Notes from the build.
Short essays on building agents that stay under human control, running LLMs on the edge, and the tooling in between.
Giving agents a map: the teamwork graph
Agents don't fail because they can't reason. They fail because they don't know how the pieces of an organization connect.
#agents#graphs#mcp
On-device LLMs make privacy a feature, not a promise
When the model never leaves the device, 'we don't store your data' stops being a policy and becomes an architecture.
#on-device#privacy#gemma
Why every real agent needs a human in the loop
Full autonomy is a demo feature. Approval gates are a product feature.
#agents#design