-assets/transformation-dossier/2026"
suggested_citation: "Source: knowledgelib.io — AI Knowledge Library (verified 2026-03-31)"

# === 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/distress-dossier/2026"
      label: "Companion template for operational distress signals"
    - id: "signal-library/retail/overview/2026"
      label: "Retail signal library taxonomy and framework"
  alternative_to: []

# === SOURCES ===
sources:
  - id: src1
    title: "The Future of Digital Commerce: AI-Driven Retail Transformation"
    author: Forrester Research
    url: https://www.forrester.com/research/digital-commerce-ai-transformation/
    type: industry_report
    published: 2025-06-15
    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: "Predicts 2026: AI Commerce Will Separate Retail Winners from Losers"
    author: Gartner
    url: https://www.gartner.com/en/articles/predicts-ai-commerce-retail
    type: industry_report
    published: 2025-11-01
    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: "Web Performance and Retail Conversion: Core Web Vitals Impact Study"
    author: Google / web.dev
    url: https://web.dev/vitals-business-impact/
    type: industry_report
    published: 2025-02-01
    reliability: authoritative
  - id: src7
    title: "How AI Is Reshaping Product Discovery in Retail"
    author: Peter Beck
    url: https://quickborn.ai/essays/ai-product-discovery-retail
    type: industry_report
    published: 2026-01-15
    reliability: high
---

# Transformation Dossier Template

## Purpose

This recipe generates a personalized, evidence-based dossier for retailers showing digital transformation gaps — outdated tech stacks, absent AI commerce capabilities, or competitive pressure from digitally advanced rivals. The output is a 2-page document plus optional AI Readiness Scorecard appendix that names specific technology gaps with dated evidence, quantifies business impact using Forrester/Gartner benchmarks, and offers 3 graduated action options — ready for delivery to the decision-maker identified during enrichment. Directly feeds the Quickborn AI Readiness Diagnostic for Retail engagement pipeline. [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)
- [ ] **Google PageSpeed Insights API key** — from [Google Developers](https://developers.google.com/speed/docs/insights/v5/get-started) (free)
- [ ] **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 technology audit: observation, measurement, options. Never use phrases like "we can help you," "our solution," "schedule a demo," or "limited-time offer." [src2]
- Maximum 2 pages plus optional scorecard appendix. Retail executives evaluating digital transformation 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 without AI commerce see 15-25% lower conversion" must reference the specific Forrester/Gartner report. [src4]
- All personalization fields must be populated. Never deliver a dossier with placeholder text like [Company Name] or [Tech Stack]. 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 + PageSpeed API + WeasyPrint + email delivery
├── Output format = PDF AND review mode = human review
│   └── PATH B: Reviewed PDF — Claude API + PageSpeed API + WeasyPrint + review queue
├── Output format = HTML email AND review mode = auto-deliver
│   └── PATH C: Automated HTML — Claude API + PageSpeed API + HTML template + email API
└── Output format = Markdown AND review mode = human review
    └── PATH D: Draft Markdown — Claude API + PageSpeed API + Markdown output + review queue
```

| Path | Tools | Cost | Speed | Output Quality |
|------|-------|------|-------|---------------|
| A: Automated PDF | Claude API + PageSpeed API + WeasyPrint | $0.02-0.10/dossier | 5-10 min | High — but requires confidence threshold (score 8+) |
| B: Reviewed PDF | Claude API + PageSpeed API + WeasyPrint | $0.02-0.10/dossier | 10-20 min (includes review) | Excellent — human catches edge cases |
| C: Automated HTML | Claude API + PageSpeed API + HTML template | $0.02-0.08/dossier | 3-7 min | High — inline rendering, no attachment friction |
| D: Draft Markdown | Claude API + PageSpeed API | $0.02-0.05/dossier | 3-5 min | Good — fastest for review-heavy workflows |

## Execution Flow

### Step 1: Assemble Input Data

**Duration**: 2-5 minutes per dossier
**Tool**: Python/Node.js script + Google PageSpeed Insights API

Collect all required inputs from the enrichment and detection pipeline outputs. Run Core Web Vitals checks on the target company's site and up to 3 competitor sites. Assemble into a single structured context object for the LLM.

