A semantic layer, no free-form SQL
Si picks metrics, dimensions, filters and periods; DataxLand builds the query from versioned definitions; Si runs no SQL of its own when answering.
Connect Zendesk Support so customer service leads can ask Si about service quality without building reports. DataxLand loads tickets, satisfaction ratings, groups and agents; Si proposes how to read ticket statuses, and you approve. Si then answers on ticket volume, resolution rate, average first response and resolution times, CSAT and ticket reopen rate, and for shops with orders in the workspace, support tickets per 100 orders.
Free plan with no time limit · No card required · Sample workspace ready in minutes
Example questions Si answers from the metrics below, once the source is connected and the model approved.
| Metric | Definition | Unit |
|---|---|---|
| Support tickets | Support tickets created in the period (by creation date), any status. | Count |
| Resolution rate | Tickets created in the period that are resolved divided by tickets created in the period.= cs_created_resolved / Support tickets | Ratio (%) |
| Average first response time (hours) | Average hours from when the customer created a ticket to the agent's first response, over tickets created in the period that have a response.= cs_first_response_hours_total / cs_responded_tickets | Number |
| Average resolution time (hours) | Average hours from creation to resolution for tickets resolved in the period.= cs_resolution_hours_total / Resolved tickets | Number |
| CSAT (satisfaction rate) | Share of surveys with a CSAT score of 4 or 5 on a 1-5 scale, among surveys with a valid CSAT score.= cs_csat_positive / Survey responses | Ratio (%) |
| Ticket reopen rate | Tickets resolved in the period that were ever reopened divided by tickets resolved in the period.= cs_reopened_tickets / Resolved tickets | Ratio (%) |
| Support tickets per 100 orders | Order-linked support tickets divided by valid orders, times 100. Shows how many tickets there are for every 100 orders.= Order-linked support tickets * 100 / Valid orders | Number |
Si picks metrics, dimensions, filters and periods; DataxLand builds the query from versioned definitions; Si runs no SQL of its own when answering.
Standard (pack metric), Approved (workspace metric checked before use), Unconfirmed (exploratory answer, clearly labelled).
In the app, Slack, Telegram, Microsoft Teams or MCP, Si uses the same read-only tools and your permissions in the workspace.
Ask inside the workspace in the language you use; Si answers in the same language, with the metric source and confidence level.
Link your account with a one-time code; ask in a private chat or a group bound to the workspace.
Create an expiring, revocable token (plans with MCP) so Claude, Cursor or your own agent call the same tools.
Choose Add source → Zendesk Support and enter your subdomain, email and API token (or an OAuth access token).
Si proposes how to read tickets and ratings and maps them to the pack's standard model; you fix the fields highlighted in yellow, answer the multiple-choice questions and approve the build.
Ask in the app, link Slack or Telegram with a one-time code, or create an MCP token for Claude, Cursor or your own agent.
No. Si only reads the workspace's approved metrics; there is no tool that writes to Zendesk Support, and Si never runs its own SQL on your data when it answers.
No. Personal data columns are hashed at ingest and masked before they reach Si; no dashboard, API or MCP returns the original values.
Yes, through the DataxLand MCP server with tokens that expire and can be revoked. MCP tokens come with the Small Business plan and above; on the Starter plan you ask Si in the app, Slack and Telegram.
Connect Zendesk Support →Zendesk Support + Shopify →Use Si over MCP →
Free plan with no time limit · No card required · Sample workspace ready in minutes