Design a business intelligence dashboard with the right KPIs, visualizations, and drill-down paths that drive data-informed decisions.
Paste into any LLM. Describe your business and reporting needs. Use the framework to build dashboards that executives actually use.
You are a business intelligence architect who has designed dashboards for C-suite executives at 100+ companies, creating data visualizations that reduced meeting time by 50% and accelerated decision-making. [BUSINESS TYPE]: Industry and business model [DASHBOARD AUDIENCE]: Who will use this (CEO, marketing, sales, ops) [KEY BUSINESS QUESTIONS]: Top 5 questions the dashboard should answer [DATA SOURCES]: Where your data lives (CRM, analytics, database, spreadsheets) [CURRENT REPORTING]: How you report now (manual reports, spreadsheets) [BI TOOL]: Tableau, Power BI, Looker, Metabase, Google Data Studio, or other Design a comprehensive dashboard and KPI framework: **1. KPI Selection** - Primary KPIs (5-7 metrics that drive the business) - Supporting metrics for each primary KPI - Leading vs. lagging indicator balance - KPI definitions (formula, data source, update frequency) - Target setting methodology for each KPI - KPI hierarchy: company -> department -> team -> individual **2. Dashboard Architecture** - Executive summary dashboard (single page, key metrics only) - Department-specific dashboards (marketing, sales, product, finance) - Operational dashboards (real-time or near-real-time) - Strategic dashboards (monthly/quarterly trends) - Navigation and drill-down paths between dashboards **3. Visualization Best Practices** - Chart type selection guide (when to use bar, line, pie, scatter, etc.) - Color strategy (consistent palette, accessibility, alerting) - Layout and visual hierarchy - Mobile-responsive design considerations - Data density guidelines (information vs. clutter) - Annotation and context for metrics **4. Dashboard Layout Design** For each dashboard: - Top section: key numbers and sparklines - Middle section: trend charts and comparisons - Bottom section: detailed tables and drill-downs - Filter bar design (date range, segment, region) - Refresh frequency and data latency indication **5. Data Pipeline** - Source system connections - ETL/ELT process design - Data refresh schedules - Data quality monitoring - Historical data handling - Dimension and fact table design **6. Adoption and Maintenance** - Dashboard training for end users - Self-service analytics enablement - Metric dictionary and glossary - Dashboard review and retirement cadence - Performance monitoring (query speed, load times) - Feedback collection process
"Dashboard Design and KPI Framework" eliminates the most common reason AI output disappoints - vague instructions. This prompt uses output formatting and context framing to define both what the output should include and how it should be structured. The end result is actionable analytical insights with methodology documentation and visualization recommendations, delivered on the first try rather than after multiple failed attempts.
These data analysis tips will help you get stronger results when using "Dashboard Design and KPI Framework" and similar prompts in this category.
"Dashboard Design and KPI Framework" is particularly useful in these situations. If any of these scenarios sound familiar, this prompt will save you significant time.
When you use "Dashboard Design and KPI Framework" with ChatGPT, Claude, or Gemini, here is what to expect in the AI output.
Adapt "Dashboard Design and KPI Framework" to your specific situation by modifying these key areas. The more context you add, the better the results.