Skip to main content

FactVerse AI Agent Capability Map

The MCP tool reference describes individual tools. This map explains how tools, data, digital twins, and product modules combine into capabilities that customers can evaluate, deploy, and govern.

Capability groups

CapabilityConnected componentsTypical outputGovernance concern
Industrial operations copilotFactVerse Platform, DFS, Inspector, knowledge storesSituation summaries, asset answers, procedure guidance, task draftsTenant context, source traceability, approval for write actions
Predictive maintenance workflowDFS signals, asset history, Inspector work orders, AI Agent analysis toolsMaintenance risk explanation, suggested checks, work-order preparationModel confidence, maintenance authority, record retention
Facility and energy operationsOperational twins, meter data, asset metadata, inspection recordsEnergy-use calculation support, abnormal trend review, evidence organizationData freshness, regulatory wording, human engineering review
Simulation and Physical AI workflowDesigner scenes, SimReady assets, simulation services, operational constraintsLayout comparison, process rehearsal, robot or equipment training contextSimulation assumptions, versioned assets, validation boundary
Knowledge and document workflowManuals, SOPs, customer documents, generated referencesRetrieval, comparison, translation support, structured answer draftsAccess control, citation quality, confidential document handling
Field execution and feedbackInspector mobile workflows, alerts, work orders, checklistsDispatch context, inspection guidance, completion records, feedback loopsOperator approval, audit trail, operational safety
Data governance and integrationDFS pipelines, quality checks, source-system connectorsData readiness review, schema mapping, anomaly flags, integration statusData ownership, quality gates, pipeline observability
Agent integration toolingMCP endpoints, scopes, tool references, customer AI clientsControlled agent access, runtime discovery, integration test pathsScope design, key rotation, monitoring, deprecation handling

How to read the map

Start from the business workflow, then identify the product modules and tools required to support it. For example, a predictive maintenance workflow normally needs asset context from FactVerse Platform, operational signals from DFS, maintenance history and work-order context from Inspector, and scoped tools exposed through MCP.

Capability assembly pattern

  1. Define the operational question or decision boundary.
  2. Attach tenant, asset, and permission context.
  3. Retrieve relevant data, knowledge, digital twin state, or simulation assets.
  4. Generate analysis or a proposed task with source references.
  5. Route write actions through approval and audit.
  6. Feed completed work, inspection results, and operator feedback back into the system.

Capability naming

In business and integration discussions, use capability names such as "predictive maintenance workflow" or "industrial operations copilot." Use raw MCP tool names for integration behavior, debugging, and API-level references.