Skip to contentSkip to main content
Get Useful Answers from AI — a free microcourse with a reusable templateStart learning
TechlyUp
Core AI skills

Using AI with Excel and Google Sheets: formulas, cleaning, and analysis

By TechlyUpUpdated 3 min readSpreadsheet users

Quick answer

AI is most useful in spreadsheets for writing and explaining formulas, suggesting cleaning steps, and drafting a first read of the data. Describe your columns and the exact result you want, test every formula on a few rows you can check by hand, and never trust an AI-stated total without recomputing it in the sheet.

Getting formulas that work

Describe the sheet layout: column letters, header names, example values, and the output you want. Mention whether you use Excel or Google Sheets because function names and behaviour differ.

Google Sheets. Column A: order date (dd/mm/yyyy). Column B: region. Column C: amount in INR.
Write a formula for F2 that totals column C for region in E2, only for orders in September 2026. Explain each part of the formula.

Cleaning messy data

Ask for a step-by-step cleaning plan rather than a single mega-formula: trim spaces, standardise date formats, split combined fields, flag duplicates. Apply steps on a copy of the sheet.

Drafting analysis

Paste a small, non-sensitive sample or summary table and ask for observations and questions to investigate. Treat the output as hypotheses to check with pivot tables or charts, not conclusions.

Checks that catch spreadsheet errors

Spreadsheet mistakes are silent. Build these habits.

  1. Test each formula on three rows you compute by hand.
  2. Compare totals from the formula with a pivot table.
  3. Check edge cases: blanks, text in number columns, dates at month boundaries.
  4. Keep an untouched copy of raw data.

Common spreadsheet-with-AI mistakes

Spreadsheet errors are costly precisely because they're quiet.

  1. Copying a formula into the whole column without testing it on a few rows first.
  2. Mixing up Excel and Google Sheets functions or regional separators.
  3. Letting AI state totals in text instead of calculating them in the sheet.
  4. Cleaning data in the original file with no untouched copy to fall back on.

Worked example: cleaning a messy export

An operations analyst receives a vendor export with inconsistent dates, extra spaces, and a combined “City - State” column. They describe the columns to the AI and ask for a step-by-step cleaning plan with formulas for each step, applied on a copy.

After applying the steps, they compare row counts with the original, check that dates at month boundaries converted correctly, and build a pivot table to confirm totals match the vendor's summary. The cleaning plan is saved as a checklist for next month's export, turning a one-off fix into a repeatable process.

Try it yourself

Take a sheet you use often and ask AI to explain your most complex formula line by line. Then ask for a simpler alternative and test both on the same rows.

Frequently asked questions

Can AI read my whole spreadsheet?

Some tools can connect to files; others need pasted data. Only share data your policy allows, and prefer samples or summaries.

Why does an AI formula give an error?

Common causes are wrong column references, regional separators (comma vs semicolon), or functions that differ between Excel and Sheets.

Is AI good at spreadsheet maths?

Don't rely on it for calculations stated in text. Let the spreadsheet calculate, and use AI to help write the formulas.

Want a suggested next step for your situation?

Share a few details and someone from TechlyUp will get back to you. No automated sequences.

Sources and further reading

Examples are authored practice material, not measured learner outcomes. Tool behavior can change. Found an error? Contact TechlyUp with the page URL and correction.

Continue learning