Writing

One publication. Many difficult questions.

Essays, research notes, experiments, and field notes about intelligent systems and the real engineering required to make them useful.

Topics describe what an idea is about. Formats describe what kind of writing it became.

Featured / opinion

AI agents are systems problems

Models matter. But architecture, context, permissions, evaluation, and operations decide whether an agent becomes infrastructure or remains a demo.

Aug 20, 2026

opinion · 7 min

The difficult part of useful agentic AI is not the model call. It is everything required to make judgment and action reliable.

Aug 18, 2026

article · 6 min

Human approval, provenance, and permissions should shape an agent system from the beginning—not arrive as an afterthought.

Aug 15, 2026

paper · 9 min

A research note on giving efficient local models and larger central systems different jobs inside one security architecture.