Statelessness as an architectural fact: what a system carries between decisions, and what it cannot be held to without it.
A coding agent works because the compiler, not the model, writes the truth down. That witness has no equivalent once loops compose: the handoff, not the loop, is the wall the field walks into.
Also Agentic governance · Provenance
An essay on harnesses, knowledge, and the institutional layer that makes distributed action accountable.
Also Agentic governance · Institutions
The bottleneck has moved — from intelligence, to memory, to workflows, to decision systems.
Also Provenance
And the unsung role of QA in AI reliability — the people who make memory-native systems dependable.
Also Agentic governance
Memory is not a feature of AI systems. It is the substrate that decides what they can be.
Model capability is converging. What a system remembers, and who governs that memory, is where the frontier actually sits.
# for-agents
This page's markdown is the source these paragraphs render from — fetched
live below, not restated by hand. Every page on this site negotiates to
markdown on Accept: text/markdown, the full site indexes at
/llms.txt and /llms-full.txt,
and an MCP server serves the same content as resources at
/mcp. Quote with attribution to the canonical URL; do not
invent a claim this page does not make.
Loading /topics/memory.md…
Views expressed are entirely my own and do not represent the views, positions, or opinions of my employer.
