Yuri Gui

The AI Frontier in Venture Capital

Where AI capability ends and human judgment begins — a living record.

This document tracks what AI can and cannot reliably do in venture capital analysis. It reflects the state of the art across all AI tools on the market — not only what claude-vc provides.

Scope of claude-vc

Claude-vc is an open-source Claude Code skill plugin focused on deal screening, investment memos, cap table modeling, term sheet analysis, financial modeling, and KPI reporting. It does not intend to be an all-encompassing VC platform. It will gradually expand, but it does not aim to replicate proprietary tools like Harmonic (deal sourcing), Affinity (CRM), PitchBook (data), Luminance (legal review), or Standard Metrics (portfolio monitoring).

Achieving state-of-the-art performance in venture capital AI today requires integrating a dozen or more MCP servers, proprietary data subscriptions, and specialized platforms. Without a larger maintainer community, it is not feasible for a single open-source plugin to maintain those integrations. This document therefore serves as a map — it tells you what is possible with the right combination of tools, even where claude-vc does not yet cover it.

Status key

Last reviewed: 2026-03-16


Deal Sourcing & Outreach

CapabilityCan DoWIPCannotEnabler
Inbound pitch triage and initial scoringExtended thinking, Harmonic signal detection
New investment opportunity identificationHarmonic, Grata, EQT Motherbrain
Founder relationship trackingAffinity AI, 4Degrees
Co-investor and syndicate coordinationCRM integrations, email MCPs
Back-channel reference callsNeeds real-world interaction
LP and stakeholder communicationsLLM drafting, email MCPs

Market Research

CapabilityCan DoWIPCannotEnabler
Industry landscape synthesis from public sourcesWeb search, Perplexity, Claude
Market sizing (TAM/SAM/SOM) from pitch materialsPDF vision, extended thinking
Competitive landscape mapping from web researchWeb search tool use
Sector trend analysis from public dataWeb search, long-context reasoning
Regulatory environment scanningWeb search, legal corpus MCPs
Real-time market data and indicesBloomberg MCP, Refinitiv MCP
Primary market research (surveys, interviews)DiligenceSquared AI voice agents
Emerging market and whitespace identificationHarmonic signals, Grata agentic search

Company Research

CapabilityCan DoWIPCannotEnabler
Pitch deck data extraction (PDF)PDF vision, multimodal understanding
Public company profiling from web sourcesWeb search tool use
Report generation (DOCX and markdown)Native file generation
Private company data accessPitchBook Navigator, Crunchbase, Grata
Deal screening with structured scoring (0-100)Parallel subagents, extended thinking
Investment memo generation (10-section format)Parallel subagents, long-context generation
KPI benchmarking by auto-detected company typePython tool use, extended thinking
Comparable company analysis with market dataPitchBook comps, Grata precedent transactions
Factual claim verification against primary sourcesWeb search with source citations
Systematic data room cross-referencingHebbia Matrix, Luminance

Product Assessment

CapabilityCan DoWIPCannotEnabler
Product claims extraction from pitch materialsPDF vision, multimodal understanding
Feature set and roadmap summarizationLong-context reasoning
Technical architecture assessmentCode analysis tools, computer use
User retention and engagement pattern analysisAnalytics platform MCPs
Product-market fit validationNeeds usage data access, user research
Hands-on product testing and UX evaluationNeeds computer use at scale

Financial Analysis

CapabilityCan DoWIPCannotEnabler
Burn rate and runway analysisPython tool use
3-statement model generation (P&L, BS, CF)Python tool use, extended thinking
Unit economics computation (LTV, CAC, payback)Python tool use
Revenue projections (3-5 year forward)Python tool use, extended thinking
KPI auto-detection and health assessmentExtended thinking, industry benchmarks
Cohort and retention curve analysisAnalytics MCPs, Python tool use
Bulk portfolio-wide financial analysisChatFin, Chronograph, 1M context
Audit-grade financial statementsNeeds formal verification, licensing

