Skip to main content
Agent Control Center

Run agents. Review approvals. Monitor catalog health.

The Agent Control Center is the PIM admin hub for Agentic PIM — where teams enable specialist agents, triage insights, review approval proposals, and track catalog quality from agent findings (not attribute fill rates alone).

Open it from the PIM sidebar → Agent Control Center (requires ai_mgmt permissions).

10Specialist agents
100%Writes approval-gated by default
FindingsCatalog quality from insights

The governed loop

Specialist agents propose — humans approve — approved changes apply to PIM — syndication publishes channel-ready output. Rejections and channel feedback map back as new findings.

StepWhat happensWhere in ACC
1. Run agentsManual, scheduled, event-triggered, or multi-step workflow runsAgents · Workflows
2. Review findingsSEO gaps, taxonomy conflicts, compliance issues surface as insightsInsights
3. Approve writesEvery proposed attribute or content change waits in the queueApprovals
4. Monitor qualityRollup health score from open insights + pending approvalsCatalog quality
Findings, not fill rates

Catalog Quality measures open agent insights and pending approvals — not PIM attribute fill rate. Use completeness as a publish gate; use ACC for operational catalog intelligence.


Information architecture

The Control Center is organized into four areas in the PIM sidebar:

Manage

Enable agents, review proposed writes, set governance policies.

Monitor

Run history, live execution steps, operational metrics.

Intelligence

Agent findings, health dimensions, cost and impact.

Automate

Prebuilt multi-agent workflows and batch catalog operations.


Page guide

In PIM, Agent Control Center pages live under /agent-center/…:

PagePIM pathWhat you do here
Agents/agent-center/agentsEnable agents, configure policies, view per-agent metrics
Approvals/agent-center/approvalsReview diffs, approve/reject/bulk approve proposed writes
Governance/agent-center/policiesToggle platform governance policies, audit runs
Activity/agent-center/activityFilter runs by agent/status; open live step timeline
Insights/agent-center/insightsTriage findings by severity/type; bulk resolve
Catalog Quality/agent-center/catalog-qualityHeadline health + eight quality dimensions
Workflows/agent-center/workflowsCreate and monitor multi-step agent workflows
Orchestration/agent-center/orchestrationActive workflows and run boards
Observability/agent-center/observabilityAggregates: workflows, failures, token usage
Cost & Usage/agent-center/cost-usagePlatform AI credits and model attribution
Business Impact/agent-center/business-impactTime-saved estimates from approval outcomes

Legacy URLs (e.g. /agent-center/runs, /agent-center/missions) redirect to the canonical paths above.


Agents page

The Agents page lists all ten specialist agent types with enable/disable controls, run metrics, and a detail drawer:

Drawer tabPurpose
OverviewRecent activity, last run, links to Activity
WorkflowsPrebuilt templates, custom goals, batch scope, parallel steps
ConfigurationAuto-apply rules, confidence thresholds, blocked attributes
PermissionsEffective IAM grants (read-only)
SchedulesCron-based recurring runs
ActivityRun history for this agent type

Tenant-wide defaults and overrides are managed per agent. See the full catalog in Specialist agents.

Typical first actions

  1. Confirm default agents are enabled for your catalog (enrichment, SEO, taxonomy, compliance).
  2. Leave auto-apply off until your team trusts agent output.
  3. Trigger a manual run on a pilot category or product set.

Approvals

Every agent-proposed catalog write lands in Approvals before it applies.

  • List view — server-paginated table with filters by agent, status, and product
  • Detail view — proposed diff, approve, reject, or retry apply after failure
  • Bulk actions — approve or reject many proposals in one session (bulk approve applies the same governed writes as single approve)

Approval types include attribute updates, category changes, content generation, translations, bulk actions, and status changes.

Governed by default

Auto-apply is available only for select agent types (e.g. duplicate detection) when tenant policy explicitly allows it. Default posture is review first.


Insights

The Insights dashboard surfaces open findings from agent runs:

  • Priority / by-type / all tabs for triage
  • Filter by severity (critical, warning, info), insight type, product, or search
  • Bulk resolve when issues are fixed outside the agent loop

Common insight types: seo_weakness, taxonomy_conflict, compliance_gap, duplicate_detected, completeness_gap, marketplace_readiness, translation_gap, and more.

