Skip to main content

Agent Platform Overview

FactVerse AI Agent is a governed runtime for industrial agents. It lets a customer environment expose multiple configured agents through one platform model, while keeping tenant boundaries, tool access, action risk, review gates, and audit records visible.

Use this page when you need to explain how Agent workflows are organized before choosing a specific module, MCP endpoint, or workflow guide.

Platform flow

What the platform controls

ControlWhat it means for customers
Agent rosterA tenant sees only the agents configured for that environment.
Agent purposeEach agent should have a named operating task, owner, and entry point.
Tool bindingAn agent can call only the tools assigned to it and visible in that environment.
Runtime discoveryTool availability is checked at runtime, keeping customers aligned with the live environment.
Risk boundaryRead, analysis, draft write, and operational action paths are handled differently.
Review gateHigher-risk actions can require confirmation or human approval before execution.
Audit trailDecisions, blocked actions, approvals, and final results should be traceable.

Agent types

FactVerse AI Agent documentation describes agent types by their business role.

Agent typeTypical roleNormal output
Capability agentRuns a model, calculation, data pipeline, or specialized analysis that other workflows use.Score, forecast, classification, simulation result, or enriched dataset.
Assistant agentHelps a user investigate a situation, summarize context, or prepare a reversible record.Explanation, recommendation, draft work request, or review note.
Worker agentCarries an approved operational task through a controlled process.Approved task update, dispatch step, or action record.
Orchestrator agentCoordinates multiple agents, tools, or operating steps inside a governed workflow.Multi-step decision package, routed approval, or coordinated execution plan.

These names describe the role of the agent. The actual tools available to an agent still depend on the customer environment, enabled modules, scopes, and risk controls.

Runtime model

An Agent workflow should be designed in this order:

  1. Define the operating task and user role.
  2. Confirm tenant, site, asset, equipment, scene, or work-record boundary.
  3. Check whether source data, documents, and digital twin context are ready.
  4. Discover the runtime tools available to the agent.
  5. Run read-only validation before adding compute or write actions.
  6. Put controlled actions behind confirmation, approval, and audit.
  7. Record feedback so later runs can improve.

This model keeps Agent work connected to real operating records, review decisions, and accepted outcomes.

Relationship to MCP

MCP is the governed tool integration layer for external AI clients and enterprise agent runtimes. Within the broader Agent Platform, it provides the tool-access layer.

LayerRole
Agent PlatformDefines agents, data context, tool binding, risk gates, review behavior, and audit expectations.
Agent HubGives users a tenant-specific place to find and enter configured agents.
MCP endpointsLet approved clients discover and call tools through scoped endpoints.
Module toolsExpose product capabilities such as predictive maintenance, CMMS, facility operations, data center operations, and Physical AI workflows.

Use Getting Started for client setup and Access and Scope Planning for endpoint and key planning.

Review boundaries

Agent outputs need handling that matches their risk and operating impact.

Output typeExpected handling
Read-only answerReturn evidence, source timestamps, and unresolved gaps.
Analysis or compute resultReturn assumptions, input boundaries, and reviewer notes.
Draft recordCreate or prepare the record only when the user has the required scope and workflow owner.
Operational actionRoute through the customer's approval and audit process before affecting a real system.

Use Workflow Run Record to capture evidence and review results.

Public documentation map

NeedUse
See configured agents in the productAgent Hub
Connect an external clientGetting Started
Plan endpoint and scopesAccess and Scope Planning
Check source readinessData Readiness
Build a workflowWorkflow Guides
Look up tool and scope referenceMCP Tool Reference and Scope Reference