An execution context is a contextual frame describing conditions, trust anchors or constraints associated with an agent action.1

The class is declared in the core module. The property contextOf has an ExecutionContext as domain and an Action as range, indicating that the context applies to a specific action. The intent module adds executedIn, linking an action to its context. The execution-context module then breaks the context into parts: hasEnvironment leads to an Execution Environment, hasSecurityContext to a Security Context, and inputState and outputState to an Input State and an Output State.2

The execution context is the domain of all four properties. visionGraph places the concept under Runtime Environment.

Footnotes

  1. 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 ↩

  2. Semantic Agent Communication Community Group, “Execution Context Ontology” (Agent Ontology, CC BY 4.0). https://github.com/s-agent-comm/agent-ontology/blob/750e06d276dd568313a6c03c4e78203887d3fa4b/ontologies/execution-context.ttl ↩