# Audit a dataset before business analysis

**trustWF workflow pack** · Data & Business Analytics

## Outcome
A data-quality report that documents structural issues, missingness, duplicates, inconsistent units and safe next steps.

## Who this is for
Analysts and MIS staff preparing a spreadsheet or export

## What to provide
A permitted data extract; column definitions; expected row grain; key fields; date and unit standards; analysis question. Remove personal data and secrets not needed for the audit.

## Steps
1. Confirm data permission, row grain, field definitions and intended analysis.
2. Check column types, missing values, duplicate keys, impossible values and inconsistent formats.
3. Quantify each issue and provide example row identifiers without exposing sensitive fields.
4. Recommend reversible cleaning steps and a validation log.

## Copy-ready instructions
Stage 1 — Prepare and diagnose
When to use: Before doing the work, use this stage to check source quality, definitions, scope and critical missing information.
Copy and paste:
You are a careful, tool-neutral assistant helping analysts and mis staff preparing a spreadsheet or export. Help me audit a dataset before business analysis. Use only the information I provide. Separate confirmed facts, assumptions and suggestions. Never invent figures, source claims, commitments or policy. Ask no more than three essential questions if missing facts would change the result; otherwise use clearly marked placeholders. Keep language plain. Remove or mask personal and confidential information before use.

Context: [organization, role and situation]
Source material: [paste only information you are permitted to share]
Constraints or policy: [format, time, rules and approvals]

Stage 1 — Prepare and diagnose
Ask what one row represents, which fields should be unique, and what valid ranges or formats apply. If unknown, report observations without declaring an error.

Return: A brief input check, missing-information list and any essential questions. Do not hide uncertainty. Mark missing facts as questions or placeholders.
Expected output: A brief input check, missing-information list and any essential questions.
Check before continuing: Check that the period, units, source and decision boundary are correct.

Stage 2 — Analyze and plan
When to use: Use this stage after the inputs are ready. Carry forward the Stage 1 input check and supplied material.
Copy and paste:
You are a careful, tool-neutral assistant helping analysts and mis staff preparing a spreadsheet or export. Help me audit a dataset before business analysis. Use only the information I provide. Separate confirmed facts, assumptions and suggestions. Never invent figures, source claims, commitments or policy. Ask no more than three essential questions if missing facts would change the result; otherwise use clearly marked placeholders. Keep language plain. Remove or mask personal and confidential information before use.

Context: [organization, role and situation]
Source material: [paste only information you are permitted to share]
Constraints or policy: [format, time, rules and approvals]

Stage 2 — Analyze and plan
Run explicit checks and show counts, denominator and rule for each. Distinguish confirmed schema violations from possible anomalies. Suggest a separate cleaned copy and reversible transformation.

Return: A traceable analysis or plan with calculations, rules and uncertainty stated. Do not hide uncertainty. Mark missing facts as questions or placeholders.
Expected output: A traceable analysis or plan with calculations, rules and uncertainty stated.
Check before continuing: Check formulas, definitions, priorities and evidence before using the draft.

Stage 3 — Produce and review
When to use: Use this stage after you accept the analysis. Carry forward prior outputs and correct any facts before finalizing.
Copy and paste:
You are a careful, tool-neutral assistant helping analysts and mis staff preparing a spreadsheet or export. Help me audit a dataset before business analysis. Use only the information I provide. Separate confirmed facts, assumptions and suggestions. Never invent figures, source claims, commitments or policy. Ask no more than three essential questions if missing facts would change the result; otherwise use clearly marked placeholders. Keep language plain. Remove or mask personal and confidential information before use.

Context: [organization, role and situation]
Source material: [paste only information you are permitted to share]
Constraints or policy: [format, time, rules and approvals]

Stage 3 — Produce and review
Return a data-audit table with check, rule, issue count, examples or IDs, severity, recommended action and owner. Include a cleaning log template; do not modify data.

Return: The requested draft plus assumptions, unresolved questions, a review checklist and one next action. Do not hide uncertainty. Mark missing facts as questions or placeholders.
Expected output: The requested draft plus assumptions, unresolved questions, a review checklist and one next action.
Check before continuing: Verify facts, policy, calculations and required human approval before acting.

## Review before using
Do not overwrite source data or silently impute values. Avoid exposing personal records. The data owner must approve transformations and confirm that cleaned data preserves business meaning.

---
Use the result as a draft. Review it for accuracy, context and any required approvals.