I write about what I learn while working with AI — tools I try, workflows I explore, and ideas that turn out to be useful.
This site is a personal notebook for things I’m learning about AI — tools I try, workflows I explore, and ideas that seem worth writing down.
Recent writing
- OpenClaw's Memory Stack: A Local-First Map of What Lives Where Mar 31, 2026
A practical walkthrough of OpenClaw's five memory mechanisms, how they work together, and why I still prefer a local-first approach to agent memory.
- Agents Are Not Prompts Mar 28, 2026
AutoHarness and Anthropic point to the same lesson: agent performance depends less on prompt cleverness than on the harness that constrains, evaluates, and carries work forward.
- Why I Wrote a Skill to Review Skills Mar 27, 2026
If stable AI performance depends on reusable skills, then skills themselves need a review method before they can be trusted.
Subscribe to my learning notes
If you’d like to follow what I’m learning about AI tools and workflows, you can subscribe below.
Subscribe to My Notes