In partnership with
Over the past year I’ve been building a set of AI-assisted systems across venture, product, and personal workflow. What has changed for me is not some abstract leap toward AGI. It’s the compression between intent and execution. If I can clearly define a system, I can usually build a functional version of it within days using Claude, GPT, Rork, and Vercel. The tools are beginning to understand intent well enough to extend my thinking, structure ambiguity, and scaffold architecture. The limiting factor is no longer code. It’s clarity.
I started with my own investing stack. Venture is full of pattern recognition and structured judgment, but most of it lives in messy notes and fragmented memory. So I built systems to formalize it:
VC Meeting OS (launching soon!) – Ingests transcripts, generates structured memos, detects companies and tasks, and creates a searchable knowledge layer across meetings
Interactive list of VC funds <$200M - Shai Goldman maintains a list and I turned into into a nicer interface and searchable
Automated DealFlow Pipeline – Structures sourcing, frames diligence, surfaces competitive context, and standardizes decision signals https://v0-vc-funnel.vercel.app/
Fund vs SPV Simulator – Models DPI, carry waterfalls, fee drag, and outlier scenarios to visualize real economics. https://v0-fund-vs-spv-battle.vercel.app/
VC Benchmarking App (most popular) – Aggregates vintage performance data to pressure-test allocation decisions.
Then I applied the same approach outside venture to test whether this leverage was real or just domain familiarity:
One Day App – Generates daily cognitive anchors for reflection https://apps.apple.com/us/app/one-day-at-a-time/id6757203578
Brain teaser tap game - Tap based game for colors and words https://apps.apple.com/us/app/yes-no-color-tap/id6757279621
Adaptive Kids Math Game – Adjusts difficulty dynamically based on performance https://apps.apple.com/us/app/super-smart-math-learning/id6758162811
None of this is about replacing judgment. It’s about amplifying structured thinking. The models help clarify inputs and outputs, expose edge cases, and reduce iteration time. They do not remove the need for taste, economics, or first-principles reasoning. They enhance them.
We are not at general intelligence. But we are close enough to general construction. If you can define a system clearly, you can often build version one yourself. That shift changes who can create, how fast ideas compound, and what one disciplined person can design without a team. The bottleneck is no longer technical capacity. It is imagination, intent, and the ability to think in systems.
What should I build next? Have any ideas I can help you build with!? Let me know!
Attio is the AI CRM for modern teams.
Connect your email and calendar, and Attio instantly builds your CRM. Every contact, every company, every conversation, all organized in one place.
Then Ask Attio anything:
Prep for meetings in seconds with full context from across your business
Know what’s happening across your entire pipeline instantly
Spot deals going sideways before they do
No more digging and no more data entry. Just answers.
