Skip to content

Card insights: explain, analyze, summarize

Every data card on a dashboard carries insight tools in its context menu. Explain this change and Analyze are statistical — the math runs on the server whether or not AI is configured. Summarize with AI writes a narrative and does need AI set up. View access is enough for all of them, and every result is computed under your data permissions — with row-level security in place, the analysis sees exactly the rows you’re allowed to see.

When a number moved and you want to know why, right-click the card (or open its menu) and choose Explain this change.

  1. The tool compares the current period against the previous one by default; switch to a custom baseline if you want a different comparison window.
  2. Pick the dimension to break the change down by — region, product, channel, whatever the card’s model offers.
  3. You get the overall delta decomposed by that dimension: which members drove the change up, which pulled it down, and by how much.

It’s a fast first answer to “what happened here?” before you drill into the underlying data.

Analyze on the same card menu opens a panel with three tabs. All three are deterministic statistics on the card’s own query results.

Flags points that deviate from the series’ expected range. A sensitivity slider (2–4σ) controls how strict the detection is — lower values flag more points, higher values only the clear outliers. Each flagged point shows how far it deviated.

Pick up to 8 breakdown dimensions and the tool ranks them by how much of the measure’s variance each one explains — a quick read on which dimension actually matters for the number you’re looking at.

Projects the series 3, 6, or 12 periods ahead with a 95% confidence band, so you see both the expected path and the uncertainty around it.

Each tab has an optional Phrase it toggle that asks the AI to write a short narrative of the findings. This is the only part of Analyze that touches AI — the anomaly detection, influencer ranking, and forecast all work without it. If AI isn’t configured on your server, the toggle simply isn’t available; the numbers still are.

Summarize with AI on a card’s menu generates a short written summary of what the card shows and stores it on the card:

  • The summary appears as a dismissible footer note under the card — and travels with it, so people on shared links and embeds see it too.
  • Regenerate whenever the data has moved on, or choose Remove AI summary to delete it from the card.

Summaries require AI to be configured on the server by your administrator; usage counts against the workspace’s monthly token budget.

Tool Works without AI
Explain this change ✓ — pure statistics
Analyze (anomalies, influencers, forecast) ✓ — pure statistics
Analyze → Phrase it ✗ — needs AI configured
Summarize with AI ✗ — needs AI configured

Either way, nothing escapes your permissions: every computation and every narrative is based only on data you can already see.

  • Exploring dashboards — the rest of the viewer toolkit.
  • AI chat — the same anomaly, influencer, and forecast tools, conversationally.
  • Metric alerts — get notified when the number crosses a threshold.