Skip to main content

FactVerse AI Agent Architecture

FactVerse AI Agent sits between enterprise AI clients and the FactVerse industrial runtime. It gives agents a governed way to use digital twins, operational data, knowledge, simulation services, and approved action paths while keeping product API access scoped and auditable.

Architecture layers

LayerRoleMain FactVerse connection
AI clients and channelsEnterprise copilots, agent runners, workflow tools, and customer applications that need industrial contextMCP endpoints and scoped API keys
Governance and tool accessTenant boundary, scope checks, audit records, human approval, and write-action controlFactVerse Platform identity, permission, and tenant context
Data and knowledgeOperational signals, asset records, documents, SOPs, maintenance history, and quality checksDFS, knowledge stores, and generated references
Digital twin and simulationScene context, equipment layout, SimReady assets, and planning models for analysis or Physical AI workflowsFactVerse Designer and simulation services
Operational executionRuntime visualization, alerts, work orders, inspection records, and field feedbackDataMesh Inspector and customer operation systems

Runtime flow

  1. The client connects through an MCP endpoint with a scoped credential.
  2. FactVerse resolves tenant, asset, permission, and product context before tool execution.
  3. The agent retrieves data, digital twin context, knowledge, or simulation-ready assets through governed tools.
  4. The agent produces analysis, recommendations, task drafts, or simulation requests based on the available context.
  5. Write actions such as work-order updates or operational changes stay behind approval and audit controls.
  6. Inspector and connected operation systems record the execution result so future agent work can learn from completed activity.

Product responsibilities

Product or serviceResponsibility in Agent workflows
FactVerse PlatformTenant, identity, asset, permission, subscription, and shared product context
DFSData ingestion, transformation, quality checks, operational signals, and integration pipelines
FactVerse DesignerDigital twin scene creation, layout planning, SimReady asset preparation, and simulation-oriented authoring
DataMesh InspectorRuntime visualization, alerts, inspection workflows, work orders, and field execution records
MCPGoverned tool discovery and access for external AI clients and enterprise agents
Knowledge and referencesManuals, SOPs, asset records, tool catalogs, and domain documents available to approved workflows

Deployment models

FactVerse AI Agent can support cloud, on-premises, and hybrid deployment discussions depending on customer security and integration requirements. The architecture model separates integration boundaries, governance surfaces, and product responsibilities so deployment planning can stay clear across environments.

Design principles

  • Expose capabilities through scoped tools instead of unrestricted product APIs.
  • Keep tenant, asset, and permission context attached to every workflow.
  • Treat digital twins as operational context with visual, data, and workflow meaning.
  • Use simulation and planning assets where they improve reasoning quality or scenario validation.
  • Keep human approval and audit records around actions that affect real operations.