Start here

New here? This is the curated path through my work — the pieces I'd point you to first, grouped by what they're about rather than when I wrote them.

Agents & long-running execution

Making capable models stay coherent across long, multi-session work.

Evaluation & reliability

How you know an AI system actually works — feedback loops, reward design, measurement.

Retrieval & prompt selection

Choosing the right context and the right prompt, adaptively.

Developer tooling

Tools and workflows that make AI assistants useful on real work.

Or browse everything: all writing · all work · notes.