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.
Excel is the fastest way to ask Si about your data, even on the Free plan. Upload a file with one table per sheet plus a data_dictionary sheet; Si understands the tables, you approve the mapping, then you ask about revenue, cost of goods and contribution margin by product, channel or month. Si also reports COGS coverage, how much of revenue already has a cost, so you know whether the profit figure is ready to trust or needs a fuller cost table.
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 |
|---|---|---|
| Net revenue | Line value after line discounts and allocated order vouchers, minus refunds to buyers. Refunds are deducted only here. | Currency |
| Cost of goods sold | Quantity times unit cost on the order date (half-open validity interval). SKUs without a cost count as 0; see COGS coverage. Returned lines do not reverse their COGS. | Currency |
| Contribution margin | Net revenue minus COGS, marketplace fees, payment fees, shipping and return costs (before advertising).= Net revenue - Cost of goods sold - Marketplace fees - Payment fees - Seller-paid shipping cost - Return cost | Currency |
| Net profit after fees and ads | Net revenue received minus COGS, marketplace fees, payment fees, shipping, return costs and advertising.= Contribution margin - allocated_ad_spend | Currency |
| Average order value | Line revenue after discounts divided by valid orders.= line_net_total / Valid orders | Currency |
| COGS coverage | Share of line revenue (after discounts) coming from SKUs that have a cost. Below 100% means the profit metrics are overstated.= line_net_with_cost / line_net_total | Ratio (%) |
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.
In the workspace choose Add source → Excel file and upload your .xlsx file (one table per sheet, plus a data_dictionary sheet).
Si proposes how to read each sheet and maps them to the pack's standard model; you fix the highlighted fields, answer the multiple-choice questions and approve the build.
Ask in the app, connect Slack or Telegram with a one-time code, or create an MCP token for Claude, Cursor or your own agent.
Upload the new file, DataxLand rebuilds and Si answers on the latest published version; every answer shows how current the data is.
No. Si only reads the workspace's approved metrics; there is no tool that writes to Excel, and Si never runs SQL it wrote itself on your data when answering.
No. Personal data columns are hashed on ingest and masked before they reach Si; no dashboard, API or MCP returns the original values.
It depends on your plan's AI question quota: Free 30, Starter 300, Small Business 1,500, and you can buy extra question packs. See pricing for details.
Connect Excel →Excel + Facebook Marketing →Excel + Shopee →Use Si over MCP →
Free plan with no time limit · No card required · Sample workspace ready in minutes