Case study · Venture capital
AI due diligence for investors
Technical reviews of early-stage AI startups for venture investors, plus retrieval tools that turn a data room into a first-draft investment memo.
- Client
- Venture investors in early-stage AI
- Result
- Seed and Series A deals
- Stack
- Retrieval-augmented generation, Vector databases, LLM APIs, LangGraph / CrewAI / AutoGen
The problem
Investors need to know whether a startup’s technology is defensible and will scale. Each deal arrives as thousands of pages of decks, financial statements and technical papers.
The work
- Reviews of each startup’s model architecture, data advantage and infrastructure.
- Tests of agent workflows: multi-step reasoning, tool use, self-correction and error recovery.
- Retrieval-based tools that condense deal documents into a structured first-draft memo.
- Ongoing tracking of the GenAI stack (LLMOps, vector databases, agent frameworks) to spot gaps worth funding.
Outcome
Investment teams get an engineer’s read on each company and a structured summary of the data room to work from.
The client isn’t named, to respect confidentiality. I can share more detail on a call where permitted.
Talk about a similar projectMore work
From LLM wrappers to agents
Design reviews and workshops for venture-backed engineering teams moving from a single LLM call to agents built on LangGraph, CrewAI or AutoGen.
Several portfolio companies
Cross-asset research platform
Pipelines and Dash apps that give a sovereign wealth fund’s bonds and FX researchers one place to pull, compare and backtest market data.
In daily use by research and trading for 3+ years