One catalog. Three AI surfaces.
Zen AI (chat in PIM), MCP (Claude, ChatGPT, Cursor), and specialist agents (Agent Control Center) all operate on the same governed tenant catalog — with your permissions, audit trails, and approval gates.
This page is for architects, integrators, and security reviewers. It describes behavior and boundaries customers need — not internal service topology.
Three paths to catalog AI
| Surface | Where | Best for |
|---|---|---|
| Zen AI | Chat in the PIM UI | Merchandisers — ad-hoc questions, inline drafts on products |
| MCP | Claude, ChatGPT, Cursor, IDEs | Developers and power users — tool-driven automation |
| Specialist agents | Agent Control Center | Scheduled runs, missions, insights, approval queue |
All three read and write through the same REST catalog APIs the PIM UI and syndication workers use — not a separate shadow database or CSV export.
→ Architecture overview · API-first
Zen AI (in-product chat)
Zen AI is the conversational assistant in PIM — grounded in live products, families, attributes, completeness, and channel rules.
| Topic | Customer-facing detail |
|---|---|
| Entry | Zen AI panel on product pages and workspace |
| Identity | Your logged-in PIM session — same tenant and roles |
| Data scope | Only catalog data your roles allow |
| Writes | Suggestions in chat; apply manually or through workflows — not silent bulk publish |
| Models | Platform-managed inference when using CataZenta-billed AI credits (tenant policy) |
Governance → Zen AI · Workflows · Security
MCP (external AI clients)
MCP connects external assistants to your tenant catalog via structured tools — the same operations documented in the MCP tools reference.
| Topic | Detail |
|---|---|
| Hosted URL | https://api.catazenta.com/mcp |
| Protocol | Streamable HTTP for Claude.ai and ChatGPT |
| Auth | OAuth sign-in → Bearer token on each request (same account as PIM) |
| Local IDEs | Optional connector for Claude Desktop, Cursor, VS Code — MCP quickstart |
| Tools | 90+ named tools (search_products, quick_publish, …) |
Setup → MCP authentication · Claude.ai · ChatGPT
Specialist agents (Agent Control Center)
In-platform specialist agents run autonomously — schedules, events, or missions — and emit insights plus approval proposals before catalog writes apply.
| Zen AI | MCP | Specialist agents | |
|---|---|---|---|
| Interaction | Chat in PIM | Tool calls in external clients | Autonomous runs |
| Persistence | Session chat | Session-driven chains | Insights + approval queue |
| Writes | Manual apply / workflows | Named tool calls (API-auditable) | Approval queue → apply |
| Best for | One product, one question | Developer automation | Continuous catalog intelligence |
→ Agent Control Center · Approvals
Identity & permissions
Every AI path respects tenant isolation and RBAC — the assistant only sees and changes what your user or integration account is allowed to.
| Path | Identity | Tenant scope |
|---|---|---|
| Zen AI | PIM session (JWT) | Active tenant in UI |
| Hosted MCP | OAuth Bearer token | Same account and tenant as PIM |
| Local MCP connector | Integration user or token from onboarding | Configured tenant only |
| Specialist agents | ai_mgmt permissions in PIM | Tenant agent policies |
Cross-tenant access is not available through any AI surface. Details → Multi-tenant design · Authentication
AI Content Studio vs Zen AI
| AI Content Studio | Zen AI | |
|---|---|---|
| Mode | Batch / bulk jobs | Conversational |
| Best for | Hundreds of SKUs at once | Explore, diagnose, refine one record |
| Output | Attribute updates + review queue | Suggestions in chat |
| API | Async generation endpoints (separate from chat) | In-product chat experience |
Both are tenant-scoped and review-gated before publish. → Zen AI · AI enrichment
Cloud & data (summary for reviewers)
CataZenta is hosted on enterprise cloud infrastructure with tenant-isolated catalog data. For procurement and security questionnaires:
| Topic | Summary |
|---|---|
| Data residency | Catalog and media stored per tenant; discuss region requirements with your account team |
| In-product AI | Zen AI and specialist agents may use platform-managed models when your tenant uses platform AI credits |
| External MCP | Your chosen model (Claude, GPT, etc.) — CataZenta exposes tools and enforces catalog permissions |
| Training | Customer catalog data is not used to train public foundation models in standard deployments |
| Audit | API and approval actions are auditable; agent runs and approvals visible in ACC |
Full trust materials → Security & trust · Security architecture · AI infrastructure
Need a detailed security pack for enterprise review? Contact CataZenta.
Get started
- Merchandisers — open Zen AI on a product with family and core attributes filled in.
- Integrators — complete First API call, then MCP quickstart.
- Catalog ops — enable agents in Agent Control Center and review Approvals.
- Architects — read API-first and Integrations.
GO DEEPER