AI Fabrix implements one operating model through four product pillars, supported by controller governance and dataplane execution. Architects use this page to align reference designs with how the product actually enforces trust.
Operating model (product)
What this shows: The product operating model from enterprise reality through governed work to evidence and learning — each arrow is a trust boundary, not an optional integration step.
What this is not: Deployment topology, CLI steps, or manifest structure. See Trust boundaries for where enforcement happens.
- Business Knowledge — Enterprise Knowledge
- Governed Capabilities — Operational Trust and capability mediation
- Digital Workers — Role Assistants (customer-facing name for role-scoped assistants)
- Evidence — Evidence Fabrix
Architectural layers (implementation)
What this shows: How optional interface orchestration, Role Assistant surfaces, execution, and governance layers relate — requests flow downward; governance and policy anchor the stack.
What this is not: Infrastructure sizing, regions, or SKUs. See Platform sizing and environments.
No layer bypasses another for enterprise data access or capability execution. AI clients never receive raw vendor credentials.
Integrator vs operator vs architect
| Role | Primary touchpoint |
|---|---|
| Integrator | Local integration project → upload → certification (Build path) |
| Architect | Pillars, trust boundaries, certification policy (Adopt) |
| Operator | Certified capabilities, worker tasks, evidence (Operator overview) |
Design principles
- Business meaning before system structure — resource types and metadata precede raw APIs.
- Capabilities, not credentials to AI — models and workers request business actions; platform executes.
- Active role as boundary — Digital Workers (exposed to users as Role Assistants) inherit role scope, not unbounded agent authority.
- Evidence from completed work — audit and learning attach to tasks and outcomes.
- Certification before scale — operations, governance, and metadata trust — not a single trust check.
Deployment note
Concrete deployment topology (regions, SKUs, networking) is customer-specific and provisioned through your platform team. This documentation describes product behavior, not infrastructure sizing.