Reads every tab
Multi-tab Sheets and Excel workbooks are read as related tables, not one blob. Each tab keeps its own columns and types.
Connect your data
Point tableArth.ai at your data. Ask in plain English.
Connect Google Sheets, Excel, and your databases — then ask questions the way you'd ask an analyst. Your analysis runs on live, synced data, not a one-time upload, and a single question can reach across every source you've connected.
Q3 Revenue Workbook
Ask
Sources
Sheets
PostgreSQL
You
Combine the sales sheet with our orders DB — revenue by region this quarter?
APAC leads at $412K, up 31% QoQ,
followed by EMEA at $286K and
NA at $255K. Figures blend the Sheets
pipeline with booked orders from Postgres.
Revenue by region
Q3 · USD
APACEMEANA
LATAMMEAF
Data sources
Everything plugs in.
Spreadsheets and databases, connected live or uploaded when you need a one-off. Pick a source, and tableArth.ai reads its structure so you can start asking in seconds.
Google Sheets
Live connect
Microsoft Excel
Live connect
MySQL
Database
PostgreSQL
Database
MongoDB
Database
Apache Druid
Database
CSV & Excel upload
Upload
More connectors
Coming soon
Live, not a snapshot
Connected data beats a one-time upload.
Uploading a file gives you an answer about the data as it was the moment you exported it. Connecting the source gives you an answer about the data as it is right now — every time you ask.
| Capability | One-time file upload | Connected in tableArth.ai |
|---|---|---|
| Data freshness | Frozen at export time | Live — reflects the source |
| Keeping it current | Re-upload every change | Auto-syncs, no re-uploading |
| Multiple tabs / tables | Flatten into one sheet | Understood & joinable |
| Join across sources | Not possible | Ask across all of them |
| Large datasets | Upload timeouts | Reliable, streamed loads |
| Private databases | Export required | Query in place, in your env |
Workbook
One place. Every source. Always in sync.
A Workbook holds all the sources behind an analysis — Sheets, Excel files, and databases — connected together. It syncs with each source automatically, so your analysis stays current without a single re-upload. Ask a question, and tableArth.ai reaches across the whole Workbook to answer it.
- Multiple sources — Sheets, Excel, MySQL, MongoDB, and more, side by side
- Automatic sync — the Workbook tracks each source as it changes
- Unified answers — one question, pulled across every connected source
Sales pipelineGoogle Sheets
OrdersMySQL
EventsMongoDB
Workbook
Synced
Sales pipeline ✓ live
Orders ✓ live
Events ✓ live
Multiple sheets & tables
Your data doesn't have to live in one flat sheet.
tableArth.ai understands workbooks with many tabs and databases with many tables. Ask questions across them and join related data — the same way you would across database tables — with no manual VLOOKUPs, no copy-paste, no combining first.
Joins related data
Ask a question that spans tabs or tables and tableArth.ai works out how they relate, joining on shared keys automatically.
Answers in context
Get a single answer and the right chart, drawn from whichever tabs and tables the question actually needed.
Talk to your database
Ask your private databases, in plain English.
Query external databases such as PostgreSQL, MySQL, MongoDB, and Druid running inside your own private environment — simply by asking. No exports, no copies leaving your network. The question is natural language; the answer is grounded in a real query run against your data.
- Runs where your data lives — nothing has to move
- SQL and NoSQL — relational tables or MongoDB collections
- Four privacy modes control exactly what a model can see
PostgreSQL · orders
AskQuery
You
Which customers churned last month but had > $10k lifetime value?
18 customers churned in June with lifetime
value above $10k — together $41.2k
of monthly recurring revenue. Top three: Northwind, Contoso, Globex.
SELECT c.name, c.ltv FROM customers c
JOIN churn e ON e.customer_id = c.id
WHERE e.month = '2026-06' AND c.ltv > 10000;
JOIN churn e ON e.customer_id = c.id
WHERE e.month = '2026-06' AND c.ltv > 10000;
How it works
Connect. Sync. Ask.
Three steps from a source to an answer — no warehouse, no data prep, no SQL.
Step 01 — Connect
Pick a source
Authorize a Google Sheet, connect an Excel file, or point tableArth.ai at a database. Upload a CSV if you'd rather. The engine reads the structure automatically.
Sheets · Excel · Databases
Step 02 — Sync
Build a Workbook
Add one source or several to a Workbook. It keeps every source in sync as the underlying data changes, so you never re-upload.
Auto-sync, multi-source
Step 03 — Ask
Ask in plain English
Type a question. tableArth.ai figures out which sources and tables it needs, joins them, runs the query, and answers with the right chart — with suggested and clarifying questions along the way.
Answers + charts
Guided, not guesswork
It suggests questions — and asks when you're vague.
Smart suggestions
tableArth.ai suggests relevant questions for your data so you always have a strong starting point — no blank box, no guessing what's answerable.
Revenue by region
Top accounts this quarter
Month-over-month growth
Churn by plan
Clarifying questions
When a request is ambiguous, tableArth.ai asks a quick clarifying question instead of guessing — so you get to the right answer faster and with more confidence.
You: best customers?
tableArth.ai: By revenue, retention, or lifetime value?
tableArth.ai: By revenue, retention, or lifetime value?
Also from tableArth.ai
Building software? Embed the same engine.
The engine that answers your questions also drops into your own product. Give your customers plain-English analytics on their tables with a two-line widget, a REST API, or a Chrome extension — the same natural-language answers, charts, and privacy modes.
FAQ
Connecting your data.
What data sources can I connect?
Google Sheets, Microsoft Excel files, and databases including MySQL, PostgreSQL, MongoDB, and Druid. You can also upload CSV and Excel files directly. More database connectors are being added.
Is my data live, or a one-time upload?
Connected sources stay live. A Workbook automatically syncs with the source, so as your underlying data changes your analysis stays up to date without any re-uploading. You can still upload a standalone CSV or Excel file when you only need a one-off look.
Can I ask questions across multiple sheets or tables?
Yes. tableArth.ai understands files with multiple tables or tabs across Google Sheets, Excel, and databases. You can ask questions across sheets and join related data the same way you would across database tables — your data no longer needs to be combined into one flat sheet first.
Can it answer one question across several sources at once?
Yes. With a multi-source Workbook, you ask a question in natural language and tableArth.ai pulls data across all your connected sources to return a single, unified answer. See how Workbook works.
Do I have to move my database?
No. You can query external databases such as PostgreSQL, MySQL, MongoDB, and Druid running inside your own private environment, simply by asking. Your data stays where it lives. Read more on the talk-to-your-database and security pages.
What about large files?
Large uploads are handled reliably — the timeout issues that used to affect bigger datasets are fixed, so the upload process is smoother for large files.
Get started
Connect a source. Ask your first question.
Start with one sheet or one database. Connect it, ask in plain English, and see an answer and a chart in seconds.