Create a full dashboard from a single prompt with Luzmo's Dashboard Agent — available both in Studio and via the API. Instead of building one chart at a time, describe the dashboard you want and let the agent assemble the charts, layout, and filters together.

In this article, you will learn how to:

  • Find and use the Dashboard Agent in Studio and the Embedded Dashboard Editor
  • Describe a dashboard goal — including with reference images or voice — and get a first working layout
  • Edit, translate, and ask the agent about an existing dashboard
  • Generate dashboards programmatically at scale through the API
  • Combine AI-generated charts with manually built ones in the same dashboard

Why dashboard-level generation is a different problem

Generating one chart only requires the AI to pick a visualization type, a metric, and a dimension. Generating a dashboard requires it to also decide:

  • Which charts belong together to answer the stated goal
  • How those charts should be arranged on the canvas — or follow a layout you specify yourself
  • Which filters or interactive controls should apply across multiple charts, not just one
  • Whether charts should be linked (for example, selecting a segment in one chart filtering the others)

Because of this, a dashboard-level prompt reads more like a brief than a chart-level prompt. Instead of describing one visualization, describe the outcome the dashboard should support.

Where to find the Dashboard Agent

In Studio and the Embedded Dashboard Editor (EDE), look for the Agent button and panel in the side menu. The dashboard empty state also points to it as a way to start a new dashboard.

In EDE, the Dashboard Agent is only shown in clients using the updated EDE with flag_embedded_studio_update. It's enabled by default; to disable it, add !flag_dashboard_agent to the feature_overrides array in your Embed token request.

Example: build a monitoring dashboard from a goal

Build me a dashboard tracking weekly active users, retention, and churn by customer segment, for the last two quarters.

A reasonable AI-generated result includes a small set of charts covering each named metric, a segment filter that applies across all of them, and a sensible default layout. From there, you can continue the conversation:

Add a filter for plan tier as well, and make the churn chart a trend line instead of a bar chart.

This mirrors how you'd iterate with a colleague building the dashboard with you — refining scope and layout incrementally rather than starting over.

Guiding the agent with more than text

The prompt box isn't limited to typed descriptions:

  • Reference images — attach an image of the dashboard you want (a sketch, a competitor's dashboard, a screenshot) and the agent uses it as a layout reference.
  • Voice — talk to the agent instead of typing your prompt.

Example: start from an existing dataset

If you already know which dataset the dashboard should use, say so up front to keep the result grounded in the right data:

Using the product usage dataset, build a dashboard that shows adoption of our three newest features over the last quarter, broken down by account tier.

Being specific about the dataset (and, where relevant, which columns matter) reduces the chance the AI reaches for the wrong metric or an unrelated dataset. See Preparing your data for AI for more on getting your datasets ready for this.

Editing, translating, and querying an existing dashboard

The Dashboard Agent isn't only for building from scratch — point it at an existing dashboard and it can:

  • Edit it: add, move, or delete charts and filters through conversation instead of manual configuration.
  • Translate it: rewrite every label on the dashboard in one go — try "Translate this dashboard to German and French."
  • Describe it: ask what's currently on the dashboard — items, filters — and get a summary back.
  • Explain itself: ask "Tell me what you can do" to see its current capabilities and limits.

Every change the agent makes can be safely undone with the Undo button below its latest message, so it's safe to experiment with a prompt before committing to it.

Refining an AI-generated dashboard

Treat the first generated result as a strong starting layout, not a final answer:

  • Swap a chart type if a different visualization fits the data better than what was generated.
  • Adjust the layout — resize, reorder, or regroup charts once you can see them together.
  • Add or tighten filters so the dashboard matches how your team actually wants to slice the data.
  • Remove charts that don't earn their place — a generated dashboard errs toward covering the stated goal completely, which can mean more charts than are actually useful.

Generating dashboards at scale through the API

Beyond Studio, dashboards can be generated programmatically through the /aiprompt endpoint (agent: 'dashboard'), then persisted with create('securable'). This is useful when you need more than one hand-built dashboard, for example to:

  • Automate dashboard creation during onboarding or bulk provisioning
  • Migrate dashboards from a competitor
  • Generate ad-hoc dashboards personalized per end user, on the fly, instead of hand-building and maintaining one dashboard per customer or use case

See Generate a dashboard with the Dashboard Agent in the developer docs for the API reference and examples.

Combining AI-generated and manually built charts

You don't need to choose one approach for the whole dashboard. It's common to generate an initial set of charts with AI, then add one or two manually built charts for a specific metric with unusual requirements (a custom formula, a specific formatting need, or a chart type the AI didn't select). AI-assisted and manually built charts behave the same way once they're on the canvas — there's no distinction in how they're edited, filtered, or shared afterward.

Where this fits with the rest of your AI toolkit

Dashboard-level AI assistance is about building the dashboard faster. It's distinct from:

  • Luzmo IQ, which answers ad hoc questions for someone exploring data — it doesn't produce a persistent, reusable dashboard for others.
  • AI Summary, which narrates what's already on a built dashboard rather than assembling one.

If your goal is a reusable asset other people will come back to and explore, build it here. If your goal is answering a one-off question, IQ is usually the faster path.

Related resources

Previous
Next

Need more information?

Do you still have questions? Let us know how we can help.
Send us feedback!