Skip to main content
Natural-language dashboards let you describe an analytics view in everyday language. Famulor prepares a preview, and nothing is added to your dashboard until you confirm it.

Build a dashboard view

  1. Open a custom dashboard.
  2. Select Create with Milian.
  3. Describe the metrics, time range, comparison, and filters you need.
  4. Select Preview insights and review every proposed card.
  5. Select Add insights to save the cards.
For example:
Show success rate and average duration for outbound calls in the last 30 days.
Generated cards work like manually created dashboard widgets. You can edit, resize, reorder, or remove them afterward.

Supported questions

You can ask about conversation volume, activity over time, success rate, call duration, talk minutes, assistant and campaign performance, outcomes, status, direction, sentiment, and recent conversations. Supported time ranges include 7, 14, 30, and 90 days, with optional comparison to the previous period. Weeks, months, and quarters map to these ranges, and the preview tells you when the closest available range was used. Questions about consumed minutes are answered with the total talk time of your conversations, for example:
List assistants with call count and talk minutes for the last 30 days.
This adds a call count, the total talk time, and an assistant leaderboard that shows calls, talk minutes, and success rate per assistant. Generated cards use the same versioned semantic metric catalog as the rest of the dashboard, so every card stays editable afterward. Provider costs and internal billing fields are intentionally unavailable. If a question mixes conversation metrics with costs or credits, the preview keeps the conversation metrics and notes what was left out. Use the minutes and credits views for balances and billing. Filters use the values available in Famulor. If a request cannot be represented, the preview explains what to change instead of adding an uncertain result.

Post-call fields and other requests

The preview covers the conversation metrics above. When a request uses your assistants’ post-call analysis fields — for example “calls by call reason” or “share of callers who asked for a callback” — or anything else the preview can’t build, Milian opens in the chat panel and builds the insights on the same dashboard. Milian reads the field names from your assistants’ Analysis settings, so this works with whatever fields your workspace uses. You can also add these insights yourself with Add insight; see Dashboard widgets.
Dashboards always use data from the active workspace. Preview every proposed card before adding it, especially when your question contains several filters.

Public API

Use POST /api/v1/dashboards/{id}/natural-language to generate a preview. Send the returned plan to PUT /api/v1/dashboards/{id}/natural-language to validate and save its widgets. With the Famulor CLI, use famulor preview-natural-language-dashboard <id> --prompt "…" and famulor save-natural-language-dashboard <id> --plan '<plan JSON>'. Both operations require the dashboards:write scope. See the API reference for the complete request and response schema. A preview request that mentions post-call analysis fields is rejected with an explanation; create those insights with the widget endpoints instead.