```json
{
  "company": {
    "name": "Maple & Vine Retail",
    "domain": "mapleandvine.com",
    "hq_city": "Portland",
    "hq_state": "OR",
    "employee_count": 2800,
    "annual_revenue": "$220M",
    "store_count": 85,
    "primary_category": "home goods"
  },
  "decision_maker": {
    "name": "James Liu",
    "title": "CTO",
    "priority": "P1"
  },
  "signals": [
    {
      "type": "digital_gap",
      "source": "BuiltWith technology profile",
      "date": "2026-03-01",
      "data_point": "Site runs on Magento 1.x (EOL 2020), no search personalization, no recommendation engine detected",
      "context": "Tech stack 6 years behind EOL — security risk, no AI commerce capability"
    },
    {
      "type": "competitive_pressure",
      "source": "BuiltWith + press releases",
      "date": "2026-01-15 to 2026-02-28",
      "data_point": "2 of 3 direct competitors (HomeNest, Artisan & Co) launched AI-powered product discovery in Q1 2026",
      "context": "Competitors invested in visual search and personalized recommendations; target has keyword-only search"
    },
    {
      "type": "web_performance",
      "source": "Google PageSpeed Insights",
      "date": "2026-03-15",
      "data_point": "LCP 4.1s (poor), CLS 0.28 (poor), FID 180ms (needs improvement); competitor avg: LCP 1.8s, CLS 0.05, FID 45ms",
      "context": "Core Web Vitals failing on all 3 metrics; Google ranks sites with good CWV higher in search results"
    },
    {
      "type": "ai_readiness_gap",
      "source": "LinkedIn job postings + company career page",
      "date": "2026-Q1",
      "data_point": "Zero AI/ML roles posted in trailing 12 months; no data engineering or analytics positions open",
      "context": "No observable investment in AI talent pipeline; competitors posting 3-5 AI roles per quarter"
    }
  ],
  "core_web_vitals": {
    "target": {"lcp": 4.1, "cls": 0.28, "fid": 180, "performance_score": 32},
    "competitors": [
      {"name": "HomeNest", "lcp": 1.6, "cls": 0.04, "fid": 38, "performance_score": 91},
      {"name": "Artisan & Co", "lcp": 2.1, "cls": 0.06, "fid": 52, "performance_score": 84}
    ]
  },
  "composite_score": 8.2,
  "signal_cluster": "digital_transformation_compound"
}
```

**Verify**: All required fields populated — company name, at least 1 decision-maker, at least 2 signals with source+date+data_point, Core Web Vitals for target and at least 1 competitor.
**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 the technology gap, competitive context, and quantified customer experience impact.

```
SYSTEM PROMPT:
You are a retail technology analyst writing a diagnostic briefing.
Tone: clinical, evidence-based, diagnostic. Never salesy.
Format: Single paragraph, 3-5 sentences.
Structure: Name the competitive context (how many competitors have moved
ahead) → state the specific technology gap with data → quantify the
customer experience cost using industry benchmarks → close with the
conversion impact.

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 CTO/CDO reader who has 30 seconds

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

Industry benchmark to cite: Retailers without AI-powered product discovery
see 15-25% lower conversion rates than AI-enabled competitors (Forrester
Digital Commerce 2025, n=156 retailers). Sites with poor Core Web Vitals
experience 24% higher bounce rates (Google/web.dev 2025, n=10,000 sites).
```

**Expected output**: 1 paragraph, 60-100 words. Example: "2 of your 3 direct competitors launched AI-powered product discovery in Q1 2026. Your website still runs Magento 1.x — end-of-life since 2020 — with keyword-only search and a 4.1-second largest contentful paint. Among the 156 retailers Forrester tracked, those without AI commerce saw 15-25% lower conversion than AI-enabled peers. Your Core Web Vitals fail all 3 Google metrics where competitors score 84-91. Here's the customer experience gap that creates."
**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**: 3-5 minutes
**Tool**: Claude/GPT API

Generate a tech stack comparison table, Core Web Vitals scores, GEO readiness audit, and leadership hiring signals — all falsifiable.

```
SYSTEM PROMPT:
You are a technology auditor documenting observable evidence.
Generate 4 evidence sections:

**1. Tech Stack Comparison**
Table format: Target vs. each competitor across 5 dimensions:
- E-commerce platform (name + version)
- Search technology (keyword-only vs. AI/vector search)
- Recommendation engine (none vs. collaborative filtering vs. deep learning)
- Personalization capability (none vs. segment vs. individual)
- Mobile experience (responsive vs. PWA vs. native app)

**2. Core Web Vitals Scores**
Table: Target vs. competitors across LCP, CLS, FID, Performance Score.
Include Google's pass/fail thresholds.

**3. GEO Readiness Audit**
How the target appears in AI-powered search results vs. competitors.
Assess: structured data quality, content freshness, schema markup,
FAQ/HowTo markup, AI-crawlable content structure.

