Clean a spreadsheet received from someone else and spot what is wrong
Duplicates, mixed formats, wrong totals: a reliable file before you use it, with the formulas that prove it.
Comfortable 25 min
The tools in this recipe
- Gemini dans SheetsPlugin
Native AI in Google Sheets: formulas, cleanup, explanation
Paid · from 12 €Data with the vendorSecurity: nothing to flag
See the card → - Copilot dans ExcelPlugin
Same role in Excel (optional)
Paid · from 15.6 €Data with the vendorSecurity: nothing to flag
See the card → - Formula BotApp
Generate a formula from a sentence, without an office subscription (optional)
FreemiumData with the vendorSecurity: one caveat, see the card
See the card →
Step by step
- 1
Duplicate the sheet
Always work on a copy. The first sheet stays the source as received; you will come back to it to check.
- 2
Ask for a diagnosis, not a fix
Starting prompt: “Describe the problems in this table without changing anything”. You get the list: dates stored as text, trailing spaces, probable duplicates, amounts with and without VAT mixed.
- 3
Fix with formulas
For each problem, ask for the formula (TRIM, VALUE, UNIQUE, XLOOKUP…) and apply it in a new column. An overwritten value can no longer be checked; a formula can.
- 4
Check the totals
Ask for three cross-checks: total before/after cleanup, row count, sum per category. An unexplained gap is an unsolved problem.
- 5
Document
Add a “Cleanup” sheet listing the corrections. Whoever picks up the file in six months will thank you, and it may be you.
Real example
- Situation
- 1,340-row export from an invoicing tool, sent by a client for analysis: columns Date, Client, Amount, Status.
- What we asked / set
- Analyse columns A to D of this sheet. List every data quality problem you find (format, duplicate, outlier, inconsistency), with the number of rows affected and one example. Do not change any cell. Then, for each problem, propose a formula to put in a new column to fix or flag it.
- What we got
- 7 problems found including 212 dates stored as text, 18 duplicate invoice numbers, 3 negative amounts without a “credit note” status. Totals checked: €0.00 gap after fixes. Time: 25 minutes.
Check by hand before using it
- ✓The source total and the cleaned file total match, or the gap is explained line by line.
- ✓Every fix is a formula or an added column, never an overwritten value.
- ✓The row count changed only by the removed duplicates, and you listed them.
Your data: precautions
- !A spreadsheet with client names and amounts is personal and commercial data: use the company Workspace or M365 account, not a personal one.
- !Gemini and Copilot read the whole workbook, hidden sheets included: remove what does not belong there first.
- !Never let the AI “remove duplicates” itself: it picks which row to keep in your place.
Share this verdict
One link, the same shortlist, the same reasons.
Each recipe was actually done. The tools cited are scored and rechecked every week; no placement is sold.