A structured description of how two or more AI agents work together within a multi-agent system. Defines the orchestration hierarchy, data flow, and human oversight for the collaboration. Enables machine-readable representation of conductor/worker patterns and org-board architectures.
ajp:collaborationIdTextrequiredUnique identifier for this collaboration
ajp:collaborationNameTextrequiredHuman-readable name
ajp:collaborationTypeTextrequiredhierarchical / parallel / sequential / consensus
ajp:workerAgents[ajp:AIAgent]requiredAgents participating in this collaboration
ajp:dataSharedBetweenAgentsTextrequiredDescription of data passed between agents
ajp:humanApprovalRequiredBooleanrequiredDoes collaboration require human approval before acting?
ajp:orchestratorAgentajp:AIAgentThe orchestrating agent (required for hierarchical)
ajp:maxAgentsActiveIntegerMaximum agents active simultaneously
ajp:humanApprovalGateajp:HumanApprovalGateGate definition (required if humanApprovalRequired)
ajp:combinedCapabilityDeclarationajp:CapabilityDeclarationWhat the collaboration as a whole can do
ajp:combinedProhibitions[ajp:ProhibitedAction]What the collaboration cannot do
ajp:spanLimitIntegerMax worker agents per orchestrator (default: 5)
ajp:auditTrailajp:AgentAuditRecordCombined audit for the collaboration
{
"@context": {
"@vocab": "https://schema.org/",
"ajp": "https://schema.anthonyjamespeacock.com/"
},
"@type": [
"ajp:AgentCollaboration"
],
"ajp:collaborationId": "<Text>",
"ajp:collaborationName": "<Text>",
"ajp:collaborationType": "<Text>"
}