AI-Powered VC Intelligence
An AI-driven due diligence platform that automates startup research, 8-category intelligence aggregation, and investment report generation. Powered by Claude Sonnet 4 with Mistral and OpenAI fallback — 6-dimension scoring, 5,000+ outcome patterns, EU regulatory intelligence built in.
6-Dimension Scoring
Claude + Mistral + OpenAI
8 Data Source Categories
Stage-Calibrated
The Problem
Why VC due diligence is broken
Analysts spend 40+ hours per deal manually researching founders, markets, and competitors across scattered sources.
Quality varies by analyst. No standardized framework means critical signals get missed on some deals.
Weeks to produce a single investment memo. Hot deals close before diligence is complete.
Insights from past deals aren't reused. Each evaluation starts from scratch with no institutional memory — and EU-specific data (EIC grants, BPI France, INPI filings, AMF disclosures) is completely ignored.
Features
End-to-end AI-powered due diligence pipeline
kairos-vc.features.items.sourcing.description
kairos-vc.features.items.duediligence.description
kairos-vc.features.items.founders.description
AI-generated competitive landscape analysis with positioning, differentiation assessment, and moat evaluation.
kairos-vc.features.items.termsheet.description
kairos-vc.features.items.monitoring.description
Performance
What Kairos VC delivers
8
Intelligence source categories
6
Kairos Score dimensions
<30m
Full report generation
3
Stage-calibrated models
4
LLM providers supported
360°
Deal assessment coverage
Tech Stack
Python, FastAPI, PostgreSQL + pgvector, Redis, SQLAlchemy, Alembic
Claude Sonnet 4 (primary reasoning), Mistral + OpenAI (fallback), Ollama (local), sentence-transformers, spaCy NLP
Next.js 16, React 19, Tailwind CSS, Radix UI, Recharts, Zustand
Playwright, Selenium, BeautifulSoup, httpx, LinkedIn, GitHub, F6S
Docker Compose, JWT auth, API keys, structlog, rate limiting
Pytest, Playwright E2E, Vitest, TanStack Query
Source Code
The Kairos VC platform source code is available upon request for evaluation and partnership purposes.
To access the source code, please sign our Non-Disclosure Agreement. This is a standard legal formality.
Looking for AI-powered due diligence or startup scaling expertise? Explore our consulting services.
70% of AI pilots never reach production. Get the playbook for the 30% that does.
Unsubscribe anytime. No spam, ever.
Architecture
Three layers: 60+ dashboards built for the workflow, 44 backend modules covering every deal stage, and a swappable LLM backend that keeps you off vendor lock-in.
Next.js 16 App Router, 60+ dashboard pages, Tailwind CSS 4, shadcn/ui, React Query. Pipeline boards, founder pages with 8-dimension scoring, competitive-landscape maps, portfolio monitoring dashboards. The UI a partner actually opens.
FastAPI backend covering deal sourcing, due diligence, founder scoring, technical assessment, competitive intelligence, term-sheet drafting, post-investment monitoring. Stage-calibrated logic — what matters at seed is not what matters at Series C.
Default Claude with a one-config migration path to Mistral, Ollama, or HuggingFace. Same prompts, same scoring rubrics, your choice of model and locality. Sovereign deployments are a switch, not a rewrite.
8-dimension founder scoring
Standardised scoring is what makes a 'we liked the team' deal memo defensible against the next deal that didn't get funded. Kairos breaks every founder into eight dimensions, each with a public rubric. Below: what each dimension actually measures.
DIM 1Domain depth × execution velocity × team-fit signals (co-founder dynamics, prior shipping evidence, hiring track record). LinkedIn enrichment + public-commit cadence + interview transcripts.
DIM 2Bottom-up TAM with sources, top-down sanity check, 5-year growth thesis, regulatory tailwind/headwind. Penalises 'all of the EU is our market' with a structured why-now requirement.
DIM 310x-better-than-status-quo evidence, user-research artefacts, retention curves where available, real-world friction map. Penalises demo-only product claims.
DIM 4Revenue curve quality (not just absolute number), net dollar retention, sales-cycle compression over time, organic vs paid mix. Stage-calibrated — what matters at seed is not Series A.
DIM 5Burn multiple vs stage, payback period on CAC, runway clarity, prior round price-to-quality ratio. Flags 'too much capital for the milestone delivered.'
DIM 6Technical assessment by domain. Generated by the LLM backend with stage-calibrated rigour — different rubrics for Seed and Series C. Identifies signal vs noise in the founder's claimed novelty.
DIM 7Data moat depth, switching cost analysis, regulatory moat where applicable (e.g. clinical, defence), network-effect curve shape. The 'why does this not get crushed by Big Tech?' answer.
DIM 8Sales motion clarity, ICP discipline, channel quality, founder-led-sales transition plan. Penalises 'we'll hire a VP Sales to figure it out' answers.