What I'm working on

Working notes

Short, evolving notes on agentic engineering — the thinking behind the method. Each is becoming its own piece; the drafts live behind the titles.

• Behavior over kit: what your Claude Code setup says about you

  Installed tools tell you almost nothing — the level lives in behavior. The story of the AI Usage Card: why I built it to calibrate a talk for a room of ~50 engineers, and how a level becomes a path instead of a horoscope.

• The harness, not the prompt

  The next dev skill is engineering the system around the model — context, the agentic layer, hooks, offloading, observability — not wording the request. Teams that optimize only the engine leave most of the leverage on the table.

• plan → build → review

  The loop I work by: scope the work, let the agent build against that scope, then review — with evals so "it works" is measured, not a vibe. Underneath it, one rule: match each piece of work to the lightest layer that can carry it — inline, a command, an agent, or a packaged skill. Keeps the system legible instead of a pile of clever prompts.

• Model-offloading & the price of lost confidence

  When sending non-interactive work to a smaller or local model wins — and when the harness you need to trust its output costs more than the model you saved. The tradeoff is reliability, not just price.

• What every team should know about LLMs

  The mental model that stops cargo-culting: tokens (models think in numbers, not words), the context window (why overstuffing it backfires), tools (why too many slow an agent down), and what an agent actually is — versus when you don't need one. The fundamentals that make everything above make sense.

• Getting yourself out of the loop

  The end state isn't a faster chat — it's work that runs without you. Loop engineering plus scheduling (cron) turns a good harness into unattended runs you can trust: the agent does the job on a timer, and the hooks, evals, and observability are what let you step away.