Dimension cards on Catalog Quality deep-link here with the right insight_type filter when a dimension maps to a single type.


Catalog Quality

Catalog Quality rolls up open insights and pending approvals into a headline score and eight quality dimensions. It is a monitoring layer — not a separate AI agent.

MeasuresDoes not measure
Count/severity of open insights from specialist agentsPIM attribute fill rate
Pending approvals (headline factor)Whether every SKU was scanned
Recent failed runs (headline factor)Channel export success rate

Scoring caveats

  • No open insights → dimensions may show 100% — meaning no known problems, not catalog is complete.
  • Headline and dimension scores use different formulas; failed runs can lower the headline while dimensions stay at 100%.

Full explainer → Catalog quality — findings not fill rates.


Activity & observability

PageWhat you see
ActivityPaginated run list; run detail with live SSE step stream during execution
ObservabilityActive workflows, failed runs (30d), token aggregates
Cost & UsagePlatform AI credit balance and per-model usage estimates (when using platform-billed models)
Business ImpactApproval-outcome time-saved model — estimates only, with methodology banners in UI

When platform AI credits are unallocated or exhausted, agent runs on platform-billed models block with a clear message — contact your administrator to allocate credits in Backoffice.


Governance

Governance loads platform policies with active/inactive toggles per policy_key. Metrics include active policy count, failed runs (30d), pending approvals, and active risk controls.

  • Per-agent enablement, auto-apply, and blocked attributes remain under Agents → Configuration
  • Audit tab shows completed and failed runs for governance review

Workflows & orchestration

PagePurpose
WorkflowsCreate and run multi-step agent workflows on a product, category, family, or catalog scope — with a live execution timeline
OrchestrationLive board of active workflows and agent runs for batch catalog operations

CataZenta ships ten prebuilt workflows (enrichment pipelines, marketplace launch, import onboarding, localization, and more). Pick a template when you create a workflow, or describe a custom goal and let CataZenta plan the steps.

→ Full catalog with step-by-step agent order: Prebuilt agent workflows

Workflows can run steps in sequence or in parallel, and some templates skip or add a step based on findings (for example, compliance only when enrichment reports critical issues). When a step proposes catalog changes, the workflow pauses for approval and resumes after your team approves in the queue.


Permissions

Agent Control Center requires the ai_mgmt module:

ActionPermission
View runs, insights, approvalsai_mgmt:prompts:view
Trigger runs, approve/rejectai_mgmt:prompts:create
View / edit agent policiesai_mgmt:configs:view / ai_mgmt:configs:update

Product workspace embeds agent triggers and insight cards on product detail pages — with links back into the Control Center.


Zen AI vs specialist agents

Zen AISpecialist agents (ACC)
InteractionConversational chat in PIMAutonomous runs, schedules, workflows
OutputInline suggestions in chatStructured insights + approval proposals
WritesManual apply or workflow gatesApproval queue → apply on approve
Best forAd-hoc questions, one-off editsContinuous catalog operations at scale

Both operate on the same governed catalog. See Zen AI and Agentic PIM overview.


MCP and the Control Center

External MCP clients (Claude, ChatGPT, Cursor) call documented catalog tools on your tenant — search, enrich, publish, analyze completeness.

In-platform agents add what MCP alone cannot persist:

  • Insights with severity, type, and bulk resolve
  • Approval queue with diffs and bulk approve
  • Catalog Quality rollup across dimensions

MCP overview · MCP quickstart · AI agents (MCP clients)


Getting started in PIM

  1. Open Agent Control Center from the PIM sidebar (confirm ai_mgmt access).
  2. Review enabled agents on the Agents page — start with enrichment, SEO, taxonomy, compliance.
  3. Run a pilot — manual run on one category or import batch; watch Activity for live steps.
  4. Triage Insights — resolve or convert findings into approval proposals.
  5. Approve proposals in Approvals before any write goes live.
  6. Check Catalog Quality — monitor headline score and dimensions weekly.
  7. Wire MCP (optional) — same catalog for conversational ops in Claude or Cursor.

Need API access? → Quick start · First API call