Writing
Notes from the work.
Architecture, agent workflows and the decisions behind them. Essays from this site and Medium, collected in one place.
Featured writing appears first, followed by dated articles. Older technical guides describe the tools as they were at the time.
-
Medium · Featured
What the Reviewer Notices
An Outreach Skill pilot made me question what we give away when we tell an AI reviewer what to look for.
-
Medium ·
Building a Self Improving AI Agent with Gemini Free Tier
A practical account of separating automated memory maintenance from human approval of changes. Published on Medium in February 2026; tooling and pricing reflect that date.
-
On this site ·
Signal, Policy, Execution: Why Replay Works
Separating signal, policy, and execution gives you a system you can replay, audit, and evolve without pretending the model is perfect.
-
On this site ·
Policy-Gated Agents in Production: Constraints, Eval, Observability
Production agent systems need explicit policies, measurable evaluations, and telemetry that makes human oversight practical.