AppsAutessaDB

Data lake and analytics · AutessaDB

Ask in plain language

Ask turns a plain-language question about your data into SQL. It reads the tables' descriptions, synonyms, measures and verified queries from the semantic layer, proposes a query, and puts it in the SQL Workbench editor, where nothing runs until you click Run.

Goes beyond a typical managed database
Ask · order_linesproposed SQLSAMPLE

◆ ask in plain language

“Monthly net sales by region this year”

-- uses measure revenue := SUM(net_amount)
-- "net sales" is a synonym of net_amount
SELECT region, date_trunc('month', order_date) AS month,
       SUM(net_amount) AS revenue
FROM order_lines
WHERE order_date >= DATE '2026-01-01'
GROUP BY 1, 2 ORDER BY 2, 1
RunScans ~1.2 GBSave as verified query
Nothing runs until you click Run.

-- the problem

Not everyone with a data question writes SQL

Operations leads, finance and support managers know exactly what they want to know, but not which column means net sales. Ask lets them start in words. Because the answer is SQL in the editor, anyone can check it, estimate it, run it and save it as a verified query for next time.

What you get

  • Ask from a data lake table's detail page or from the SQL Workbench.
  • Proposals use your descriptions, synonyms, measures and verified queries, so "net sales" means what your team means.
  • The proposed SQL lands in the editor, and nothing runs until you click Run.
  • Check the scan estimate first, then run, download, or save the query as a verified query.
  • Queries run as you, so results respect your sharing, row rules and masks.
  • The same capability is in the CLI as autessadb analytics ask, for terminals and scripts.

-- how it works

How does ask in plain language work in AutessaDB?

  1. Ask

    Click Ask and describe what you want to know, such as monthly revenue by region this year.

  2. Review

    Read the proposed SQL in the editor and watch its estimate.

  3. Run

    Click Run; results arrive as soon as the job finishes.

  4. Keep it

    Save as verified query so agents and teammates reuse the same answer.

-- every option

How Ask works

optionwhat it does
InputA plain-language question about the tables you can read.
ContextDescriptions, grain, synonyms, measures, joins and verified queries.
OutputProposed SQL in the workbench editor.
RunningOnly when you click Run.
SecurityThe query runs as you, with your row rules and masks.

-- example

A proposal for "monthly revenue by region this year"sql
SELECT region, date_trunc('month', order_date) AS month, SUM(net_amount) AS revenue
FROM order_lines
WHERE order_date >= DATE '2026-01-01'
GROUP BY 1, 2
ORDER BY 2, 1

Full reference in the AutessaDB CLI docs and the API reference.

-- permissions

Who can do what?

accesscan
READ on the tablesAsk, review and run proposals.
ADMINImprove the semantic layer that Ask relies on.

◆ AI assist

Where AI helps

Ask is text-to-SQL grounded in your semantic layer: the better your descriptions, measures and verified queries, the closer the first proposal is to the query you would have written.

AI in AutessaDB works inside the same access rules as the person using it, and schema changes always wait for a person to apply them.

-- relations

How it connects

autessadb feature

Semantic layer

What Ask reads to write good SQL.

autessadb feature

SQL Workbench

Where proposals land and run.

autessadb feature

Data agents

The same idea, in a conversation.

-- faq

Questions about ask in plain language

Does Ask run queries on its own?

No. Ask proposes SQL and puts it in the editor; nothing runs until you click Run.

How does Ask know what my columns mean?

From the semantic layer: table and column descriptions, synonyms, measures, joins and verified queries.

Can I use Ask from the command line?

Yes. autessadb analytics ask turns a question into proposed SQL for the tables you name.

$ autessa autessadb tables create

Try ask in plain language in AutessaDB

Type a question such as "monthly revenue by region this year" and Ask proposes SQL from your descriptions, measures and verified queries. Nothing runs until you click Run.

Read the AutessaDB guide or install the CLI.

100% customizable, code and all

Make AutessaDB fully your own.

Use it out of the box, then change anything. Ask Autobot, Autessa’s AI builder, for a new field, screen, report, workflow or agent and it builds it into your copy of the app. Or open the code and edit it yourself. Nothing is locked: the app, its data and its code are yours.

Start free and make it yours