Notes for Machines

These notes cover the same ground as the main Writing section, but written in a different register: definitions first, claims stated one at a time, and every qualifier attached to the claim it limits, so a single sentence can be quoted without losing the condition that makes it true. That is how a language model or an agent reads a page — in fragments, out of order, one claim at a time. Writing this way is a way of keeping a claim honest even after it leaves the page. Humans are welcome to read them; the flowing prose versions of the same arguments live in Writing.

Same discipline as the rest of the site: each note stands on its own, every claim is checkable against the live system, and each page also serves a hand-written Markdown version to any reader that asks for text/markdown.

Self-Signed Evidence Is Not Evidence — a cryptographic signature proves a record was not changed relative to a key; if the audited party holds that key, the record is self-attestation; custody, meaning a copy held by a party that is not the audited one, is what converts it to third-party evidence. Definitions, claims, and the AgenticRail archive implementation, stated flatly. Published 23 July 2026.

Unrecorded Oversight Is Indistinguishable From None — a requirement to have a human in the loop is not evidence that one was; an approval with no ordered, verifiable record is indistinguishable from no approval; sequence enforcement makes oversight provable by denying the action until the review step has a receipt. What the receipt proves, and the two honest limits (procedure not cognition; custody). Published 23 July 2026.

The formal, fingerprinted documents — the enforcement specification, evidence completeness, and the provable-safeguards note — live under /spec/. Machine-readable indexes: llms.txt, llms-full.txt, verified-claims.json.