Skip to main content
Prompts are guided workflows that your AI assistant can follow. They encode best practices and the correct tool sequence for common tasks. You can trigger a prompt by asking naturally (the assistant matches your intent) or by referencing the prompt name directly.

​
At a Glance

PromptCategoryWhat It Does
embed-existing-dashboardSetupEmbed a dashboard from the Databrain UI
embed-blank-dashboardSetupMulti-tenant setup with per-client dashboards
query-dataSetupNatural language querying + semantic layer
populate-semantic-layerSetupBootstrap table/column descriptions
brand-my-embedCustomizationColors, fonts, charts, responsive layout
localize-embedCustomizationMulti-language, translations, calendar
setup-filtersCustomizationDropdowns, date ranges, SQL filters
secure-my-embedManagementPermissions and access controls
enable-metric-creationManagementSelf-serve metric creation modes
manage-embedsManagementList, compare, audit embeds

​
Setup Prompts

These prompts handle the initial setup of embeds and data exploration.
Embed a dashboard you’ve already built in the Databrain UI.The most common starting point. Walks through data app selection, API token creation, workspace and dashboard selection, embed creation, and frontend code generation.Example asks:
  • “Embed my sales dashboard in my React app”
  • “Set up a Databrain embed for my dashboard”
  • “I want to embed the revenue overview dashboard”
Tools used: list_data_apps → create_api_token → list_workspaces → list_dashboards → create_embed → generate_guest_token → generate_embed_codeSee full workflow →
Multi-tenant setup — each client gets their own dashboard.Creates per-client embeds using clientId for row-level data isolation. Each embed is scoped to a single client’s data.Example asks:
  • “Create per-client dashboard embeds for my SaaS app”
  • “Set up multi-tenant embeds with separate data per customer”
  • “I need a blank dashboard for each of my clients”
Tools used: list_data_apps → list_datamarts → create_embed (per client with clientId) → generate_guest_token → generate_embed_codeSee full workflow →
Query your data with natural language and manage the semantic layer.Ask questions about your data without setting up dashboards. The AI converts your question to SQL, executes it, and returns results with a chart type suggestion.Example asks:
  • “What was total revenue last month?”
  • “Compare sales across regions for Q1”
  • “Show me the top 10 products by revenue”
Tools used: list_datamarts → get_semantic_layer → update_semantic_layer (if needed) → ask_questionSee full workflow →
Auto-generate table and column descriptions to enable natural language querying.Bootstraps the semantic layer by generating human-readable descriptions from table and column names, then pushes them to Databrain. A well-populated semantic layer is required for accurate ask_question results.Example asks:
  • “Set up the semantic layer for my orders datamart”
  • “Add descriptions to all my tables and columns”
  • “Improve the semantic layer quality for better query accuracy”
Tools used: get_semantic_layer → update_semantic_layer → get_semantic_layer (verify)See full workflow →

​
Customization Prompts

These prompts help you customize the look, feel, and behavior of your embeds.
Customize colors, fonts, chart styles, responsive layout, and theme presets.Applies visual theming to match your product’s branding. Supports granular control over card styling, chart appearance (tooltips, legends, axes), and responsive breakpoints.Example asks:
  • “Make my embed match our brand — primary color #4F46E5, dark mode”
  • “Apply the corporate theme and use Inter font”
  • “Customize chart colors to use our brand palette”
Tools used: list_embeds → get_embed_details → customize_embed_theme → configure_embedSee full workflow →
Multi-language support, translations, and calendar format.Sets the UI language, calendar type, and custom translation strings for embedded dashboards.Example asks:
  • “Set up French translations for my embed”
  • “Change the calendar format to Hijri”
  • “Localize my dashboard labels to Spanish”
Tools used: get_embed_details → configure_embed (language, calendarType, translations)See full workflow →
Dashboard filters — dropdowns, date ranges, and server-side SQL filters.Configures filtering on embeds including string, number, and date filters, plus SQL-based server-side filters for advanced use cases.Example asks:
  • “Add a date range filter and a region dropdown”
  • “Set up server-side SQL filters for my dashboard”
  • “Hide the default dashboard filters and add custom ones”
Tools used: get_embed_details → configure_embed (stringFilters, dateFilters, numberFilters, sqlFilters, hideDashboardFilters)See full workflow →

​
Management Prompts

These prompts handle permissions, security, and embed lifecycle management.
Permissions, access controls, and role-based guest tokens.Configures what end-users can do within an embed — view, download, create metrics, edit dashboards — and generates guest tokens with the appropriate permission flags.Example asks:
  • “Lock down the embed so users can only view”
  • “Enable download but disable metric creation”
  • “Set up role-based access for admin vs viewer users”
Tools used: get_embed_details → update_embed (accessSettings) → generate_guest_token (with permissions)See full workflow →
Let end-users build metrics with drag-and-drop or AI-powered chat.Enables self-serve analytics by updating embed permissions and configuring the metric creation mode (visual drag-and-drop builder or AI chat mode).Example asks:
  • “Enable metric creation on my embed”
  • “Let users create metrics with the visual builder”
  • “Turn on AI-powered metric creation for end users”
Tools used: list_embeds → update_embed → configure_embed → diagnose_embed_healthSee full workflow →
List, compare, and review existing embed configurations.Provides an overview of all your embeds and their settings. Useful for auditing, comparing configurations, or finding specific embed IDs.Example asks:
  • “Show me all my embeds and their settings”
  • “Compare the configuration of my production and staging embeds”
  • “Run a health check on all my embeds”
Tools used: list_embeds → get_embed_details → diagnose_embed_healthSee full workflow →

Workflows

See these prompts in action with end-to-end walkthroughs

Tools Reference

Detailed docs for every tool the prompts use