Field notes · the expertise layer for agents

Essays on the expertise layer for AI agents.

A series on what real memory for agents demands — provenance you can audit, time as a first-class dimension, identity as an access-control boundary, and structure that knows not just what is true, but what to do and when it stopped being true.

pip install smartmemory→Read the docs

The series · one argument in 10 parts

The problem
01

Memory Is the New Attack Surface in Agentic AI

Agent memory is durable, self-modifying state nobody reviews — and it is the next real attack surface.

Check back weekly for new essays.