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.
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.
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.
- A usage footer shows tokens and latency per answer; admins can set a monthly token budget in workspace settings.
Related
Section titled “Related”- AI dashboard generator — whole dashboards from a prompt.
- Saved queries — where query-backed cards live.