Analytics
Analytics in Qefro shows how Customer AI and Employee AI are used in your organization — conversations, messages, feedback, and related signals — so you can improve knowledge and tools with evidence.
Short definition (citation-ready)
Tenant analytics aggregates conversation and feedback signals for an organization; platform operators have separate admin analytics for fleet-wide usage.
What you can see
| Signal | Why it matters |
|---|---|
| Conversation / message volume | Capacity and channel adoption |
| Feedback scores | Answer quality perception |
| Tool errors (via tool logs) | Broken Business Actions |
| Low-citation chats (spot check) | Knowledge gaps |
Admin Console exposes tenant views. APIs:
GET
/api/v1/tenant/analyticsTenant-scoped usage analytics for the authenticated organization.
GET
/api/v1/tenant/feedbacksUser feedback entries tied to conversations.
Platform Super Admin surfaces also exist under /api/v1/admin/analytics/* (not for tenant Admins).
Architecture
Weekly review workflow
Weekly quality loop
- Open analytics — Compare channels and workspaces.
- Sample poor feedback — Read 5–10 conversations.
- Classify root cause — Missing doc vs wrong workspace vs tool error.
- Fix — Reingest, split workspaces, or repair tools.
- Retest — Ask the same questions again.
Best practices
- Pair dashboards with manual citation spot-checks
- Track tool error rates in Audit Logs / tool logs
- Do not chase vanity message counts without quality review
- Keep Support and HR analytics interpreted separately (different workspaces)
Security notes
FAQ
Are analytics real-time?
Near real-time depending on traffic. Refresh after test chats before drawing conclusions.
Can Members see analytics?
Analytics are intended for Owners/Admins operating the tenant. Members use the Internal Portal for chat.