The Cognitive Fab blog

Provable Trust

Assurance that rests on "our monitoring is very good" is a promise. Provable trust rests on a proof and a receipt. Writing on what that distinction means in practice — sector by sector, and control by control.

Sector
Topic
16 August 2026 · 8 min read · Field note

A count is not a verdict

Claude Code now counts the rules a folder pre-approves — 278 in this repo — and drafts a trust boundary from evidence rather than a questionnaire. Both are the right instinct, and both stop one step short of the question those labels make askable: can the permitted operations, in some order, carry untrusted input out with no gate in between?

Cross-sector Governance Runtime enforcement
12 August 2026 · 7 min read · Field note

Cloudflare just gave AI agents a wallet

It comes with real spending controls — a budget, a per-payment limit, an approved-merchant list. Good controls. They also answer a narrower question than they look like they do: a $10 cap under a $500 budget authorizes fifty transactions, and money has no undo button.

Financial services Governance Runtime enforcement Formal verification
4 August 2026 · 13 min read · AI Agent Governance, Part 1 of 5

When every step is allowed

An agent can take a sequence of authorized actions, and the sequence as a whole causes harm. Hugging Face and GitLost show the failure is architectural, not operational — and none of the four control layers answers the question it poses.

Cross-sector Governance Runtime enforcement Monitoring & audit
1 August 2026 · 7 min read

When banking agents can act, the edge is proving what they can't

Banking's intelligent operating model rests on governance and trust. Neither can stay a promise once agents can act — a per-action check never holds a fact about the set of actions, and the exposure lives in the gaps between the checks.

Financial services Governance Monitoring & audit Formal verification
No posts match that combination yet.