Essays on context, agents, meaningful work, and systems that make people more capable.
A small public notebook for the ideas behind the work: production AI, human-centered automation, provenance, complexity, design, and the future of careers.
Presetter began as a way to stop copying config files. Version 9 turns that small irritation into a clearer system for preserving engineering decisions across projects, packages, and time.
The smallest loop that calls a model, dispatches its tools, keeps a memory, and decides when to stop — and what each of those choices is actually saying.
Context shapes decisions, creates leverage, and compounds over time. The next durable AI products will treat context as infrastructure, not prompt decoration.
Agent demos are optimized for spectacle. Production agents need memory boundaries, verifiable action, recovery paths, and a clear theory of when not to act.