/ doctrine
The Signal,
Not The Noise.
The AI era has produced more demos than it has solutions. More hype than heat. More frameworks for thinking about building than actual things built.
This site is not a portfolio. It’s not a blog. It’s not a thought leadership platform.
It’s a lab.
Everything here was built, tested, broken, or shipped by one person. No team. No committee. No venture backing. Just a workstation in Wisconsin, a stack I trust, and a high tolerance for things failing at 2 a.m.
I apply one standard to every experiment: does it solve a real problem, or does it make me feel smart? If it’s the second one, it doesn’t ship.
Four Rules
no exceptions- 01
Real problems.
Every experiment has a target. A measurable outcome. An actual human on the other end who benefits if it works. AI used to generate lorem ipsum is a parlor trick. AI deployed against a production workflow that costs someone money when it fails — that’s infrastructure.
- 02
Ship or it doesn’t exist.
I don’t write about things I’m planning to build. I write about things I built. The draft, the failure, the version that worked — those all count. But they have to be real.
- 03
One engineer.
No dilution. I own every decision: the schema, the API contract, the UX, the production deploy, the 3 a.m. incident. That constraint is not a limitation. It’s a forcing function for discipline.
- 04
Discipline over hype.
Explicit errors, typed contracts, zero silent failures, minimal dependencies. The frontier moves fast. The fundamentals don’t.
“Make it work. Make it right. Make it fast. In that order.”
— Kent Beck
This is what that looks like, applied to AI.