Skip to main content

AI Agent Architecture and Reference

Use this section when a team needs to understand how FactVerse AI Agent is structured before designing a workflow, integration, or deployment model. These pages define the product boundaries, architecture layers, capability areas, and documentation structure used by the rest of the docs.

Reference map

PageUse it forMain questions answered
Core ConceptsShared vocabulary for agent workflowsWhat is an endpoint, tool, scope, tenant context, source reference, and approval boundary?
ArchitectureRuntime and product responsibility modelHow do clients, MCP, Platform, DFS, Designer, Inspector, knowledge, and simulation services work together?
Capability MapCapability planning and roadmap discussionWhich capability groups support facility operations, predictive maintenance, and Physical AI workflows?
Documentation ArchitectureDocumentation ownership and expansion planningWhich pages should be written next, and which content belongs in product manuals or workflow guides?

When to use this section

  • Designing a new AI client or enterprise agent integration.
  • Deciding which FactVerse product owns a workflow capability.
  • Planning data, simulation, inspection, or work-order boundaries.
  • Reviewing whether a workflow should use a base MCP endpoint or a module endpoint.
  • Checking whether a page belongs in concept docs, operating guides, workflow guides, use cases, or reference material.

Architecture checklist

AreaCheck before design moves forward
Product contextThe workflow identifies which roles belong to Platform, DFS, Designer, Inspector, MCP, and connected systems.
Tenant boundaryThe client has a clear tenant, site, asset group, and permission boundary.
Data boundaryRequired signals, documents, scenes, and work records have owners and freshness expectations.
Tool accessTool discovery, scopes, and approval controls are planned before implementation.
Output evidenceThe workflow can return source references, assumptions, and review notes.
Operating handoverThe operating team knows how workflow runs, exceptions, and feedback will be recorded.

Next step

Start with Core Concepts if the team needs vocabulary alignment. Start with Architecture if the next decision is about integration boundaries or deployment planning.