create-dashboard

Create Dashboard

Create new team or initiative dashboards, organize scattered charts, build executive reporting, or set up review cadence dashboards.

Instructions

Step 0: Discovery (if unfamiliar with the feature)

Before building, understand what you're tracking:

• Search for existing dashboards/charts related to the topic
• Inspect the connected catalog and use its taxonomy search/read capabilities to find relevant events and segmentation properties; never guess names or scopes
• Ask user for clarification on primary goals, key segments, or time horizons

Step 1: Define Dashboard Purpose

Clarify:

• Who is the audience?
• What decisions will it inform?
• How frequently will it be reviewed?
• What's the narrative structure?

Step 2: Gather or Create Charts

If existing charts found (>5 relevant):

• Use Amplitude:search_amp_entities to find relevant existing charts
• Use Amplitude:get_amplitude_charts with include: "definition" to retrieve their definitions
• Identify gaps that need new charts

If few/no charts exist (<5 relevant):

• Switch to "greenfield build" mode
• Use Amplitude:query_amplitude_data to create needed charts
• Keep the returned chart edit IDs; use_amp_dashboards promotes them when creating the dashboard
• Consider searching for relevant events first with entityTypes: ["EVENT", "CUSTOM_EVENT"]

Creating new charts:

• Prototype with query_amplitude_data to verify data
• Collect the returned chart edit IDs before creating the dashboard

Step 3: Plan the Layout

Organize into logical sections:

1. Summary Row: Key metrics at a glance (headline view)
2. Trend Section: How things are changing
3. Breakdown Section: Segments and dimensions
4. Detail Section: Supporting analyses

Step 4: Create the Dashboard

Use Amplitude:use_amp_dashboards with action: "create" and:

• Clear, descriptive name
• Rows with appropriate heights (375, 500, 625, or 750px)
• Charts sized appropriately (3-12 columns)
• Rich text headers for sections
• Chart display configurations in chartMetas:
  • metric_only: Headline KPIs (single number)
  • series: Trend lines (default view)
  • converted: Funnels (conversion view)
  • table: Data tables