AI-assisted SQL generation

Instead of writing SQL by hand, you can describe what you want in plain language and have arcodash draft the query for you.

How it works

Type a question about the connected data source (e.g. “monthly signups by plan for the last 6 months”) and arcodash generates a SQL statement for you to review, using the currently connected data source’s dialect. If you already have a query in the editor, describing a change refines the existing SQL instead of starting over.

[!NOTE] This only ever produces SQL text. It never runs the generated query for you — you review it in the editor and hit Execute yourself, exactly like any SQL you typed by hand.

The “Ask with AI” tab sits next to “SQL Editor” and holds the question box and the Generate SQL button:

What’s sent, and what isn’t

Generating SQL sends the connected data source’s schema — table and column names only — plus your question to Google’s Gemini API, using your organization’s own key. It never sends any row-level data from your database.

Admin configuration

This feature is optional and configured per organization. An admin enables it by adding an API key (in AI Settings) and can set a rate limit on how many generation requests are allowed per user per minute. Whether AI generation is available to you at all depends on whether your organization’s admin has configured it — if it isn’t, the feature simply reports that no key is configured and points you at AI Settings rather than failing silently.

Once configured, generating SQL is available to any user with access to the target data source — using the feature doesn’t itself require admin rights, only configuring it does.

[!TIP] Always read the generated SQL before running it, the same as you would review any query someone else handed you — it’s a draft to check, not a black box to trust blindly.

Where to go next

• The SQL editor — where the generated SQL lands.
• Parameters — parameterize a query once you’ve got the SQL right.