Skip to main content

FactVerse AI Agent

FactVerse AI Agent connects FactVerse digital twins, operational data, simulation services, knowledge, and governed execution paths. Implementation teams use it to build agent workflows for facilities, equipment, maintenance, simulation-ready assets, and industrial operations.

Use this page to choose the right document for the task in front of you.

Implementation flow

Choose your path

I need toStart withThen use
Connect an AI client for the first timeGetting StartedMCP Integration Guide
Plan endpoints, API keys, scopes, and approvalsAccess and Scope PlanningMCP Scope Matrix
Check whether the workflow has enough usable dataData ReadinessDFS overview
Build a facility operations workflowFacility Operations Workflow GuideFacility Operations use case
Build a predictive maintenance workflowPredictive Maintenance Workflow GuidePredictive Maintenance use case
Build a Physical AI workflowPhysical AI Workflow GuidePhysical AI use case
Review request and output patternsExamplesWorkflow Run Record
Diagnose a failed client, scope, data, or write actionTroubleshootingMCP Errors and Audit
Move a workflow from pilot to regular useValidation and HandoverWorkflow Guides
Look up available tools and scopesTool ReferenceScope Reference

Operating model

A production workflow should be built in this order:

  1. Connect a read-only client and confirm runtime tool discovery.
  2. Verify tenant, site, asset, equipment, scene, and source-system boundaries.
  3. Check source freshness, signal quality, document context, scene version, and review ownership.
  4. Add compute or simulation steps only after the inputs and assumptions are visible.
  5. Add draft write actions behind explicit human approval and audit records.
  6. Capture final evidence, reviewer decisions, operator feedback, and accepted corrections.

Use Core Concepts for the vocabulary behind this operating model. Use Architecture and Capability Map when planning a larger deployment.

Product context

Product areaRole in an Agent workflow
FactVerse PlatformTenant, asset, permission, and product context.
Data Fusion ServicesSource connection, mapping, quality checks, governed datasets, fusion, review, and BI-ready data.
FactVerse DesignerDigital twin scenes, simulation-ready assets, layout planning, and scenario preparation.
DataMesh InspectorRuntime visualization, alarms, work orders, inspection records, and facility operations context.
MCP endpointsGoverned tool access for AI clients and enterprise agent runtimes.

Expected implementation output

For each Agent workflow, keep these artifacts visible:

ArtifactPurpose
Workflow contractDefines role, boundary, inputs, output, reviewer, and approval path.
Access packageLists MCP endpoint, scopes, key owner, rotation rule, and client runtime.
Data readiness noteRecords source systems, mappings, freshness, quality issues, and missing evidence.
Validation runShows the first read-only output with source references and reviewer comments.
Run recordCaptures tool calls, evidence, assumptions, final decision, and feedback.

Naming

Use FactVerse AI Agent as the product name for agent workflows, customer-facing guidance, and integration documentation.