Grounded in the institutional GP stack
We build AI into the deal and portfolio workflows of Dutch private equity firms, so sourcing, IC memos and value creation move faster and stay consistent.
It works for simple tasks (summarise, draft, reformat). On anything complex it stalls at 70-80 percent, and tomorrow starts from the same blank prompt.
ChatGPT
Claude
Copilot
Works for simple tasks (summarise, draft, reformat). On anything complex it stalls, and nothing carries forward.
The model cannot see Affinity, the data room, or last week's IC memo. Every conversation starts from zero.
The model picks the section structure, the risk weighting and the evaluation criteria without checking. You find the mismatch only in the final draft.
In a long session the original goal blurs. You asked for a thesis-level view and got company-level detail.
Tomorrow's memo starts from the same blank prompt. Your corrections, preferences and structural decisions vanish when the session closes.
An LLM is a brilliant new hire on day one: sharp, well-read, fast. What it lacks is everything a person absorbs over years inside a firm. We onboard every human, then hand AI a prompt and expect senior work.
The systems hold the data, but not in a shape an agent can use. Meaning lives in people's heads, and every run is driven by hand.
Two moves, and they only work together. Each run produces reviewed, reusable artifacts that make the next run faster, more accurate and more aligned.
Decompose each workflow into an abstraction hierarchy. Each layer produces a distinct artifact, and each artifact gets reviewed before the next layer proceeds.
A layer on top of your existing ops stack that holds persistent context (the data every run reads and writes) and packages reusable workflows, for both humans and agents.
Both are required. Together they create a compounding system. A correction or new signal enters at the layer it belongs to and re-flows from there, so you fix the cause rather than rerun the whole job.
Today, the only structured step is the lowest-value one. The judgment that matters, what "fit" means, never gets written down, so there is no place for an agent to plug in.
Filtering is the only structured step, and the analyst already does it by hand. What "fit" means is locked in the associate's head: no artifact for an agent to match against, no checkpoint for the partner to validate.
Workflows shipped end-to-end across sourcing, reporting and value creation, running live inside PE teams today.
A cockpit for investment teams and portfolio companies: valuations engine, quarterly roll-up, an 8-pillar maturity scorecard and playbook-driven task management.
→
→
→
Competitor analysis over 10,000+ deals, live dealflow analytics dashboards, and a fully automated advisory-board slide pipeline scheduled before each board.
→
→
→
Manual lead sourcing replaced with an automated pipeline that mapped the EU premium-meat market. Sales now focuses on closing, against a complete addressable market.
→
Analyst + Investment Manager. Scope on the table, design, build, blockers.
Partner + working-session group. Roll-up of decisions, scope, risk, budget.
Full sponsor group + IC member. Kickoff, mid-engagement, pre-handoff sign-off.
Founder, Poolman Ventures · Delft, NL
Building AI solutions for private equity, grounded in engineering and a deep knowledge of PE workflows. Computer science at TU Delft, econometrics at VU Amsterdam, and hands-on AI delivery inside PE firms before founding Poolman Ventures.
TU Delft · BSc Computer Science
VU · MSc Econometrics
Cloud Solutions
Vortex Capital Partners
Lexar
Today · Poolman Ventures
What are your biggest operational challenges?
What are you already doing with AI?
Where does your data live, and how structured is it?
Where do you see the highest-ROI use cases?
Which workflow would you want to tackle first?
What would make a first pilot a success?
A short Discovery sprint maps where AI plugs into your deal and portfolio work, and gives you a prioritised roadmap to act on.