Guardian
Assurance since 1.0
aow:GuardianThe oversight Actor that enforces Policy and Assurance Levels, monitors behavior, and escalates to people when needed.
Separates performing work from checking it.
A kind of Actor.
Attributes
| Attribute | Type | Required | Description |
|---|---|---|---|
enforcement_mode | one of preventive, detective, corrective | Whether it blocks before, detects after, or repairs after the fact. | |
scope | text | The Actors, Skills, or Work Items it watches. | |
name | string | Display name. (from Actor) |
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.
Relationships
| Relationship | Points to | How many | Required | Meaning |
|---|---|---|---|---|
constrained_by (as Actor) | Policy | many | Policies that apply. | |
fills_role (as Actor) | Role | many | Roles the Actor is authorized to fill. | |
has_skill (as Actor) | Skill | many | Skills the Actor can invoke. | |
writes_to (as Actor) | Memory | many | Memory the Actor records its experience in. | |
enforces | Policy, Assurance Level | many | The Policies and Assurance Levels the Guardian enforces. | |
oversees | Actor, Plan, Skill | many | What the Guardian watches. | |
escalates_to | Role, Human Actor | many | Where escalations go. |
Pointed to by
| From | Relationship | Read backward as |
|---|---|---|
| Plan | planned_by | plans |
| Task | assigned_to | assigned |
| Action | performed_by | performs |
| Observation | about | observed by |
| Feedback | provided_by | provided |
| Feedback | updates | updated by |
| Guardian | oversees | overseen by |
Notes
A Guardian may be software, a person, or both. Its interventions are recorded as Actions.
Example
Source: examples/claims-processing.jsonld. The example passes all validation checks.
{
"id": "guardian-claims",
"type": "Guardian",
"name": "Claims guardian",
"enforcement_mode": "preventive",
"scope": "All eligibility decisions on disability claims.",
"enforces": [
"policy-auto-approval",
"policy-high-risk-review",
"aow:AL2"
],
"oversees": [
"agent-validation",
"agent-coverage",
"agent-benefit"
],
"escalates_to": [
"role-claims-adjuster"
]
}Term reference · JSON Schema · SHACL shape aowsh:GuardianShape