Do I need a data team?

No, but it is not zero setup either. Start with what it gets wrong: on our own dirty test schema it answered two questions confidently and got them wrong — whether revenue is net of tax, and which of two date columns is the one you mean by "ordered" — with nothing to signal it was unsure. Those two are the ones no tool can guess from a schema. What it does get right on its own is the mechanical layer: which tables are abandoned, which flag means soft-deleted, which total is a line rather than an order. You correct the rest once in chat and it keeps the definition, so the next session starts from your answer instead of guessing again.

By industry

AI analytics for e-commerce — ask in plain English, no SQL

Updated 2026-08-22

E-commerce teams sit on rich data — orders, customers, products, sessions, ad spend — spread across a store database, spreadsheets and ad platforms. An AI data analyst connects those sources and answers revenue, product and retention questions in plain English, so you don't wait on an analyst to pull a report.

If you don't control the store database — a lot of operators don't — you can still start today. A Google Sheet connects with no read-only user, no open port and nothing for anyone else to approve, and it never counts against the free tier's one source; CSV and Excel uploads work on the 14-day Pro trial. Export your orders, connect the sheet, ask the question. The one thing no plan waives is your own AI provider key, and a Google Gemini key is free to create.

First, the question that decides whether any of this applies to you: can we reach your database?

Intellrise connects from our servers, not from your browser, so your database has to accept a connection from the internet, and the account you give us has to be read-only. That second one stays your control, not ours — and when you connect we check whether you used one: Intellrise asks your database what that account is allowed to do and puts the answer on the connection screen. It reports, it never blocks, and it says so plainly when it cannot tell. On our side we also refuse the statements we send. Three sources skip that question entirely: BigQuery, Google Sheets and uploaded CSV or Excel files need no inbound rule at all, because there is no port to open. If you do open one, the page below has the checklist, the copy-paste GRANT statements for four databases, the two outbound ranges we connect from, and the TLS position per database type: Postgres always connects with sslmode=require and there is no setting to turn it off, while MySQL, SQL Server and Redshift follow whatever your server negotiates.

Can Intellrise connect to my database?

The other prerequisite is an AI provider key of your own, on every plan including the trial. A Google Gemini key is free and takes about a minute:

How do I get a free AI key?

Sources it connects for e-commerce

Your store or orders database (PostgreSQL, MySQL, SQL Server).
Warehouses if you've centralised (BigQuery, Snowflake, Redshift).
Spreadsheets and exports (Google Sheets, CSV, Excel) for ad spend or ops.
Cross-source questions join orders with a marketing sheet in one query.

Questions e-commerce teams ask

Revenue by month, with this year vs last
Repeat purchase rate and time-to-second-order by cohort
Top products by margin, not just units
AOV by channel, device or discount used
Which SKUs are trending down over the last 8 weeks

Metrics worth keeping on a dashboard

Revenue, orders and AOV trends
New vs returning revenue split
Contribution margin by category
Cohort retention and repeat rate

Why it fits e-commerce

Store schemas are full of ambiguous fields — is "revenue" gross or net of refunds? An AI data analyst lets you clarify that once and holds the definition against the source, so later answers reuse it instead of re-guessing. It survives later sessions and a schema refresh; on a Google Sheet, re-running the tab picker clears the definitions saved for that source. You get the dashboards and exportable reports of a BI tool, without modelling the data first.

Frequently asked questions

Yes — cross-source questions join your orders database with a Google Sheet or CSV of ad spend in one query.

Get your end-to-end AI business intelligence now.

Ask in plain English, pin the answer to a dashboard, export it as CSV, Excel, PDF or PowerPoint — on the free tier that whole loop runs on one database source plus Google Sheets, and the field definitions you save carry into every later session, including after a schema refresh. One exception you should hear from us rather than discover: on a Google Sheet, re-running the tab picker — even only to add a tab — clears the definitions saved for that source and reads its schema fresh. Connecting a database is the technical part: a read-only user and network access, once. If your numbers live in a spreadsheet, none of that applies: put the file in a Google Sheet and it connects on the free tier, with no read-only user and no open port. Uploading a CSV or Excel file directly is a Pro feature, and every new account gets 14 days of Pro with no card. The one thing no plan waives is your own AI provider key, and a Google Gemini key is free to create.

Get started free Talk to us

Every new account starts on a 14-day Pro trial with no card. After it lapses, the free tier stays free.