How to ask questions about a spreadsheet in plain language
Once your data is a table, questions become answers: numbers, small tables, charts. How to phrase them and what to expect back.
Behind each answer is a query on your table, run by an analytical engine. You can copy it into the Data tab or into an automation.
Name the table or let it guess
“In expenses, …” when you have several tables. With one obvious candidate the assistant picks it.
Ask for a shape
“How much” gives a number; “which” or “list” gives a table; “chart” or “plot” gives a chart. Add a period: “in August”, “this quarter”.
Ask your spreadsheet a question - expenses-2026.csv
Here's my bank export
Imported 312 rows into the table
expenses— 4 columns, dates from January to August.How much did I spend on restaurants in August?
€412.30 across 17 visits. The top three:
Restaurants, August 2026
merchant visits total Trattoria Nonna 5 €148.00 Bao House 4 €96.50 Café Lumen 3 €61.20 14 more rows
Refine
Follow-ups keep context: “only restaurants”, “per month instead”, “top ten”. Ask to see the query if you want to reuse it.
A chart from a sentence Chart my spending per merchant this quarter, top five
Top five merchants, July to September.
Spend per merchant, Q3 2026
- Rewe
- €612
- Deutsche Bahn
- €388
- Amazon
- €297
- Trattoria Nonna
- €214
- Spotify
- €36
Questions
What if the answer looks wrong?
Ask to see the query. Most surprises are a column meaning something else than assumed; tell the assistant and it remembers for the table.
Can it join two tables?
Yes — “match expenses to the merchants table by name” works when both are in the same project.
Related
Features
Spreadsheets you can question
Drop a CSV or JSON into the chat and it becomes a queryable table. Ask in plain language; get a number, a table or a chart.
Features
Reports the AI writes, your browser runs
Describe a recurring report or check. The AI writes a small program that runs on your data inside your browser — nothing leaves it.