Agentic Ontology of Work · Skan.ai

Ontology / Assurance

Assurance Level

Assurance since 1.0 aow:AssuranceLevel

A governance-set level of permitted autonomy, with the human oversight and evidence it requires.

Specifies the permitted autonomy and required human oversight for a piece of work. AOW defines five levels, AL0 to AL4.

Attributes

AttributeTypeRequiredDescription
levelinteger (0–4)yesPosition on the AL0 to AL4 scale.
human_roletextWhat people do at this level.
agent_roletextWhat Agents may do at this level.
review_protocoltextThe human oversight this level requires.
default_confidence_floornumber (0–1)Confidence below which an Actor operating at this level must escalate, unless a Policy sets a different threshold.
risk_classstringThe class of risk this level is suited to.

Every entity also has an id and a type, and may carry label, description, and the provenance facet: version, created_at, created_by, revision_of.

Pointed to by

FromRelationshipRead backward as
Intent, Task, Skillrequires_assurancerequired by
Confidencecompared_againstthreshold for
Guardianenforcesenforced by

Notes

Higher levels permit more autonomy and require more evidence before they are granted.

Term reference · JSON Schema · SHACL shape aowsh:AssuranceLevelShape