Valuation

CapabilityCan DoWIPCannotEnabler
Pre/post-money round modelingCarta, Pulley, Python tool use
Multiples-based valuation with industry rangesPython tool use, reference data
DCF analysis from user-provided assumptionsPython tool use, extended thinking
Comparable company analysis with live dataPitchBook comps, Grata deal data
Precedent transaction analysisGrata (EBITDA/revenue multiples on 800K+ deals)
Conviction weighting on valuation outputsNeeds calibrated confidence, human judgment

Deal Structuring & Negotiation

CapabilityCan DoWIPCannotEnabler
Cap table modeling and dilution analysisCarta, Pulley, Python tool use
SAFE and convertible note conversionCarta, Pulley, OCF standard
Multi-series liquidation waterfallCarta, Pulley, Eqvista
Exit scenario modeling at multiple valuationsCap table platforms, Python tool use
Term sheet red-flag identification (NVCA baseline)Spellbook (10M+ contracts reviewed)
Cap table platform sync (Carta, Pulley) via MCPCap table platform MCPs
Negotiation strategy and counter-offer structuringNeeds relationship context, game theory
Binding legal document generationNeeds legal licensing, formal verification

Technical Due Diligence

CapabilityCan DoWIPCannotEnabler
Technical claims summarization from materialsLong-context reasoning
Technology stack identificationWeb search, code analysis tool use
IP and patent strength evaluationIPRally, Patsnap, Patlytics
Codebase quality and architecture reviewCode analysis agents, computer use
Scalability and infrastructure assessmentNeeds system access, load testing
Technical team capability evaluationNeeds real-world interaction

Legal Due Diligence

CapabilityCan DoWIPCannotEnabler
Common provision pattern flaggingSpellbook, Luminance
NVCA baseline term comparisonSpellbook VC clause library
Contract review (SHA, IP assignments, employment)Luminance, Kira/Litera (64% Am Law 100)
Regulatory compliance analysisEmerging legal AI tools
Legal opinions and formal adviceNeeds legal licensing
Cross-jurisdiction tax and structuringNeeds tax law MCPs, licensed professionals

Financial Due Diligence

CapabilityCan DoWIPCannotEnabler
Individual financial document analysisHebbia Matrix, PDF vision
Private company financial dataPitchBook, Morningstar, Grata
Financial model internal consistency checksPython tool use
Portfolio company data connectivityStandard Metrics, Chronograph MCPs
Data room systematic cross-referencingHebbia Matrix, Luminance
Historical financials verificationNeeds SEC EDGAR MCP, audit trail access
Tax and transfer pricing analysisNeeds tax law MCPs, licensed professionals

Portfolio Management

CapabilityCan DoWIPCannotEnabler
CRM and deal pipeline trackingAffinity AI (auto-capture, relationship intel)
One-time portfolio summary generationExtended thinking, structured output
Board deck preparation assistanceLong-context generation, native file output
Ongoing portfolio monitoringStandard Metrics, Chronograph, ChatFin
Scheduled recurring reportsStandard Metrics, Visible.vc automation
Anomaly detection and alertsChatFin anomaly engine
LP reporting preparationclaude-vc portfolio skill, Standard Metrics

Investment Decision & Closing

CapabilityCan DoWIPCannotEnabler
IC preparation materialsExtended thinking, long-context generation
Decision framework structuringExtended thinking, structured output
Invest/pass recommendationNeeds calibrated confidence, human judgment
Founder and team qualitative assessmentNeeds real-world interaction
IC facilitation and votingNeeds multi-user collaboration
Closing coordination and executionNeeds legal tooling, payment systems
Post-closing deliverable managementWorkflow automation, persistent agents

Changelog

Track when capabilities cross the frontier — things that became feasible, and things we discovered AI still can't do. Dates reflect when the enabling product or feature shipped, not when adoption reached maturity.

