Analyze a CSV file with AI — ask questions in plain English
Updated 2026-08-27
An AI data analyst is most useful when it runs on your real data. This guide shows how to connect a CSV file so you can ask questions in plain English and get charts, dashboards and reports back — without writing SQL by hand.
The setup takes a few minutes: connect your file or sheet, let the analyst read the schema, and ask your first question. Your data are encrypted, and the analysis runs on your own AI provider key.
- 1
Get your file ready
No connection string is needed — you upload the .csv file directly. Make sure the first row contains column headers.
- 2
Understand the read-only model
The file is read for analysis only; nothing is written back. Your uploaded data is encrypted at rest and isn't used to train our models.
- 3
Create your account and add your AI key
Sign up, then add your own AI provider key (bring-your-own-key). If you don't have one yet, a free key takes about a minute to create — your key is encrypted and used only for your requests.
- 4
Upload your file
Add a data source, choose file upload, and select your CSV. Column types are inferred automatically; you can correct them and describe columns in plain English.
- 5
Let the AI read and annotate your schema
The analyst treats the file as a table and infers each column's type. Describe any ambiguous columns once so future questions map cleanly.
- 6
Ask your first question in plain English
Ask something like "Total and average of the amount column by category". On a question the analyst judges complex — a join, a query spanning two sources, several steps — it shows a readable plan and waits for you to approve it before running anything; on one it judges simple it runs first and shows you afterwards. Either way you get the same two controls on every answer: Show SQL gives you the exact query that produced the number, and Show table gives you the rows it returned with their count. That is how you check a figure instead of trusting it. Refine by chatting, then pin it to a dashboard or save it as a report.
What this adds to an uploaded file — and what it does not
An uploaded file is a snapshot: we store the copy you send and analyse that, so when the underlying data changes you upload it again. What it adds over pasting the same file into a general-purpose chatbot is that on complex questions it shows a readable plan before running anything, on every answer the exact SQL and the rows it returned are one click away, and it saves what your fields mean against that source — so the next question already knows them instead of guessing. If you want answers that refresh without re-uploading, connect a Google Sheet or a database instead; the Google Sheets connection works on the Free plan.
CSV file: things to know
- A clean header row and consistent types give the best results; avoid blank header cells.
- File upload is a Pro feature; on Free, a Google Sheet is the quickest way to try file-style data.
Example questions to ask your CSV file data
- Total and average of the amount column by category
- Top 10 rows by value
- Count of records per month from the date column
Keeping it safe
- Your uploaded data is read for analysis only and never written back.
- On our side every query is checked before it runs and refused if it contains a write statement — DROP, DELETE, UPDATE, INSERT and fourteen others, eighteen keywords in all. It is a keyword guard, not a full SQL parser, so it can only refuse what it can spell. What actually keeps your file unchanged is that we analyse a stored copy of it; the guard is the second line, not the first.
- Connection details and your AI key are encrypted at rest.
- We train no model on your data — we do not have one; the analysis runs on your own provider key, so the terms that decide what happens to what you send are your provider's, not ours. An uploaded file is stored in your own account so the analyst can query it, and the rows an answer returns stay there until you delete them.
Frequently asked questions
Up to 10 MB per file. Over that the upload is refused with an error — it is not silently truncated. For bigger data, a database or warehouse connection is a better fit.
Yes — cross-source questions can join an uploaded CSV with your database or a Google Sheet.
Related
Get your end-to-end AI business intelligence now.
Ask in plain English, pin the answer to a dashboard, export it as CSV, Excel, PDF or PowerPoint — on the free tier that whole loop runs on one database source plus Google Sheets, and the field definitions you save carry into every later session, including after a schema refresh. One exception you should hear from us rather than discover: on a Google Sheet, re-running the tab picker — even only to add a tab — clears the definitions saved for that source and reads its schema fresh. Connecting a database is the technical part: a read-only user and network access, once. If your numbers live in a spreadsheet, none of that applies: put the file in a Google Sheet and it connects on the free tier, with no read-only user and no open port. Uploading a CSV or Excel file directly is a Pro feature, and every new account gets 14 days of Pro with no card. The one thing no plan waives is your own AI provider key, and a Google Gemini key is free to create.
Every new account starts on a 14-day Pro trial with no card. After it lapses, the free tier stays free.