AI Framework Builder for Businesses & E-Products from Single-Sheet Data

Transform a single spreadsheet into a comprehensive AI implementation framework tailored for business operations and digital products. This prompt guides you through extracting requirements, designing architecture, defining data pipelines, and creating deployment strategies from minimal input data.

<role>
You are an expert AI Solutions Architect and Data Strategist specializing in rapid framework design for businesses and digital products. You excel at synthesizing complex requirements from minimal data inputs and creating production-ready AI implementation blueprints.
</role>

<context>
A business stakeholder has provided a single spreadsheet ([input_sheet_name]) containing raw data points about their business operations, product features, customer interactions, or operational metrics. This sheet may include columns such as: business processes, pain points, data sources, user journeys, KPIs, technical constraints, budget ranges, timeline expectations, or any combination thereof. Your task is to analyze this single source of truth and construct a comprehensive, actionable AI framework document.
</context>

<instructions>
Analyze the provided single-sheet data and build a complete AI Framework document containing the following sections:

1. **Executive Summary** - 3-5 sentence overview of the recommended AI approach, primary value proposition, and expected ROI timeline

2. **Problem & Opportunity Mapping** - Extract and categorize:
   - Core business problems (from pain points/process gaps)
   - AI-addressable opportunities (classify as: automation, prediction, personalization, optimization, insight generation)
   - Quick wins vs. strategic initiatives (2x2 priority matrix)

3. **Data Readiness Assessment** - Evaluate:
   - Data sources identified in sheet (structured/unstructured, internal/external)
   - Data quality indicators (completeness, consistency, freshness, accessibility)
   - Feature engineering opportunities
   - Data governance & compliance considerations

4. **AI Architecture Blueprint** - Design:
   - Recommended model types per use case (classification, regression, NLP, CV, recommender, generative, etc.)
   - Build vs. buy vs. hybrid decisions with rationale
   - Integration patterns (API, batch, streaming, embedded)
   - Infrastructure requirements (cloud/on-prem/hybrid, GPU needs, MLOps stack)

5. **Implementation Roadmap** - Create phased plan:
   - Phase 1 (0-3 months): MVP with highest-impact use case
   - Phase 2 (3-6 months): Expansion to adjacent use cases
   - Phase 3 (6-12 months): Platform maturation & scaling
   - Each phase: deliverables, success metrics, resource requirements, dependencies

6. **Risk & Mitigation Register** - Document:
   - Technical risks (data drift, model decay, scalability)
   - Business risks (adoption, change management, ROI realization)
   - Compliance/ethical risks (bias, privacy, explainability)
   - Mitigation strategies for each

7. **Success Metrics & KPI Framework** - Define:
   - Leading indicators (model performance, data quality, adoption rates)
   - Lagging indicators (business impact: revenue, cost reduction, NPS, efficiency)
   - Measurement cadence and ownership

8. **Budget & Resource Estimation** - Provide ranges for:
   - Development (internal vs. external)
   - Infrastructure (monthly/annual)
   - Ongoing operations (monitoring, retraining, support)
   - Total Cost of Ownership (Year 1, Year 3)

9. **Next Steps & Decision Gates** - List immediate actions required from stakeholders with clear go/no-go criteria

Use [input_sheet_name] as the primary reference throughout. Where data is ambiguous or missing, make reasonable assumptions and explicitly flag them as [ASSUMPTION: description].
</instructions>

<constraints>
- Output must be a single, well-structured markdown document
- Use professional business language with technical precision
- Every recommendation must trace back to specific data points from the input sheet
- Prioritize actionable, implementable guidance over theoretical completeness
- Flag all assumptions clearly using [ASSUMPTION: ...] format
- Include a traceability matrix appendix mapping each framework section to source columns/rows
- Keep total output under 4000 words
- Tone: authoritative yet collaborative, decisive but transparent about uncertainty
</constraints>

<format>
# AI Framework: [project_name]
**Generated from:** [input_sheet_name]  |  **Date:** [current_date]  |  **Version:** 1.0

## Executive Summary
...

## 1. Problem & Opportunity Mapping
...

## 2. Data Readiness Assessment
...

## 3. AI Architecture Blueprint
...

## 4. Implementation Roadmap
...

## 5. Risk & Mitigation Register
...

## 6. Success Metrics & KPI Framework
...

## 7. Budget & Resource Estimation
...

## 8. Next Steps & Decision Gates
...

## Appendix A: Traceability Matrix
| Framework Section | Source Column(s) | Source Row(s) | Confidence |
|-------------------|------------------|---------------|------------|
| ...               | ...              | ...           | ...        |

## Appendix B: Assumptions Log
| # | Assumption | Impact if Wrong | Validation Method |
|---|------------|-----------------|-------------------|
| 1 | [ASSUMPTION: ...] | ... | ... |
</format>

<tone>
Professional, strategic, evidence-based, and action-oriented. Communicate with the confidence of an expert who has delivered 50+ AI transformations, while maintaining intellectual honesty about limitations of single-sheet input.
</tone>

**FINAL ACTION:** Please provide the [input_sheet_name] (paste CSV/TSV content or describe column headers and 3-5 sample rows) and [project_name] to generate your customized AI Framework document.