**4. Leadership Hiring Signals**
Observable AI/data talent investment (or absence): number of AI/ML roles
posted, data engineering positions, CDO/CTO hiring patterns.

CONSTRAINTS:
- Only state what is directly observable from the source
- Context interpretation must be conservative
- Every entry must include a verification path
```

**Verify**: All 4 evidence sections present. Tech stack comparison has at least 1 competitor. Core Web Vitals include numeric scores. Verification paths are actionable.
**If failed**: If any section lacks verifiable data, remove the section 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 Forrester/Gartner benchmarks with full citation.

```
SYSTEM PROMPT:
You are a retail strategy analyst quantifying digital transformation risk.
Structure:
1. Name the pattern observed (compound digital gap 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 conversion / revenue impact in dollar terms

CONSTRAINTS:
- Only use benchmarks from the provided reference data
- Show the math: "At $220M revenue, 15-25% lower conversion on 40%
  e-commerce share = $13.2M-$22M annual impact"
- State the time horizon explicitly
- Include a confidence qualifier

BENCHMARK REFERENCES:
- AI commerce gap: 15-25% lower conversion for retailers without AI
  product discovery (Forrester Digital Commerce 2025, n=156) [src1]
- Core Web Vitals: Sites with poor CWV see 24% higher bounce rates and
  up to 15% lower conversion (Google/web.dev 2025, n=10,000) [src6]
- Digital laggards: Retailers in bottom quartile of digital maturity lose
  3-5 points of market share annually to digitally advanced competitors
  (Gartner Predicts 2026, n=200) [src4]
- AI talent pipeline: Companies with no AI hiring in trailing 12 months
  require 18-24 months to build initial AI capability vs. 6-9 months for
  companies with existing data teams (Forrester 2025, n=89) [src1]
```

**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 AI Readiness Scorecard

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

Score the target across 6 dimensions of AI readiness using observable public signals. This is a lightweight version scored 1-5 per dimension.

```
SYSTEM PROMPT:
You are scoring a retailer's AI readiness across 6 dimensions.
For each dimension, assign a score from 1 (no capability) to 5 (advanced)
based ONLY on observable public evidence. Cite the specific signal that
justifies each score.

DIMENSIONS:
1. Data Infrastructure — Does the company have modern data architecture?
   Observable signals: tech stack age, CDW/data lake job postings,
   analytics tool adoption (GA4, Snowflake, BigQuery)
2. Automation Maturity — Are processes automated or manual?
   Observable signals: marketing automation tools detected, API
   integrations, headless commerce architecture
3. Organizational Receptivity — Is leadership investing in transformation?
   Observable signals: CDO/CTO hiring, digital transformation press
   releases, board-level technology background
4. Compliance Readiness — Can the company handle AI governance?
   Observable signals: privacy policy maturity, cookie consent
   implementation, data handling practices
5. AI Commerce Capability — Does the company use AI in customer-facing
   commerce?
   Observable signals: recommendation engines, visual search, chatbots,
   personalization, dynamic pricing
6. Workforce Adaptation — Does the company have AI talent?
   Observable signals: AI/ML job postings, data science team size,
   training program announcements

FORMAT per dimension:
- Dimension name
- Score: X/5
- Evidence: "{specific observable signal with source and date}"
- Gap: "{what the score means operationally}"

AGGREGATE:
- Total score: X/30
- Readiness tier: Critical (6-12) | Developing (13-18) | Emerging (19-24) | Advanced (25-30)

