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.
Subscription software businesses that bill through Stripe can ask Si about recurring revenue growth without building a spreadsheet. DataxLand loads customers, subscriptions, invoices and charges; Si proposes how to read MRR movements, and you approve. Si then answers on average MRR, new MRR, churned MRR, net new MRR, average revenue per account, logo churn rate and invoice collection rate.
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 |
|---|---|---|
| Average MRR | Average monthly recurring revenue in the period = total MRR across month-end snapshots divided by the number of snapshot dates.= tech_mrr_snapshot_total / tech_snapshot_count | Currency |
| New MRR | Total MRR from subscriptions that start paying in the period (events of type new), by effective date. | Currency |
| Churned MRR | Total MRR lost from customers cancelling their subscriptions in the period, as a positive number. | Currency |
| Net new MRR | New MRR plus expansion, minus contraction and churn, in the period.= New MRR + Expansion MRR - Contraction MRR - Churned MRR | Currency |
| Average revenue per account (ARPA) | Average MRR per paying account = total MRR across snapshots divided by the number of paying-account occurrences in those snapshots.= tech_mrr_snapshot_total / tech_paying_account_snapshots | Currency |
| Logo churn rate | Churned accounts in the period divided by average paying accounts in the period.= Churned accounts / Average paying accounts | Ratio (%) |
| Invoice collection rate | Amount collected divided by amount invoiced, for invoices issued in the period.= tech_invoice_paid_amount / Invoiced amount | 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 → Stripe and enter the Account ID and a secret key (a read-only restricted key is recommended).
Si proposes how to read subscriptions, invoices and charges 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 Stripe, 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.
Every answer names the metrics it used and its confirmation level: Standard for pack metrics, Approved for workspace metrics that passed the number checks, Unconfirmed for exploratory answers.
Connect Stripe →Stripe + Intercom →Stripe + HubSpot →Use Si over MCP →
Free plan with no time limit · No card required · Sample workspace ready in minutes