An agent intent is a semantic expression of purpose, objective or expected action outcome.1 The intent module reads it as a statement of what an agent aims to achieve,2 and the threat-model module as a purpose or goal communicated by an agent, which is the basis of the intent-ambiguity threat.3 visionGraph places it under Goal.
An intent has an Intent Type (hasIntentType), typed Intent Parameter values (hasParameter), and an authorising Agent Delegation (authorizedBy). It leads to an Agent Action through producesAction.2 An agent is linked to its intent by hasIntent, or expressesIntent in the threat model.
An intent can be aligned with the Agent Task it authorises or motivates, through IntentAlignsWithTask in the security-binding module.4 Working out an intent from natural language is the work of Intent Recognition. The schema.org mapping aligns the class with schema:Intent.5
Footnotes
-
Semantic Agent Communication Community Group, “Core Agent Ontology” (Agent Ontology, CC BY 4.0). https://github.com/s-agent-comm/agent-ontology/blob/750e06d276dd568313a6c03c4e78203887d3fa4b/ontologies/core.ttl ↩
-
Semantic Agent Communication Community Group, “Intent Ontology” (Agent Ontology, CC BY 4.0). https://github.com/s-agent-comm/agent-ontology/blob/750e06d276dd568313a6c03c4e78203887d3fa4b/ontologies/intent.ttl ↩ ↩2
-
Semantic Agent Communication Community Group, “Threat Model Ontology” (Agent Ontology, CC BY 4.0). https://github.com/s-agent-comm/agent-ontology/blob/750e06d276dd568313a6c03c4e78203887d3fa4b/ontologies/threat-model.ttl ↩
-
Semantic Agent Communication Community Group, “Security Binding Ontology” (Agent Ontology, CC BY 4.0). https://github.com/s-agent-comm/agent-ontology/blob/750e06d276dd568313a6c03c4e78203887d3fa4b/ontologies/security-binding.ttl ↩
-
Semantic Agent Communication Community Group, “Agent Ontology to Schema.org Mapping” (Agent Ontology, CC BY 4.0). https://github.com/s-agent-comm/agent-ontology/blob/750e06d276dd568313a6c03c4e78203887d3fa4b/ontologies/schema-org-mapping.ttl ↩