AI-Powered Diligence Automation Roadmap

Prepared for Strike Capital


Executive Summary

This roadmap outlines the development of an internal AI-powered "diligence co-pilot" that automates and standardizes Strike Capital's venture diligence process. The system will evolve through three phases: V0 (Pre-Call DD), V1 (Post-Call DD), and V-Infinity (Advanced DD).

Timeline: MVP (V0) deliverable in 2 weeks upon data availability.


Technical Architecture

Core Technology Stack

Component Technology Rationale
Foundation Model GPT-4o Latest OpenAI model with superior reasoning capabilities
PDF Processing Text extraction + GPT-4o Accurate extraction with sentence-level chunking
Embeddings text-embedding-3-small Cost-effective, high-quality embeddings (1536 dimensions)
Vector Database Pinecone Managed, scalable vector storage with metadata filtering
User Interface Gradio Rapid prototyping, Python-native, built-in file handling
Initial Hosting Hugging Face Spaces Fast deployment, easy team access, low cost
Production Hosting AWS (future) Enterprise scalability and security

Why Gradio for the UI?

  1. Rapid Prototyping: Functional internal UI in hours rather than weeks
  2. Python-Native: Seamless integration with data science workflows
  3. Built-in File Handling: Native drag-and-drop support for PDFs
  4. Authentication: Built-in authentication options for internal tools
  5. Hugging Face Integration: One-click deployment to Spaces
  6. Migration Path: Can be wrapped in FastAPI for AWS deployment

Data Pipeline Architecture

Harmonic PDF Upload
    → Text Extraction + Sentence Chunking
    → Context Window (1 sentence before + after)
    → GPT-4o (structured data extraction)
    → Pinecone Vector DB (1 vector per sentence chunk)
    → GPT-4o (section-by-section generation)
    → Structured V0 DD Document

Vectorization & Chunking Strategy

Sentence-Level Chunking with Context Window

Content Type Chunking Strategy Context Window
PDF Text Sentence-level 1 sentence before + 1 sentence after
Extracted Sections Section-level N/A (stored as JSON)
V0 Document Full document N/A

Key Design Decisions

  1. Sentence-level granularity: Each sentence stored as separate vector for precise retrieval
  2. Context window: Include 1 sentence before and after for semantic coherence
  3. Metadata-rich chunks: Every chunk tagged with company_id, chunk_index, version, timestamp
  4. Batch processing: 20 chunks per API call to reduce costs

Embedding Model: text-embedding-3-small


Phase 1: V0 - Pre-Meeting DD Doc (MVP)

Timeline: 2 weeks (upon data availability)

Objective: Auto-generate a complete V0 diligence document from an uploaded Harmonic PDF report.

PDF Processing Pipeline

  1. User uploads Harmonic PDF to Gradio app
  2. Text extracted and split into sentences
  3. Context window applied (1+1)
  4. GPT-4o extracts structured data from batched chunks
  5. Each sentence chunk stored in Pinecone with embedding
  6. V0 document generated section-by-section

V0 Document Sections

  1. Deal Overview - Company, round size, stage, intro source
  2. Company Summary - Product description, users, problem solved
  3. Investors - Total count, existing investors, angels
  4. Company Overview - Founded, HQ, Headcount, ARR, Funding, Customers
  5. 2-3 Key Insights - High-signal facts from Harmonic data
  6. Team Overview - Founder bullets + team composition
  7. Market Overview - Target market, TAM/CAGR, tailwinds
  8. Competitive Landscape - Competitors, differentiation hypotheses
  9. Smart Talking Points - Credible talking points for founder call
  10. DDQs - 8-12 evidence-anchored questions

MVP Deliverables


Phase 2: V1 - Early-Stage DD Doc (Post-Founder Call)

Timeline: 2-3 weeks after V0 completion

Additional Data Sources

Key V1 Features


Phase 3: V-Infinity - Advanced DD Doc (Long-term)

Timeline: Ongoing development after V1

V-Infinity Vision


Quality Assurance & Anti-Hallucination Measures

Template Adherence

Hallucination Prevention


Deployment Timeline

Phase Deliverable Hosting Timeline
MVP (V0) Pre-Call DD Generator Hugging Face Spaces Weeks 0-1
V0 Refinement Template tuning, bug fixes Hugging Face Spaces Weeks 1-2
V1 Development Post-Call DD + Version Control AWS Weeks 3-4
V-Infinity Advanced DD System AWS Ongoing

Dependencies & Requirements

From Strike Capital

  1. Sample Harmonic PDF reports (2-3 examples) - For testing
  2. Sample DD documents (2-3 V0/V1 examples) - For template calibration
  3. OpenAI API key with GPT-4o access

Infrastructure


Questions? Let's discuss any adjustments to scope, timeline, or technical approach.