Back to templates
Data AnalysisIntermediateUser Prompt

Dashboard Design Advisor

March 28, 2026

The Dashboard Design Advisor creates a complete dashboard specification based on your business context and data. Instead of building a dashboard by trial and error, you get a structured layout with recommended KPIs, chart types, and visual hierarchy before writing a single line of code.

Data analysts, BI developers, and product managers use this template when designing new dashboards for stakeholders, redesigning underperforming existing dashboards, or translating vague requests ("I want to see our metrics") into concrete specifications.

The prompt applies data visualization best practices: it selects chart types based on the data relationship (comparison, composition, distribution, trend), positions the most important metrics at the top-left (following natural reading patterns), and limits each dashboard to 6-8 visual elements to prevent information overload. It also recommends interactivity (filters, drill-downs) based on the audience's technical level.

This prompt is just the starting point

Score it with AI, optimize it with one click, track versions, and build your prompt library.

AI quality score on 6 criteria
One-click optimization with 3 strategies
Version history to track improvements

The Prompt

Design a data dashboard based on the following requirements:

**Dashboard Purpose**: [WHAT BUSINESS QUESTION DOES THIS DASHBOARD ANSWER, e.g., "Track weekly sales performance and identify underperforming product categories"]
**Primary Audience**: [WHO WILL USE THIS DASHBOARD AND HOW OFTEN, e.g., "Sales VP, checks daily at 9am; Regional managers, check weekly"]
**Data Sources Available**:
```
[LIST YOUR TABLES/DATA, e.g.,
- Sales transactions (date, amount, product, region, salesperson)
- Product catalog (name, category, margin, launch_date)
- Sales targets (region, month, target_amount)]
```
**Dashboard Tool**: [Tableau / Looker / Power BI / Metabase / Grafana / custom]
**Key Metrics the Stakeholder Has Mentioned**: [LIST ANY SPECIFIC METRICS REQUESTED, e.g., "Revenue, conversion rate, average order value"]

Generate a complete dashboard specification:

### 1. Dashboard Header
- Dashboard title (clear and specific)
- Global filters (date range, region, product category, etc.)
- Data freshness indicator recommendation

### 2. KPI Cards (Top Row)
Select 3-5 headline KPIs. For each:
- Metric name and calculation formula
- Comparison context (vs. previous period, vs. target, vs. benchmark)
- Conditional formatting rules (green/yellow/red thresholds)

### 3. Main Visualizations (2-4 charts)
For each visualization:
- Chart type and why it is the best choice for this data
- X-axis, Y-axis, and color/size encoding
- Specific data to plot
- One insight the chart should immediately reveal

### 4. Supporting Visualizations (1-2 charts)
Secondary charts that provide drill-down or context:
- What question they answer
- How they relate to the main visualizations

### 5. Layout Wireframe
Describe the grid layout (e.g., "2 columns, 3 rows"):
- Row 1: KPI cards
- Row 2: main charts
- Row 3: supporting charts and tables
Explain the visual hierarchy (what draws the eye first and why).

### 6. Interactivity
- What filters should be available?
- What drill-down paths make sense? (e.g., "Click a region to see city-level breakdown")
- Cross-filtering behavior between charts

### 7. Alert Recommendations
Suggest 1-2 automated alerts (e.g., "Notify via email if daily revenue drops below 80% of the 30-day average").

Usage Tips

  • Be specific about the audience: A dashboard for a VP needs 3 KPIs and a trend line. A dashboard for an ops team needs granular tables and filters. The audience changes everything.
  • List ALL available data: Include data you are not sure about. The advisor may suggest metrics you had not considered but that are derivable from your existing tables.
  • Mention the tool: Tableau, Metabase, and Grafana have different capabilities. Specifying yours ensures the recommendations are feasible.
  • Iterate section by section: If the KPI selection looks wrong, regenerate just that section with additional context rather than rebuilding the whole spec.
  • Pair with the SQL Report Query Builder: Use template DA-01 to generate the actual queries that power each chart in the dashboard.

analystdesignplanningquality-improvement

Get more from this prompt

Save it, score it with AI, optimize it, and track every version. Free to start.

AI quality score on 6 criteria
One-click optimization with 3 strategies
Version history to track improvements