Reconcile conflicting metric totals between two reports
Diagnose discrepancies between two data sources to identify the root cause of differing metric totals.
You getDiscrepancy Snapshot, root Cause Analysis and resolution Protocol
Prompt
Act as a senior data analyst and financial systems auditor. Reconcile the discrepancy between the two pasted report summaries.
Rules:
- Identify likely structural causes for variance (such as timezone cutoffs, timezone offsets, gross vs. net calculations, status filters, or cancellation exclusions).
- Break down the variance into testable hypotheses ranked from most likely to least likely.
- Avoid making assumptions; highlight what definitions or parameters must be confirmed in the underlying data systems.
- Note that this guidance provides analytical frameworks only, not formal audit advice.
Output format:
- Discrepancy Snapshot (Total Difference, Percentage Gap)
- Root Cause Analysis (Numbered list of hypotheses with validation tests)
- Resolution Protocol (Checklist to align definitions across teams)
Here are the two reports and their notes:Example output
Paste the figures, date ranges, and metric definitions from both systems directly below the prompt in ChatGPT, Claude, or Gemini. Follow up by providing any known query filters or database table schemas to get a targeted SQL comparison script.
Make it repeatable
Keep using this prompt without pasting it in every time.
Prompt details
- By
- Prompts-GPT editors
- Published
Did this prompt work?
Keep exploring
More like this
Build standardized KPI definition templates for teams
Standardize team metrics and eliminate conflicting calculations for critical business KPIs. Use this before building dashboards or quarterly reports.
Summarize customer segment shifts for executive updates
Convert raw cohort and customer segmentation tables into clear movement summaries. Use this to highlight changing customer mixes before monthly leadership reviews.
Translate statistical model outputs into plain business decisions
Turn regression coefficients, p-values, and confidence intervals into direct business trade-offs. Use this when presenting analytical models to non-technical executives.
Create an anomaly investigation checklist for analytics teams
Run a disciplined diagnostic process before investigating metric shifts. Use this checklist whenever unexpected data spikes or drops appear in reports.
Differentiate structural null values from missing data
Identify whether null values represent expected business logic or export dropouts. Use it when auditing schema quality or preparing datasets for modeling.
Map inconsistent export columns to target schemas
Match disparate, poorly named export headers to a structured target data schema. Use it when consolidating CSV reports from multiple platforms.
- Separate true anomalies from pipeline data errors
- Triage sudden metric spikes for event tracking bugs
- Audit a metric definition guide for ambiguity
- Evaluate pricing tier performance from subscriber data
- Identify top customer churn drivers from exit feedback
- Separate correlation from causation in business metrics