The same three questions, every time
- 01What was I trying to solve?
- 02How did I build it?
- 03What worked?
I am not a software developer. I am testing how far I can go by combining what I know about finance, investing and sport with AI tools.
Experiment 01Prototype
The court’s scorekeeper; an AI system that watches game video and keeps the player-by-player statistics table itself.
Can player-level statistics be extracted from an amateur basketball game video without anyone keeping score by hand?
June 2026
Experiment 02Prototype
A tool for angel investors that turns a start-up pitch deck into a structured analysis with the discipline of an institutional investment committee.
How close can an angel investor get to the discipline of an institutional fund’s investment memo, starting from a single pitch deck?
March 2026
Experiment 03Prototype
An experiment in turning speech into text from lip movements alone, in video without sound.
Can speech be read from video alone, without any audio?
September 2026