CONSTRAINTS:
- Never score based on assumptions — only observable evidence
- If no evidence exists for a dimension, score it 1 with note
  "No observable evidence found"
- Do not extrapolate from industry norms — score this company only
```

**Verify**: All 6 dimensions scored. Each score cites at least 1 specific signal. Aggregate score calculated correctly. Readiness tier matches score range.
**If failed**: If more than 2 dimensions have "no observable evidence," the enrichment data is insufficient. Return to enrichment pipeline for deeper research before generating the scorecard.

### Step 6: 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 CTO/CDO. Three options, graduated
by commitment level:

Option 1 (Low commitment): Free, 30-minute AI readiness preview. What
the executive gets: verbal walkthrough of the scorecard findings and
what peer retailers have done. No obligation.

Option 2 (Medium commitment): Full AI Readiness Diagnostic ($20K).
What the executive gets: comprehensive assessment across all 6
dimensions, vendor-neutral technology recommendations, implementation
roadmap with timeline and budget, and ROI modeling. Duration: 4-6 weeks.
Deliverable: 40-page diagnostic report + executive presentation.

Option 3 (No action): Do-nothing trajectory modeling. What happens if
the digital gap continues for 2-4 more quarters based on benchmark data.
Not a threat — a projection using Gartner's digital laggard benchmarks.

CONSTRAINTS:
- Option 1 must be genuinely free and low-friction
- Option 2 must state $20K price, 4-6 week duration, and specific deliverables
- 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 2 states $20K and 4-6 week timeline. 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 7: 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
# transformation_dossier_assembly.py
from datetime import datetime

def assemble_dossier(company, decision_maker, exec_summary, evidence_pack,
                     impact_analysis, ai_scorecard, 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": "transformation"
        },
        "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": {
            "ai_readiness_scorecard": ai_scorecard,
            "signal_sources": [s["source"] for s in signals],
            "methodology_note": "All signals sourced from public technology "
                "profiles, public web performance APIs, public job boards, "
                "and public review platforms. No proprietary or confidential "
                "data used. AI Readiness Scorecard dimensions based on "
                "Forrester's Digital Commerce Maturity Model (2025).",
            "benchmark_references": [
                "Forrester Digital Commerce AI Transformation 2025 (n=156)",
                "Gartner Predicts 2026: AI Commerce (n=200)",
                "Google/web.dev Core Web Vitals Impact Study 2025 (n=10,000)",
                "Peter Beck, AI Product Discovery in Retail 2026"
            ]
        }
    }
    return dossier
```

**Output files**:
- `transformation_dossier_{company_slug}_{timestamp}.pdf` — Formatted 2-page dossier + scorecard appendix ready for delivery
- `transformation_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 plus optional 1-page scorecard appendix. All personalization fields populated (no placeholder text). All source citations present. AI Readiness Scorecard totals correctly.
**If failed**: If PDF exceeds 2 pages (excluding appendix), 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": "transformation_dossier",
  "format": "PDF + JSON",
  "sections": [
    {"name": "executive_summary", "type": "string", "description": "1-paragraph hook naming technology gap, competitive context, and conversion impact", "required": true},
    {"name": "evidence_pack", "type": "object", "description": "4 sub-sections: tech_stack_comparison (table), core_web_vitals (table), geo_readiness_audit, leadership_hiring_signals", "required": true},
    {"name": "impact_analysis", "type": "string", "description": "Quantified business impact with dollar figures and Forrester/Gartner benchmark citations", "required": true},
    {"name": "recommended_actions", "type": "array", "description": "3 graduated options (free 30-min AI readiness preview, full $20K diagnostic, do-nothing trajectory)", "required": true},
    {"name": "ai_readiness_scorecard", "type": "object", "description": "6-dimension scorecard (1-5 per dimension): data_infrastructure, automation_maturity, organizational_receptivity, compliance_readiness, ai_commerce_capability, workforce_adaptation", "required": true}
  ],
  "scorecard_schema": {
    "dimensions": [
      {"name": "data_infrastructure", "score_range": "1-5", "evidence_required": true},
      {"name": "automation_maturity", "score_range": "1-5", "evidence_required": true},
      {"name": "organizational_receptivity", "score_range": "1-5", "evidence_required": true},
      {"name": "compliance_readiness", "score_range": "1-5", "evidence_required": true},
      {"name": "ai_commerce_capability", "score_range": "1-5", "evidence_required": true},
      {"name": "workforce_adaptation", "score_range": "1-5", "evidence_required": true}
    ],
    "aggregate_score_range": "6-30",
    "readiness_tiers": {
      "critical": "6-12",
      "developing": "13-18",
      "emerging": "19-24",
      "advanced": "25-30"
    }
  },
  "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": "tech_stack_findings", "type": "object", "required": true},
    {"name": "core_web_vitals_scores", "type": "object", "required": true},
    {"name": "competitor_names", "type": "array", "required": true}
  ],
  "expected_page_count": "2 + optional scorecard appendix",
  "sort_order": "sections in fixed order: summary, evidence, impact, actions; scorecard in appendix",
  "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 | + competitor-specific comparisons | + industry-specific benchmarks |
| 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 + appendix or fewer | 1.5-2 pages + focused appendix | 1.5 pages + 1-page scorecard |
| Tech stack comparison depth | Target vs. 1 competitor | Target vs. 2-3 competitors | Target vs. 3 competitors + industry benchmark |
| AI Readiness Scorecard completeness | All 6 dimensions scored | All scored with evidence | All scored with evidence + gap 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 |
| PageSpeed API returns errors | Rate limit exceeded or site unreachable | Use cached results if available (<7 days old); otherwise use WebPageTest API as fallback; note "CWV data unavailable" if both fail |
| Tech stack detection incomplete | BuiltWith/Wappalyzer returns limited data | Supplement with manual site inspection; note "partial tech stack — manual verification recommended" |
| AI Readiness Scorecard has >2 unscored dimensions | Enrichment data insufficient | Do not generate dossier — return to enrichment pipeline for deeper research |
| PDF exceeds 2 pages (excluding appendix) | 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 to fill gaps |
| Competitor data unavailable | No comparable retailers identified during enrichment | Generate dossier without competitive comparison section; note limitation; use industry benchmarks instead |
| LLM refuses to generate impact projections | Safety filter triggered by financial predictions | Reframe as "industry benchmark range" rather than "prediction"; cite study explicitly |

