Ontology
Classes
AOW 2.0 defines 25 classes in four layers. Each class page lists the definition, purpose, attributes, relationships, related standards, and an example. A compact listing of all terms is available in the term reference.
Layer 1
Perception
Records the Work Items in progress and the Signals and Observations about them. The other layers use this information.
Work Item new in 2.0
The unit of business work that the rest of the ontology is about: a claim, an application, an order, a case, a ticket.
Signal new in 2.0
A raw, time-stamped trace emitted by a system, a person, or the environment: an event, a log line, a user-interface interaction, a document arriving, a state change, a metric sample.
Observation new in 2.0
An interpreted fact about a Work Item, Actor, or Action, derived from one or more Signals and carrying a Confidence.
Layer 2
Cognition
Derives Intents from business Objectives, adds Context, applies Policy, and plans the work.
Objective
A business-level goal expressed in strategic or operational terms.
Intent
A structured, actionable goal derived from an Objective and interpretable by agents, orchestrators, and people.
Context
The structured situational information that gives relevance to an Intent.
Policy
Declarative constraints defining permissible, required, or restricted behavior.
Plan new in 2.0
An ordered or partially ordered set of Tasks intended to fulfill an Intent, produced by an Orchestrator or other Actor.
Layer 3
Execution
Actors, both Agents and people, are assigned Tasks, invoke Skills through Actions, and produce Results.
Task new in 2.0
A unit of assigned work within a Plan, performed by an Actor filling a Role.
Actor new in 2.0
Anything that can be assigned Tasks, perform Actions, and be held to account for them: an Agent, a person, an Orchestrator, or a Guardian.
Agent
A software Actor that interprets Intents and Tasks and acts on them using Skills, within the autonomy it has been cleared for.
Human Actor new in 2.0
A person who performs, approves, reviews, or oversees work.
Orchestrator
A coordinating Actor that turns Intents into Plans, assigns Tasks to Actors, and manages sequencing and exceptions.
Role new in 2.0
A named set of responsibilities and authority that an Actor can fill, such as "claims adjuster" or "eligibility reviewer".
Skill
A reusable capability that an Actor can invoke.
Action
A single execution event in which an Actor invokes a Skill, in service of a Task, at a point in time.
Result
The immediate, atomic effect or output of an Action.
Layer 4
Assurance
Sets permitted autonomy, measures confidence, oversees behavior, evaluates Outcomes, and records Feedback in Memory.
Guardian
The oversight Actor that enforces Policy and Assurance Levels, monitors behavior, and escalates to people when needed.
Confidence
A model-, rule-, or human-derived measure of certainty about an Observation, a Result, or an Action.
Assurance Level
A governance-set level of permitted autonomy, with the human oversight and evidence it requires.
Outcome
The aggregated business impact of one or more Results, measured against an Objective.
Feedback
Structured information, from people or systems, used to improve future behavior.
Memory
Persistent knowledge accumulated from experience, used to inform future Context.
Operational Memory
Short-lived, execution-oriented memory scoped to a session, Task, or Work Item.
Knowledge Base
Long-lived memory of generalized patterns, rules, and precedents.