CRM Revenue Data Integrity Auditor
Audit CRM exports for data quality issues, operational risks, and actionable cleanup rules to ensure reporting and automation accuracy.
Customise & copy
Add the context you have. The prompt updates as you work.
Paste the raw CRM dataset or field export in CSV, JSON, or tabular text format.
List the core revenue fields to focus the audit on.
Provide basic context on current revenue pipeline stages or automation rules.
Live prompt
3 fieldsYou are a revenue data quality engineer and CRM auditor. Audit the provided raw CRM data export to identify missing, contradictory, stale, duplicated, or structurally inconsistent revenue data. Do not invent missing values or fabricate records. CRM Data Export: {{crm_data_export}} Core Revenue Fields to Audit: Deal Amount, Close Date, Stage, Owner, Account ID Pipeline Stages and Automation Rules Context: {{pipeline_context}} Target Output Format: 1. Audit Summary Table: Categorize each identified data issue including Severity (High/Medium/Low), Affected Process, Operational Consequence (specific reporting or automation failure), and Supporting Evidence from the dataset. 2. Data Cleanup Rules: Provide specific, deterministic data cleanup rules and ownership actions for each class of error without assuming unstated values.
Proof before you use it
A real example
Tested on gemini-3.1-flash-lite on 2026-09-06
{
"revenue_fields": "Subscription ID, MRR, Renewal Date, Lifecycle Stage, CS Rep",
"crm_data_export": "Subscription ID,MRR,Renewal Date,Lifecycle Stage,CS Rep\nSUB-101,500,2026-05-01,Active,Bob Jones\nSUB-102,0,2023-01-15,Churned,\nSUB-101,1200,2025-12-01,Expansion,Bob Jones\nSUB-103,-200,2024-06-30,Trial,Alice Admin",
"pipeline_context": "Lifecycle stages: Trial -> Active -> Expansion -> Churned. MRR cannot be negative and Active subscriptions must have a positive MRR."
}A small ritual that works
How to use it
- 01Paste your raw CRM export (CSV/JSON) into the data field.
- 02Define the core revenue fields you are auditing (e.g., Deal Amount, Close Date).
- 03Provide your pipeline stages and relevant automation rules for context.
- 04Review the generated audit table and implement the deterministic cleanup rules provided.
Why it works
The prompt successfully enforces a structured, evidence-based CRM data audit by strictly binding the model to evaluate provided raw exports against specific core revenue fields and pipeline automation rules. It prevents hallucination by explicitly prohibiting the invention of missing values or fabricated records, requiring the output to split findings between an actionable audit table and deterministic cleanup rules.
Where it fails
INSUFFICIENT_EVIDENCE
Customisation tips
Modify the 'pipeline_context' variable to include strict state transition rules or required field dependencies (e.g., 'Closed Won requires non-zero amount and valid close date') to guide the audit table toward specific logical inconsistencies present in your dataset.
Watch-outs
- Ensure the CRM data export format matches tabular or JSON structures cleanly so the model can isolate record IDs and field values accurately.
- Watch for LLMs attempting to guess or auto-correct invalid data (like negative revenue or missing owners) rather than adhering strictly to deterministic data quality and ownership actions.
- Verify that the fields listed in core revenue fields actually exist in the provided export to prevent phantom data mismatch errors.
Works in
Was this useful?
Submit your variation
If your version helps, it may be published with your name and a link back to you.
Related prompts
Want to make AI useful across your team? Explore Atul's training.