## 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 |
| PageSpeed Insights API | $0 (free) | $0 | $0 |
| BuiltWith/Wappalyzer lookup | $0 (free tier) | $0 | $0-10 |
| PDF generation (WeasyPrint) | $0 (open source) | $0 | $0 |
| 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** | **$10-40** |

## Anti-Patterns

### Wrong: Leading with AI hype

Dossier opens with "AI is transforming retail and your company is falling behind" or "Every retailer needs AI to survive." Result: recipient classifies the dossier as generic thought leadership spam. Diagnostic credibility is destroyed by unsubstantiated claims. [src2]

### Correct: Lead with their specific technology gap

Open with observable signals the recipient will recognize ("Your website runs Magento 1.x — end-of-life since June 2020. Your LCP is 4.1 seconds against competitors averaging 1.8 seconds."). The measured gap sells the conversation — not AI hype.

### Wrong: Comparing against Silicon Valley leaders

Dossier compares a $220M home goods retailer against Amazon, Walmart, or Shopify. Result: the comparison feels absurd and unactionable. The executive knows they are not Amazon. [src4]

### Correct: Compare against direct competitors and category peers

"HomeNest (your direct competitor, similar revenue) launched AI-powered product discovery in January 2026 and reports a PageSpeed score of 91 vs. your 32." Direct competitors create urgency; industry titans create despair.

### Wrong: Scoring AI readiness without evidence

Scorecard shows "Automation Maturity: 2/5" with justification "Most retailers of this size have limited automation." This is an assumption, not evidence. Indistinguishable from hallucination. [src1]

### Correct: Every score cites a specific observable signal

"Automation Maturity: 2/5. Evidence: BuiltWith detects no marketing automation platform, no API gateway, no headless CMS. Career page shows manual data entry roles (3 posted Q1 2026). Verification: Check BuiltWith profile for mapleandvine.com."

### Wrong: Generic "you need to transform" recommendation

Option 2 says "We recommend a comprehensive digital transformation." No price, no duration, no deliverable, no scope. Reads like every other consulting pitch. [src3]

### Correct: Specific scope, price, timeline, and deliverable

"Option 2: Full AI Readiness Diagnostic ($20K, 4-6 weeks). Deliverable: 40-page assessment across 6 dimensions, vendor-neutral technology recommendations, implementation roadmap with quarterly milestones, and ROI model. Covers data infrastructure audit, platform migration options, and AI commerce capability gap analysis."

### Wrong: Fear-mongering in do-nothing projection

"If you don't act now, your company will lose customers and eventually fail." This is speculative, unfalsifiable, and reads as a threat. [src2]

### Correct: Benchmark-based trajectory projection

"Among 200 retailers tracked by Gartner (Predicts 2026), those in the bottom quartile of digital maturity lost 3-5 points of market share annually to digitally advanced competitors. At $220M revenue, 3-5 points = $6.6M-$11M in revenue moving to competitors with better digital experiences."

## When This Matters

Use this recipe when the signal detection pipeline has identified a retailer showing digital transformation gaps — outdated tech stack, absent AI commerce capabilities, poor Core Web Vitals, or competitive pressure from digitally advanced rivals — 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). Unlike the distress dossier (which addresses operational pain), the transformation dossier addresses opportunity cost: what the retailer is losing by not keeping pace with digital-first competitors. The dossier directly feeds the Quickborn AI Readiness Diagnostic for Retail engagement pipeline.

## 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
- [Distress Dossier Template](/signal-library/retail-assets/distress-dossier/2026) — Companion template for operational distress signals
- [Retail Signal Library Overview](/signal-library/retail/overview/2026) — Framework and taxonomy this template operates within