From memory to nervous system
The first problem with running multiple agents is that they forget. The second is that they can't coordinate. A state layer that solves storage first and then adds signaling becomes a nervous system, not just memory.
Posts
Essays, technical articles, and thoughts on building sovereign systems.
The Human Inversion
When capable AI absorbs most artifact production in the execution middle, human leverage concentrates at foundation and review. Coherence stops living in hallway handoffs and starts living in explicit standards, cross-readable artifacts, and judgment you can defend at volume.
Your agent fleet can build trustworthy state with their own keys
When many agents write to one memory, you need proof on every row: who signed, what they were allowed to do, and no shared bearer secrets. Neotoma integrates AAuth so each agent signs with its own key and writes through grant-scoped admission.
When building got easy, the PM job got harder to explain
On the PM role, AI, and the strange decision to define your job around the skill that just got commoditized.
Plancast wasn't early, it needed agents with a proper substrate and mesh
Fourteen years ago I wrote a postmortem for Plancast. Reading it again now, the failure modes weren't really about product mechanics; they were about missing personal AI agents, a proper substrate for them to write to, and a sovereign mesh between them. All three exist now, and the original mission becomes tractable in a way the feed era never could.
OpenClaw plugin for Neotoma gives your agent memory it can't corrupt
OpenClaw stores memory in markdown files. Neotoma v0.4.3 plugs in natively as a structured state layer underneath, giving OpenClaw agents provenance, entity resolution, and versioned history without replacing the agent.
The markdown memory ceiling
Three independent AI agent platforms worth billions converged on plain text files for memory. The convergence validates the problem. The failure modes they share define what comes next.
When agents share state, everything breaks
Most teams bolt agent memory onto whatever database they already have. It works until two agents write to the same store. Then one bad write propagates at machine speed, triggering downstream actions before any human can intervene. The industry is heading toward a trust crisis that retrieval optimization won't fix.
Your agent harness owns context, not truth
Sarah Wooders argues memory is the harness. She's right about context management. She's wrong that context is the whole problem.
Agent memory breaks at 500K tokens, not 10 million
BEAM tests retrieval at 10 million tokens. State integrity degrades at 500K. The two failure modes activate at different scales, and nobody benchmarks the earlier one.
No AI memory benchmark tests what actually breaks
The metrics that drive adoption in AI memory are almost all retrieval metrics. Good retrieval is necessary. No widely used benchmark tests what happens to stored data after agents write to it.
Agent-mediated customer research and onboarding
Eighteen human product evaluators ran the same evaluation prompt through their AI tools. The writeups were sharper than any call. That feedback reshaped the product’s positioning : and then its acquisition flow. The homepage now asks agents to evaluate, not humans to sign up.