Analysis / Data engineering and quality
Audit missing values in business data
Audit nulls, blanks and sentinel values in required business fields, quantify affected records, and prioritize issues by downstream metric impact.
Data analyst · Analytics engineer
Bring this question into Chat
Your starting prompt.
Audit [dataset] for missing values in [required fields], distinguishing nulls, blanks, sentinel values and fields that are legitimately not applicable. Calculate completeness by [source] and [period], showing affected row counts and downstream metrics at risk. Produce a prioritized issue table with sample records and proposed fixes. Preserve the original data and require a documented rule before imputing or dropping records.
Copy this starting point, then replace the placeholders with your own inputs.
Method and review
Keep the assumptions visible.
Profile keys, row counts, types, missing values and join cardinality. Retain source lineage and concrete exception records so a correction can be checked.
For this task, check
A legitimately inapplicable field should not be counted as a data defect.
Before you begin
- Bring exports you are allowed to upload, or data your Workspace can already query.
- Choose the reporting period and agree what each record represents.
Work with permitted files or queryable data. Verify the result against the original records.
Synthetic illustrative example
See the method in practice.
Synthetic input. Illustrative output checked locally; this is not a live Proforma run or customer result. Four records. Blank, null and UNKNOWN count as missing; region N/A is legitimately not applicable. Zero amount is a present value.
These invented records explain the method. They are not a recorded Proforma run.
| Record | Account ID | Amount | Region |
|---|---|---|---|
| R-1 | A1 | 100 | North |
| R-2 | A2 | null | N/A |
| R-3 | null | UNKNOWN | |
| R-4 | A4 | 0 | South |
| Field | Missing / eligible | Completeness | Review |
|---|---|---|---|
| Account ID | 1 / 4 | 75.0% | Join coverage at risk |
| Amount | 2 / 4 | 50.0% | Totals incomplete |
| Region | 1 / 3 | 66.7% | One N/A excluded |
Method
Count missing values only among applicable records. Completeness = (eligible − missing) / eligible. Preserve sentinels and original rows; an N/A exclusion requires the supplied business rule.
What the result tells you
Amount completeness is 50%; zero is not a missing amount. Region completeness uses three applicable rows. Proposed fixes must resolve business meaning before imputation or row removal.
Take the next step
Make it your investigation.
Copy the prompt above, create or open your Workspace, and paste it into Chat. Add the inputs you have permission to use and adapt the assumptions with your agent.
Start exploringYour prompt is carried by copy and paste. Signing up does not submit it or start this work automatically.
Or start with your own agent
The setup prompt includes this public task. Your agent will help you connect when needed and use the access you approve.