Creating Dashboards and Visualisations with AI/BI
Who this is for:
Architecture / Concept Overview: Creating Dashboards and Visualisations with AI/BI
AI/BI dashboards connect directly to SQL warehouse compute and are governed by Unity Catalog permissions. The AI layer (Genie) lets business users ask questions in natural language, which the system translates into SQL behind the scenes.
%%{init: {"theme":"base","themeVariables":{"background":"#0B0E14","primaryTextColor":"#E0E6ED","lineColor":"#5D6470","darkMode":true,"primaryColor":"#2E4A4A","secondaryColor":"#374151","secondaryTextColor":"#E0E6ED","tertiaryColor":"#111827","tertiaryTextColor":"#E0E6ED","edgeLabelBackground":"#1f2937"}}}%%
flowchart LR
classDef source fill:#3F4B59,stroke:#9CA3AF,stroke-width:2px,rx:8,ry:8,color:#E0E6ED
classDef ingestion fill:#5A4B36,stroke:#C9A86B,stroke-width:2px,rx:8,ry:8,color:#E0E6ED
classDef processing fill:#535072,stroke:#8E82B4,stroke-width:2px,rx:8,ry:8,color:#E0E6ED
classDef storage fill:#2E4A4A,stroke:#5FAFA8,stroke-width:2px,rx:8,ry:8,color:#E0E6ED
classDef serving fill:#3D5550,stroke:#6BB7AA,stroke-width:2px,rx:8,ry:8,color:#E0E6ED
classDef governance fill:#5A3F52,stroke:#C28BB0,stroke-width:2px,rx:8,ry:8,color:#E0E6ED
BU[Business User] -->|Natural language| GENIE[Genie AI Layer]
ANALYST[Analyst] -->|SQL datasets| DASH[AI/BI Dashboard]
GENIE --> WH[SQL Warehouse]
DASH --> WH
WH --> UC[Unity Catalog]
UC --> DELTA[Delta Lake Tables]
BU:::source
ANALYST:::source
GENIE:::processing
DASH:::serving
WH:::processing
UC:::governance
DELTA:::storage
*Figure 1 — AI/BI dashboard architecture showing the dual entry paths: analyst-authored visualisations and Genie-powered natural language queries.*
A dashboard is composed of datasets, widgets, filters, and optional Genie spaces — each playing a distinct role.
%%{init: {"theme":"base","themeVariables":{"background":"#0B0E14","primaryTextColor":"#E0E6ED","lineColor":"#5D6470","darkMode":true,"primaryColor":"#2E4A4A","secondaryColor":"#374151","secondaryTextColor":"#E0E6ED","tertiaryColor":"#111827","tertiaryTextColor":"#E0E6ED","edgeLabelBackground":"#1f2937"}}}%%
graph TD
classDef source fill:#3F4B59,stroke:#9CA3AF,stroke-width:2px,rx:8,ry:8,color:#E0E6ED
classDef ingestion fill:#5A4B36,stroke:#C9A86B,stroke-width:2px,rx:8,ry:8,color:#E0E6ED
classDef processing fill:#535072,stroke:#8E82B4,stroke-width:2px,rx:8,ry:8,color:#E0E6ED
classDef storage fill:#2E4A4A,stroke:#5FAFA8,stroke-width:2px,rx:8,ry:8,color:#E0E6ED
classDef serving fill:#3D5550,stroke:#6BB7AA,stroke-width:2px,rx:8,ry:8,color:#E0E6ED
classDef governance fill:#5A3F52,stroke:#C28BB0,stroke-width:2px,rx:8,ry:8,color:#E0E6ED
DB[Dashboard] --> DS[Datasets<br/>SQL queries returning data]
DB --> WG[Widgets<br/>Charts · Tables · Counters · Text]
DB --> FL[Filters<br/>Cross-widget interactivity]
DB --> GS[Genie Space<br/>Natural language Q&A]
DB:::governance
DS:::processing
WG:::serving
FL:::ingestion
GS:::processing
*Figure 2 — Anatomy of an AI/BI dashboard: datasets power widgets, filters drive interactivity, and Genie provides AI-driven exploration.*
Key Terms
Prerequisites and Setup
- A SQL warehouse (serverless recommended for sub-second dashboard loads)
CAN USEon the warehouseSELECTprivileges on the tables your datasets query- Unity Catalog enabled in the workspace
Step-by-Step Implementation
Configuration Reference
| Setting | Scope | Default | Notes |
|---|---|---|---|
| Warehouse | Dashboard | Last used | Select a warehouse optimised for interactive latency |
| Auto-refresh | Dashboard | Off | Set intervals from 1 minute to 24 hours |
| Result row limit | Dataset | 10,000 | Increase up to 100,000 for large datasets |
| Genie instructions | Genie space | None | Add business context to improve AI accuracy |
| Embed credentials | Published | Viewer's identity | Each viewer sees data filtered by their Unity Catalog permissions |