Memory, Routing, and Bounded Ownership in Agent Teams
Why agent teams scale through scoped memory, specialist lanes, explicit routing, and operator-visible handoffs, not by giving every agent more context.
The blog
Writing on AI development, agentic tools, and building software products.
Why agent teams scale through scoped memory, specialist lanes, explicit routing, and operator-visible handoffs, not by giving every agent more context.
Why I am building OpenClaw around visible work, clear ownership, approvals, and intervention.
Everyone assumes AI plus email equals full automation. I went the other direction. Here's why manual-first beats hands-off for B2B outreach, and how the pipeline actually works.
How running my woodworking factory taught me more about building software than I expected, and what the transition to AI engineering looked like from the inside.