Enterprise trust. One intelligence layer.
CataZenta is built for enterprise trust — API-first, multi-tenant, and designed to feed classical integrations and AI agents from the same governed catalog.
The web UI, syndication workers, specialist agents, Zen AI, and MCP all call the same REST surface — no shadow APIs, no separate chatbot database.
Platform at a glance
| Layer | Responsibility |
|---|---|
| Experience | PIM UI, Zen AI chat, Agent Control Center |
| Integration | REST /v1/*, MCP tools, webhooks, async jobs |
| Catalog | Products, attributes, categories, DAM, completeness |
| Syndication | Connections, export profiles, per-SKU job items |
| AI | Platform-managed models (Zen), specialist agents, MCP tools on REST |
| Governance | RBAC, workflows, approvals, audit |
Who we serve → Commerce ecosystem
Architecture principles
Eight docs — each answers a question enterprise architects and integrators ask.
API-first
Every capability reachable via REST; the UI uses the same APIs you integrate against.
Multi-tenant
Organization → tenant isolation with RBAC and scoped JWT claims.
AI infrastructure
Tenant-scoped models, audit, human review — not a public chatbot on CSV exports.
Scalability
Async import/export jobs at catalog scale; workers, not synchronous bulk HTTP.
Security & trust
Data protection, isolation, AI governance — materials for enterprise review.
Security architecture
Auth model summary for technical reviewers and procurement.
Data model
How catalog, media, connections, and export jobs connect.
Zen AI & MCP
Zen AI, MCP, and specialist agents on one catalog — identity and isolation.
Agentic PIM in the architecture
Specialist agents are first-class platform citizens — not a bolt-on chat widget.
| Component | Role |
|---|---|
| Agent Control Center | Enable agents, triage insights, approve writes |
| Zen AI | Conversational assistant in PIM on governed catalog data |
| MCP endpoint | Structured tools for external AI clients — same REST surface |
| Syndication | Connections, export profiles, per-SKU job results |
→ Agentic PIM · Agent Control Center
Three AI paths, one catalog
| Path | Entry | Identity | Model |
|---|---|---|---|
| Zen AI | Chat in PIM | PIM session | Platform-managed when using CataZenta AI credits |
| Hosted MCP | https://api.catazenta.com/mcp | OAuth JWT | Client model (Claude, GPT) |
| Specialist agents | Agent Control Center | ai_mgmt + tenant policy | Per tenant agent policy |
All AI paths execute catalog operations with the caller's permissions on the same REST APIs.
→ MCP overview · Zen AI
Data & syndication
| Entity | Architecture role |
|---|---|
| Product family | Schema for validation, AI extraction, channel mapping |
| Completeness | Publish gates and agent thresholds |
| Connection | Channel credentials (Amazon LWA, Shopify, …) |
| Export job + items | Per-SKU syndication truth and retry scope |
Expanded ER diagram → Data model · Setup concepts → Catalog fundamentals
Syndication flow → Integrations · Syndication guide
Start by role
Enterprise architect
Security / procurement
AI / platform engineer
Integration developer
Platform context
Traditional PIM concepts still exist under the hood — they power intelligence rather than defining the story:
- Catalog fundamentals · Why PIM · Why DAM
- For brands · Brand Hub · Why CataZenta
- Glossary · Core concepts
Get started
- Read API-first — confirm no shadow APIs for your integration design.
- Review Multi-tenant — tenant scope for sandbox vs production.
- Walk Zen AI & MCP if AI is in scope.
- Share Security & trust with procurement.
- Map entities via Data model before custom connectors.
GO DEEPER