Flag impossible or suspicious values in my data
Checks your data against logic and business rules for impossible, placeholder, and implausible values, and gives reusable validation rules.
The prompt
Check my data for values that are impossible or suspicious and need a closer look before I use them.
Data: [PASTE SAMPLE ROWS and column names, with units]
What the data describes: [e.g. "sales orders", "employee records", "sensor readings"]
Business rules I know: [e.g. "discount can't exceed 40%", "hire date comes before termination date", "prices are in USD"]
Check for:
- Impossible values: negative quantities or ages, percentages over 100, future dates, dates before the business existed, end dates before start dates.
- Conflicts between columns: status "closed" with no close date, totals that don't equal the sum of their parts, a city in the wrong country.
- Suspicious values: placeholders and defaults (0, 999, 1/1/1900), the same value repeated far too often, numbers off by a factor of 10, 100, or 1,000 (unit or decimal errors), text in number fields.
- Values that are possible but implausible for this business.
Return:
1. A table: Row or ID | Column | Value | Rule broken | Impossible or suspicious | Likely cause | Suggested action.
2. Reusable validation rules for this dataset, written so they can be built as Excel data validation or formulas, or as SQL checks.
3. Questions to ask the data owner.
Don't correct values yourself: flag them and suggest a fix for a person to confirm. Keep genuine extreme values separate from errors.
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
- PASTE SAMPLE ROWS and column names, with units
- e.g. "sales orders", "employee records", "sensor readings"
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
- Explain a dataset or report in plain business languageExplains what a dataset or report contains, what each column or metric means, and what it shows, in words anyone can follow.
- Find what my dashboard is not telling meReviews a dashboard for blind spots, missing comparisons, vanity metrics, and misleading views, and suggests what to add.
- Create a data-quality checklist for a recurring report or datasetA reusable pre-publish checklist with checks, formulas, pass thresholds, owners, and what to do when a check fails.
- Clean and standardize spreadsheet data with a log of every changeCleans pasted spreadsheet rows, fixes formats and inconsistencies, and gives you a change log plus steps to repeat it in Excel.