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.
If your orders and products live in a PostgreSQL database (a custom website, your own sales software), connect it so the whole team can ask Si instead of waiting for someone to write SQL. DataxLand loads the tables you choose (full, incremental or CDC), Si proposes how to read each table, you approve, and Si answers with defined metrics: net revenue, order count, average order value, cost of goods sold, contribution margin and return rate. Answers go through the semantic layer, never through free-form queries on your database.
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 |
| Valid orders | Orders that were not cancelled (standard status other than cancelled). | Count |
| Average order value | Line revenue after discounts divided by valid orders.= line_net_total / Valid orders | 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 |
| Return rate | Returned orders divided by valid orders.= returned_orders / Valid orders | 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.
Choose Add source → PostgreSQL, enter the host, port, database, a read-only user and password, then pick the tables and sync mode.
Si proposes how to read the tables 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. When answering questions, Si only calls the semantic layer on the workspace's built warehouse; your source database is read only during scheduled loads.
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.
Each person must link their DataxLand account with a one-time code and have the Analyst role or higher, and an admin must bind the group to exactly one workspace before Si answers with data.
Connect PostgreSQL →PostgreSQL + Facebook Marketing →PostgreSQL + Google Sheets →Use Si over MCP →
Free plan with no time limit · No card required · Sample workspace ready in minutes