DUNIN7 · LOOMWORKS · RECORD
record.dunin7.com
Status Current
Path standing-notes/loomworks-standing-note-agent-accountability-v0_1.html

Loomworks standing note — agent accountability: a responsible human, auditable and discoverable by construction

Version. 0.1
Date. 2026-06-14
Status. Standing note. Records a settled commitment: every agent action in the four-product framework carries a responsible human, and that responsibility is auditable and discoverable by construction — not by policy. The agent work (Stele's agent identity, the delegation substrate, the Companion Agents) must preserve this. Operator-facing. HTML companion to follow; this Markdown source alongside.
Source grounding. Grounded in the engine's actual actor/delegation/commit model (coupling map and operation-shape pulls, 2026-06-13/14): the ActorRef carrying kind + capability_ref, the delegation contract as a committed assertion in personal Memory, the R-B20 human-commit gate at the data layer and HTTP boundary, and FORAY as the tamper-evident attribution sink. Sits alongside the four-product + Stele standing note (v0.3) and the Stele body-of-work brief (v0.2). Settled in discussion 2026-06-14.

Plain-language summary

When an AI agent acts on someone's behalf, the framework guarantees three things, and it guarantees them by construction — meaning the system cannot produce an agent action that lacks them, the way it could if these were merely policies someone has to remember to apply. First: there is always a responsible human — the agent acts only under a grant from a named person, and the final binding act is always a human's. Second: it is auditable — every action records who did it and, for a delegated action, the exact grant that authorized it. Third: it is discoverable and tamper-evident — that record is written non-suppressibly to FORAY, so the chain from an action back to the responsible person can always be walked and cannot be quietly altered. This note locks that as a commitment the agent work must preserve. The one piece it does not yet cover — watching an agent's conduct in real time and intervening before it misbehaves — is named as future work, distinct from the accountability this note guarantees.

1. The commitment

Every agent action carries a responsible human, and that responsibility is auditable (the action records who acted and what authorized it) and discoverable (the record is tamper-evident and the chain back to the responsible person is always walkable). This holds by construction — the system cannot produce an agent action without it — not by policy that could lapse.

2. Why a responsible human is always present (by construction)

Two structural facts make the responsible human a precondition for an agent action existing, not metadata that could be omitted:

Because both are enforced in code, the responsible human is not a field that could be left blank — it is a condition for the action to occur at all. This is responsibility by construction, distinct from responsibility by policy (which can be skipped, forgotten, or disabled).

3. Why it is auditable and discoverable (by construction)

Two layers, both structural:

The full chain is always present and always walkable:

this action ← performed by this agent ← under this delegation ← granted by this person ← who committed it ← recorded tamper-evidently.

Every link lives in the data, not in a policy that might lapse.

4. Who owns which part of agent responsibility (the four-product split)

No single product owns the agent end-to-end; that separation is deliberate.

5. The boundary of this commitment — what it does and does not cover

Covered (and guaranteed by construction): after-the-fact accountability and discovery — who is responsible, what authorized the action, what was done, all attributed and tamper-evident, the chain always walkable.

Not covered (named as future work): real-time behavioral governance — watching an agent's conduct as it acts and intervening before it does something unwanted (monitoring, anomaly detection, pulling an agent's authorization mid-flight). This is Loomworks/delegation territory and is the same ground the agent-governance competitors occupy (Oasis, Astrix, Entro — governance overlays). The structural safety (the agent cannot commit) and the accountability (everything is attributed and discoverable) are built; live-conduct governance is not yet designed.

The distinction matters and should not be blurred: this note guarantees you can always discover, after the fact, who is responsible and what happened. It does not yet guarantee you can catch an agent misbehaving in the moment. Both matter; they are different pieces, and only the first is settled here.

6. What the agent work must preserve

Any future agent work — Stele's agent-authentication path, the delegation substrate, Companion Agents, an eventual behavioral-governance layer — must preserve the §1 commitment. Specifically:

A future behavioral-governance layer adds to this; it must not be built in a way that bypasses or dilutes the structural accountability above.

What this settles and what it leaves open

Settled: agent actions carry a responsible human, auditable and discoverable by construction (§1–§3); the four-product ownership split for agent responsibility (§4); the boundary between guaranteed after-the-fact accountability and undesigned real-time governance (§5); the invariants the agent work must preserve (§6).

Open (named, not designed here): the real-time behavioral-governance layer (monitoring an agent's conduct and intervening mid-flight) — Loomworks/delegation territory, future scoping. It must add to, never bypass, the structural accountability this note locks.

DUNIN7 — Done In Seven LLC — Miami, Florida
Loomworks standing note — agent accountability: a responsible human, auditable and discoverable by construction — v0.1 — 2026-06-14