Skip to content
DataSquaresDocs

AI chat: ask your data

AI Chat is a data agent over your connected sources: ask a question in plain language and it answers with numbers, charts, and the SQL it actually ran.

Asking questions

Section titled “Asking questions”

Type anything from “Show top customers by revenue” to “Compare Q1 vs Q2 sales” (suggestion chips get you started). The agent works in conversations — tabbed threads with history that persists across sessions; start a new chat per line of inquiry. Reopening a thread restores it completely: the answers, the generated SQL, the charts, links to anything the agent created, and your own thumbs ratings — you pick up exactly where you left off.

What answers look like

Section titled “What answers look like”
  • Written answers with the supporting numbers, plus a live chart preview panel and data table alongside the thread.
  • The generated SQL behind any query-backed answer is one click away in a collapsible block — nothing is a black box.
  • For multi-step work, the agent shows its progress steps, may propose a plan for you to confirm, and asks clarifying questions with clickable options when your question is ambiguous.
  • Each answer ends with follow-up suggestion chips, and links to any dashboards or reports the agent created for you.

Grounded in your governance

Section titled “Grounded in your governance”

The agent doesn’t improvise definitions:

  • Governed metrics — ask “how is revenue pacing?” and it lists and evaluates your governed metrics (targets, certification and all) instead of hand-writing SQL for a KPI that already has a blessed definition.
  • Business glossary — questions and field names are matched against your glossary, so “active customers” means what your organization defined it to mean.
  • Analysis tools — beyond queries, the agent can detect anomalies, surface key influencers behind a change, forecast a trend (the same statistics behind card insights), and even create a metric alert for you when you ask to be told next time.

From answer to dashboard

Section titled “From answer to dashboard”

Every result carries Copy and Save to Dashboard. Saving a query-backed result creates a live card — backed by a saved query, re-runs on refresh, and participates in the dashboard’s filters. (A chart-only result saves as a static snapshot.) You choose which dashboard it lands on.

Practical notes

Section titled “Practical notes”
  • Rate the answers — thumbs up/down feed back into quality.
  • If a response errors mid-stream, Retry re-sends your last message.
  • Errors say what’s actually wrong: if AI hasn’t been configured on the server you’re told exactly that (ask your admin), and quota states — like an exhausted monthly token budget — are called out distinctly rather than surfacing as a generic failure.
  • A usage footer shows tokens and latency per answer; admins can set a monthly token budget in workspace settings.

On mobile

Section titled “On mobile”

The Android app (Early Access) has an Ask AI tab: the same governed agent, streaming answers with live tool progress, links that open the dashboards it creates for you, and conversation history you can resume or delete. The tab appears only when your server has AI configured.

Section titled “Related”
© 2026 DataSquares