Learning out loud while building, teaching, and becoming.
I write about AI systems, developer tools, community, career, and the quieter lessons around the work.
- Technical notes on agents, retrieval, local AI, and the systems I’m trying to understand.
- Field notes from DevRel, speaking, teaching, and working with developer communities.
- Life in progress on career, becoming, place, family, and the bits I’m still figuring out.
Learning Out Loud
New notes when I publish. No cadence, just what I’m learning and still figuring out.
Latest Notes
Browse all notes-
Could agents learn to work better from their own runs?
Most agent memory research is about remembering the user. I built a browser agent that mines its own traces instead, and the lessons that transferred were not the ones I expected.
-
Context engineering needs a context engine
Stronger models help, but agent reliability may depend just as much on better context systems around them.
-
Borrowed confidence is fragile in agentic systems
Production-like evals revealed the retrieval architecture I actually needed and reminded me that confidence in agentic systems has to be earned, not borrowed.