Selected writing
Evidence, authority, and the cost of another question
How I separate evidence, authority, and spending from an agent’s choice of what to investigate.
Designing AI agents for decisions that keep changing
The personal starting point, the business question, and what it takes to keep a recommendation useful as new information arrives.
A little background
I studied Computer Science and Business at the University of Michigan. My background spans cloud infrastructure and startups, and I tend to gravitate toward problems where the technical choices and the business question are tangled together.
With AI, I’m particularly interested in the gap between a convincing answer and a recommendation I could defend. A personal rebuild-analysis project gives me a concrete way to explore that gap. I haven’t bought a car at auction; I’d like to understand the economics before I talk myself into it.
I write about what I’m learning on Substack.