LIVE
OpenAI Raises $11 Billion at $1.25 Trillion Valuation08/11/26 · OpenAI|Anthropic IPO valuation expectations drop to as low as $1.1 trillion06/11/26 · Anthropic|Mark Cuban Accuses Facebook of Knowingly Profiting From Deepfake Scam Ads06/11/26 · Meta|OpenAI Unveils GPT‑6 Cyber, a Model Built for Vulnerability Research05/11/26 · OpenAI|OpenAI's AI Pipeline Uncovers Nearly 1,000 Linux Kernel Flaws04/11/26 · OpenAI|Hidden AI-related debt at US tech giants jumps 90% to $3.2 trillion03/11/26|China Introduces Its First Export Controls on Frontier AI02/11/26|Claude Code's 'Don't Ask Again' option linked to password leaks in 1,122 public GitHub files07/11/26 · Anthropic|Microsoft Research disbands its AI Frontiers group as John Langford departs07/11/26 · Microsoft|Essay argues AI is already sharply speeding up AI research itself06/11/26|University libraries overwhelmed by AI scraping bots06/11/26|ToyBlocks: A Controlled Environment for Robot Learning and Evaluation06/11/26 · Allen Institute for AI|OpenAI Raises $11 Billion at $1.25 Trillion Valuation08/11/26 · OpenAI|Anthropic IPO valuation expectations drop to as low as $1.1 trillion06/11/26 · Anthropic|Mark Cuban Accuses Facebook of Knowingly Profiting From Deepfake Scam Ads06/11/26 · Meta|OpenAI Unveils GPT‑6 Cyber, a Model Built for Vulnerability Research05/11/26 · OpenAI|OpenAI's AI Pipeline Uncovers Nearly 1,000 Linux Kernel Flaws04/11/26 · OpenAI|Hidden AI-related debt at US tech giants jumps 90% to $3.2 trillion03/11/26|China Introduces Its First Export Controls on Frontier AI02/11/26|Claude Code's 'Don't Ask Again' option linked to password leaks in 1,122 public GitHub files07/11/26 · Anthropic|Microsoft Research disbands its AI Frontiers group as John Langford departs07/11/26 · Microsoft|Essay argues AI is already sharply speeding up AI research itself06/11/26|University libraries overwhelmed by AI scraping bots06/11/26|ToyBlocks: A Controlled Environment for Robot Learning and Evaluation06/11/26 · Allen Institute for AI|
Practical recipe · Data & spreadsheets

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

Step by step

  1. 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. 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. 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. 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. 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.

All recipes →