DepthChartIQ
DepthChartIQ helps college basketball players choose a program. It projects a player's minutes at each school, with a range around each number.
It started as a prototype its founder built, and I rebuilt it into a production app with billing in about nine weeks. The web and mobile apps share one prediction service, and Spotter runs as its own service.
The prediction models are the company's. I built the service that runs them. Each prediction shows a calibrated range. When there isn't one for a player, the app says so. Before the service went live, I checked its answers against the model's own test results.
Every model call goes through one gateway the company runs, which shows what each part of the product spends on models.
Spotter
An AI advisor that will talk a player and their parents through a transfer or player-development decision. It's part of DepthChartIQ.
- Players and parents each get their own set of tools.
- It asks a player only for what it needs to answer.
- It marks anything it finds on the open web as unchecked.
DepthChartIQ program pages
Profiles for D1 men's and women's basketball programs on DepthChartIQ.
- A pipeline I built adds each program's logo and arena photo when it can find a usable one.
- A vision model checks the images.
Public program directory, captured Sept 29, 2026.
- Data
- Cloudflare R2
- Infrastructure
- Inngest
Stack
- Languages
- TypeScriptPython
- Mobile
- Expo
- Models and agents
- LiteLLM
- Data
- Cloudflare R2
- Payments
- Stripe
- Infrastructure
- InngestFly.ioSentryOpenTelemetry