DateChangeCapability affectedDirectionEnabler
2022-09AI contract drafting and reviewCommon provision pattern flaggingHuman -> WIPSpellbook launch
2022-11AI-powered deal sourcing signalsNew investment opportunity identificationHuman -> WIPHarmonic Series A, early product
2022-11Basic memo drafting and market summariesInvestment memo generationHuman -> WIPChatGPT (GPT-3.5)
2023-03Professional-grade investment analysisIndustry landscape synthesisWIP -> Can DoGPT-4 reasoning quality
2023-06Structured API tool calling for data accessKPI benchmarking, financial model checksHuman -> WIPOpenAI function calling
2023-07Full document analysis (100K context)Pitch deck data extractionHuman -> Can DoClaude 2
2023-09AI relationship intelligence in CRMFounder relationship trackingHuman -> WIPAffinity AI features
2023-11Reliable structured data extractionKPI benchmarking, deal screeningWIP -> Can DoGPT-4 Turbo, JSON mode, 128K context
2024-03Pitch deck and chart visual analysisPitch deck data extraction, product claimsHuman -> Can DoClaude 3 vision + 200K context
2024-05AI-orchestrated multi-tool workflowsDeal screening, financial model generationHuman -> WIPClaude tool use GA
2024-06Cost-effective AI analysis at pipeline scaleInbound pitch triageWIP -> Can DoClaude 3.5 Sonnet
2024-08Perfect structured extraction (100% schema)KPI benchmarking, financial model checksWIP -> Can DoOpenAI structured outputs
2024-09Native PDF document processingPitch deck data extraction, document analysisHuman -> Can DoClaude PDF support
2024-10Computer-use automation for legacy toolsTechnical architecture assessmentHuman -> WIPClaude computer use beta
2024-10Multi-agent due diligence workflowsSystematic data room cross-referencingHuman -> WIPCrewAI maturity, AutoGen
2024-11Natural-language private company data queriesPrivate company data accessHuman -> WIPPitchBook Navigator + OpenAI
2024-11Standardized AI-to-data connectivityPortfolio company data connectivityHuman -> WIPMCP (Model Context Protocol)
2025-02Deep financial reasoning on demand3-statement model generation, DCF analysisHuman -> WIPExtended thinking (Claude 3.7)
2025-02Agentic coding for custom VC toolsUnit economics computation, burn rate analysisHuman -> WIPClaude Code research preview
2025-03Real-time market intelligence in AISector trend analysis, competitive mappingHuman -> Can DoClaude web search
2025-05Production-grade agentic VC toolingReport generation, exit scenario modelingWIP -> Can DoClaude Code GA
2025-09End-to-end document productionReport generation (DOCX), board deck prepHuman -> Can DoNative file generation
2025-11AI-accessible private market data at scalePrivate company data accessWIP -> Can DoPitchBook Navigator MCP
2026-02Full data room in single contextSystematic data room cross-referencingHuman -> Can Do1M token context (Claude 4.6)
2026-03PitchBook data in conversational AIComparable company analysis, precedent txnsWIP -> Can DoPitchBook + Perplexity MCP
2026-03claude-vc v1.2.0 baseline----Initial AI Frontier assessment
2026-03Parallel multi-agent deal screeningFull screening with 6 concurrent agentsWIP -> Can Doclaude-vc v1.3.0 parallel agents
2026-03Side-by-side company comparisonStructured comparison of 2-4 companiesWIP -> Can Doclaude-vc v1.3.0 vc-compare
2026-03Customizable due diligence checklistsStage+sector-specific DD checklist generationCannot -> Can Doclaude-vc v1.3.0 vc-diligence
2026-03One-shot portfolio reporting for LPsLP-ready portfolio summary from provided dataCannot -> Can Doclaude-vc v1.3.0 vc-portfolio

Footnotes

  1. Enabler = the AI product, feature, or integration that made (or would make) this capability possible. Common enablers: extended thinking (chain-of-thought reasoning), Python tool use (script execution for verified calculations), web search (real-time public information), PDF vision (multimodal document understanding), MCP (Model Context Protocol server integrations), native file generation (DOCX/XLSX/PPTX output), 1M context (full data room ingestion), structured output (reliable JSON schema adherence). Product names (Harmonic, PitchBook, Spellbook, etc.) refer to best-in-class commercial tools.


Source: claude-vc/docs/frontier.md