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.
The series · one argument in 23 parts
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.
Why Context Windows Are Not Memory
A bigger context window is a roomier scratchpad, not memory. Durability and trust are a different problem.
The Five Types of AI Memory
Someone saying a thing once is not the same as it being true, and a flat vector store throws that away.
Why Most Agent Failures Are System Failures
When an agent fails, suspect the system before the model. Corruption enters on the write path, upstream.
Retrieval Is a Trust Boundary
Retrieval's real question is not 'is this relevant?' but 'should I believe it?' Make that decision explicit.
Time Is the Missing Dimension of AI Memory
A stale fact is not a wrong fact. Most memory systems know what but forget when, and when is everything.
Identity Is Harder Than Memory
Entity resolution is an access-control mechanism. A bad merge is a cross-tenant leak, not a data-cleaning bug.
Claude Code vs Hermes Agent: The Comparison Is Mostly a Trap
Claude Code and Hermes Agent keep getting compared as rivals, but they are good at opposite jobs. One you choose to supervise diff by diff, even though it can run unattended. The other is a persistent agent built to keep running while you are gone.
Trust the Harness, Not the Agent
I wrote that the smart move is to compose Claude Code and Hermes, then realized I had skipped the hard part. Composition is not a vibe, it is a mechanism. There are two ways to trust work that happens without you: invest in the agent, or invest in the process. Hermes does the first. The two tools I built, Stratum and Compose, do the second.
Do Memory Types Earn Their Keep?
I built a typed memory system, so when a leading minimal baseline in this year's ICLR submissions asks whether all that structure is worth it, I have to take the question personally. This is me taking it personally, and then answering it with the rest of the literature.
The Tools We Had to Build
Before Stratum and Compose had names, they were a diary of things going wrong. The origin story of the harness, told from the notes we kept while it happened: the product that forced it, the day the plan flipped, and the agent that drifted off-plan while we were designing the anti-drift tool.
Check back weekly for new essays.