IRIntellrise
How-to

How to query a database in plain English

Updated 2026-07-01

Querying a database usually means writing SQL and then building a chart somewhere else. An AI data analyst collapses that into one step: you ask in plain English, it plans the query, runs it on your connected data, and shows you a chart plus the numbers behind it.

Here is how the flow works and how to get reliable answers.

  1. 1

    Connect your data source

    Connect a database, a spreadsheet or a file. The analyst reads the schema so it knows what tables and columns are available.

  2. 2

    Ask a business question

    Type what you want to know: "monthly revenue this year", "which regions grew fastest last quarter", "repeat purchase rate by cohort". Business language is fine — you don't need table or column names.

  3. 3

    Review the query plan

    On anything non-trivial, the analyst shows a plain-English plan — the sources, joins, filters and aggregation it will use — with the exact SQL one click away. Review it and approve, so you trust the answer instead of guessing at a black box.

  4. 4

    Read the chart and refine

    You get an auto-selected chart, the underlying table, and a short written insight. Refine by chatting: "add profit margin", "only the top 3", "group by month". It keeps the full conversation in context.

  5. 5

    Save, pin or export

    Pin the chart to a dashboard, save the analysis as a report, or export to CSV, Excel, PDF or slides. It's end-to-end — you never switch tools to finish the job.

How to ask questions that get good answers

  • Ask for an outcome ("revenue by month"), not a table name.
  • Add the time frame you care about ("this year", "last 90 days").
  • Refine in steps rather than one giant question.
  • If a field is ambiguous, clarify it once — the analyst can remember your definition for next time.

Why the query plan matters

Plain-English-to-SQL is only trustworthy if you can see what it did. Showing the plan and the exact SQL before running turns the analyst from a black box into something you can verify — which is what makes it safe to use for real decisions.

Frequently asked questions

Common databases, cloud warehouses, Google Sheets, and uploaded CSV/Excel files — and you can even join across sources in one question.

Related

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

Conversational analytics with AI that understands your data — no SQL, no data team required.