Audit and retire unused or duplicate dashboards
A plan to inventory BI content, find what's unused or redundant, and retire it safely without breaking anyone's workflow.
The prompt
Help me audit our BI content and safely retire unused or duplicate dashboards.
BI tool(s): [e.g. Power BI, Tableau, Looker]
Inventory data: [PASTE list of reports/dashboards with owner, created date, last modified, view counts over the last 90 days, data sources]
Known problems: [e.g. "five versions of the sales dashboard with different numbers", "slow refresh capacity"]
Constraints: [regulatory or audit reports that must be kept, executive reports, embedded reports]
Steps:
1. Define classification rules and apply them: keep, merge, refresh/fix, archive, delete. Suggest thresholds (e.g. no views in 90 days, single viewer, owner has left).
2. Identify duplicates or near-duplicates by name, data source, and metrics shown; recommend a single "certified" version for each topic.
3. Flag reports to protect regardless of usage (quarter-end, annual, compliance, embedded in apps).
4. Plan the retirement process: notify owners and viewers, archive before deleting, a grace period, and a way to restore.
5. Suggest governance to prevent sprawl: certification, naming conventions, workspace structure, and a periodic review cadence.
Return:
- The classified inventory: Report | Owner | Usage | Recommendation | Reason | Replacement.
- A summary of what changes (counts by action, expected capacity or cost savings).
- A ready-to-send notification message to report owners and viewers.
- A one-page governance policy draft.
Base recommendations only on the inventory I provide. Where usage data is missing, mark the item [CHECK] instead of guessing.
Highlighted [brackets] are blanks to replace with your own details.
Fill in the blanks and use this promptMore Data & Analysis prompts
What to fill in
- e.g. Power BI, Tableau, Looker
- CHECK
How this prompt is built
This prompt follows the Few-Shot structure (Few-shot prompting). A few-shot prompt includes one or more worked examples of the input and the output you want, so the model can copy the pattern instead of guessing it.
Related prompts
- Explain, debug, or speed up a SQL, Python, or DAX snippetExplains what an existing query or script does, fixes errors, and optimizes it.
- Find what my dashboard is not telling meReviews a dashboard for blind spots, missing comparisons, vanity metrics, and misleading views, and suggests what to add.
- Compare two Excel sheets and flag every differenceMatches records between two spreadsheets or lists, flags missing, extra, and changed rows, and gives formulas to reconcile them.
- Build a dynamic Excel dashboard from my raw dataPlans a refreshable one-page Excel dashboard for management, with tab layout, KPIs, pivot charts, slicers, and the formulas behind them.