Spec-Driven Development, but the Specs Are a Graph
A 12-lesson course that rebuilds the DeepLearning.AI spec-driven development tutorial on Rust + sphinx-needs — and the AgentClinic domain you build to learn it.

Software isn't art; it's engineering. Complexity is the enemy of security. I don't look for 'intricate details'—I try to eliminate them. By keeping the code and architecture simple, I build systems that are actually robust. You can't secure what you can't understand.
I spent most of the last 15 years writing code, designing, securing and breaking systems. Some of my random thoughts are collected in my blog.
A 12-lesson course that rebuilds the DeepLearning.AI spec-driven development tutorial on Rust + sphinx-needs — and the AgentClinic domain you build to learn it.
Why unstructured AI coding burns your budget and still delivers incomplete results — and what a queryable traceability graph changes about that.
Every team that needs PLC data writes its own bridge. Adsify is the one I got tired of rewriting.
Inspiration comes from looking at the data. My career started with game hacks—poking at binaries to see what the hardware was doing. Since then, I’ve worked across different domains and languages, always looking for the simplest way to make the computer do the work.





