Reconcile two reports that show different numbers
Pinpoints why two dashboards or reports disagree on the same metric and gives a fix plus a short explanation for stakeholders.
The prompt
Help me reconcile two reports that show different numbers for what should be the same metric.
Metric: [e.g. "March revenue", "active customers", "signups"]
Report A: [tool/source, the number, and how it is calculated - PASTE SQL, DAX, or logic if you have it]
Report B: [same details]
Size of the gap: [absolute and %]
Who noticed and why it matters: [e.g. "CFO asked before board meeting"]
Check these common causes systematically and tell me which ones fit:
- Definitions: gross vs. net, bookings vs. recognized, included/excluded statuses (refunds, tests, internal accounts, trials).
- Time: timezone, date field used (created vs. closed vs. paid), period boundaries, late-arriving data, snapshot vs. live.
- Population and filters: different segments, deleted or merged records, default filters in the BI tool.
- Joins: fan-out duplicates, inner vs. left joins dropping rows, many-to-many relationships.
- Currency, rounding, and aggregation level (average of averages, distinct counts across groups).
- Refresh timing and source system differences.
Then:
1. Propose a step-by-step reconciliation: start from a common base and add each difference until the numbers match, with the query logic for each step.
2. Build a bridge: Report A number -> each difference -> Report B number.
3. Recommend which number is "right" for which use, or which definition should become the standard.
Return the cause checklist, the reconciliation steps, the bridge table (with [ADD] where I need to supply numbers), and a short plain-English explanation for the stakeholder. Do not invent figures.
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. "March revenue", "active customers", "signups"
- same details
- absolute and %
- e.g. "CFO asked before board meeting"
- ADD
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
- Find duplicate records in my data, including near-duplicatesFinds exact and fuzzy duplicates, separates them from legitimate repeats, and gives you Excel or SQL steps to resolve them safely.
- Explain a complicated Excel formula in plain EnglishBreaks down a long or nested Excel formula step by step, says what it actually returns, and points out hidden risks.
- Build a simple spreadsheet to track ticket sales for an eventStep-by-step setup for a ticket sales tracker with a data entry form, search, totals, and payment status for fundraisers and community events.
- Measure the impact of a change when an A/B test isn't possibleChooses and plans a quasi-experimental method like difference-in-differences or synthetic control, with assumptions and checks.