Defines a partition boundary finer than tenant level — an engagement, a matter, a project — within which content and authorship are scoped, independent of role…
The logged record of a single Agent Policy evaluation — which policy fired, what action it was evaluated against, and what it resolved to.
A proposed or executed action taken by an AI agent on the organisation's behalf, carrying its origin (synthesis-triggered, per the domain's scope test), the…
A governance rule evaluated at the moment an agent attempts a tool call, resolving to block, filter, or flag for review.
A retrievable fragment derived from a Source Document or Knowledge Item, carrying its own inherited permission scope and embedding.
Evidence that a specific person completed a specific Procedure, at a specific version, including any required photo or comprehension-check evidence.
A detected disagreement between two live, currently published content items, requiring routing to an accountable owner for resolution. The domain's direct…
A captured structured elicitation session with a subject-matter expert — transcript, extracted themes, and any flagged gaps.
The synthesised response to a Query, carrying its citations, confidence signal, and — where applicable — a flagged contradiction.
A resolved workflow item — a support ticket, an on-call page, a closed thread — that byproduct capture (CAP-161) can draw from to draft new knowledge.
A deliberately authored or curated piece of content — a card, an article, a policy — with an accountable owner and a lifecycle. The central registry entity…
A normalised access-control entry tied to a piece of content, translated from whatever native scheme (ACL, RBAC scope, sensitivity label) the source system…
Structured, step-sequenced, safety- or compliance-critical content — an SOP or work instruction — with its own versioning and sign-off requirements distinct…
A single ordered step within a Procedure, carrying its instruction, any embedded media, and whether it branches conditionally.
A search or question event initiated by a person, carrying the requester's identity, the query text, and the context it was issued from.
Structured, template-conformant knowledge captured as a byproduct of resolving an Incident — symptom, diagnosis, fix, verification — distinct from a general…
A formal, named-authority approval event for a Procedure version or a promoted piece of sanitised content — distinct from a routine Verification Record because…
The raw artefact pulled from a connected external system — a wiki page, a Slack message, a ticket, a file — before or independent of any curation. May never…
A risk-register entry for a role or individual whose departure would create a critical, undocumented-knowledge gap.
A computed, point-in-time aggregation of verification status, staleness, usage, and contradiction signals for a Knowledge Item, surfaced to whoever consumes…
An act of a human or an automated rule confirming, or un-confirming, a Knowledge Item's accuracy at a point in time.
A queryable, person-scoped knowledge corpus built from one individual's captured Expert Interviews, recordings, and documents, with explicit coverage…