Commerce overview
Revenue$267.6KSeptember 2026 · Sample
Understand the revenue mix across markets.
Explore dashboard
AI native · The product
AI native analytics.
AI native analytics.
Built around your data.
Connect the sources your business runs on. Ask in plain English, investigate the answer, and build useful dashboards. Extend selected workbooks to Claude, ChatGPT, and other compatible tools through the MCP preview.
AI native analytics · Dashboard libraryOne connection.
One connection.
Twelve ways to see more.
Start with a business question.
Open a dashboard. See the value in your data.
Illustrative dashboards using fictional September 2026 data. Available analyses depend on the fields in your source.
Order fulfillment
Orders dispatched21.1KSeptember 2026 · Sample
Put fulfillment workload and timeliness in context.
Explore dashboardSubscription sales
Subscription revenue$194KSeptember 2026 · Sample
Focus subscription reviews on the plans that matter.
Explore dashboardPayment activity
Processed value$448.4KSeptember 2026 · Sample
Understand payment activity before reviewing costs.
Explore dashboardInventory flow
Units moved51.8KSeptember 2026 · Sample
Review the product categories driving warehouse work.
Explore dashboardSupport demand
Tickets created14KSeptember 2026 · Sample
Plan support capacity around actual workload.
Explore dashboardProduct engagement
Product events4.4MSeptember 2026 · Sample
Explore the behaviors behind product engagement.
Explore dashboardAPI traffic
API requests7.3MSeptember 2026 · Sample
Direct reliability reviews toward heavily used endpoints.
Explore dashboardSupplier orders
Purchase value$265.7KSeptember 2026 · Sample
Understand purchasing concentration.
Explore dashboardBooking performance
Booking value$241.3KSeptember 2026 · Sample
Review your booking mix before adjusting channel plans.
Explore dashboardFeature adoption
Feature sessions301.5KSeptember 2026 · Sample
Identify workflows to investigate for product improvements.
Explore dashboardTransaction workload
Transactions201.2KSeptember 2026 · Sample
Understand operational throughput and activity peaks.
Explore dashboardEvery preview opens a full dashboardTake the question into your AI tools
Capability 01
Connect your data. Give AI the context.
Connect spreadsheets, databases, cloud billing, advertising, and Tally. Database queries run on demand; other sources use refreshed or imported snapshots. Keep that source context together in a workbook.
- Google Sheets, Excel, MySQL, PostgreSQL, MongoDB, Druid — plus CSV upload.
- Build analysis around related tables, sheets, and imported collections.
- Review the detected source structure and add the context your questions need.
Google Sheets
Microsoft Excel
SQL databases
MongoDB
Capability 02
Natural-language queries.
Ask in plain English. tableArth.ai writes the query, runs it against your data, and returns the answer. SQL for relational databases, the right query for a document store — no SQL, no schema knowledge, no training data required.
- Schema-aware — understands your columns, types, joins, and filters.
- Multi-step questions, drill-downs, and follow-ups in the same context.
- Answers are grounded in a real query, so they're verifiable — not guessed.
tableArth.ai · Customer orders
AskDashboard
You
Which regions grew fastest YoY?
tA
APAC leads growth at
+48%, driven by new enterprise accounts in
Singapore and Tokyo. EMEA
follows at +22%, NA at +14%, LATAM at +9%.
Region · YoY growth%
APACEMEANALATAM
MEAFCISOC
Capabilities 03 & 04
Across every sheet, table, and source.
Multi-sheet & table joins
tableArth.ai understands files with multiple tabs and databases with multiple tables. Ask a question that spans them and it joins related data automatically — the way you would across database tables, with no VLOOKUP and no flattening into one sheet first.
Workbook & multi-source answers
A workbook keeps selected sources and table relationships in one place. Ask questions across compatible query paths, and check each source’s refresh state before combining results.
Capability 05
The right visual, picked automatically.
Eight chart types, one engine. tableArth.ai chooses the right one based on the question and the shape of the answer — no chart config from you.
Bar
Compare categories
Line
Trends over time
Area
Cumulative growth
Pie / Donut
Visualize proportions
Scatter
Reveal correlations
Stacked bar
Multi-dimension breakdown
Funnel
Process drop-off
Table
Detail & raw data
Capability 06
Guided to the right answer — not left guessing.
Smart suggestions
tableArth.ai suggests relevant questions for your data, so users never face a blank box and always have a strong place to start exploring.
Top 10 by revenue
Churn risk this quarter
YoY growth by region
Outlier customers
Last 7 days summary
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?
Capabilities 07 & 08
Live-streamed answers. Dashboards on day one. Self-correcting queries.
Streaming answers & auto dashboards
Answers can stream as analysis completes. Response time depends on the source, query, model, and deployment. Use the resulting charts and dashboards to inspect trends, then validate the numbers against your business definitions.
Active users
1,284
+18%
Customers
42
+6 this week
Questions / 30d
9,402
↑ 22%
Query retry intelligence
A generated query self-corrects up to three times before an error ever reaches the user — column name fixes, type coercions, join repair, and dialect adjustment.
attempt 1 · column "rev" not found
attempt 2 · rewrite → SELECT revenue
attempt 3 · ✓ executed in 240ms
FAQ
How the product works.
What can I connect to tableArth.ai?
Connect Google Sheets, Excel and CSV files, nine database engines, cloud billing exports, supported ad reports, and Tally imports. Setup and availability vary by connector. Databases support on-demand queries; snapshot sources require refresh or a new import.
Can it work across multiple sheets, tables, and sources?
Yes. tableArth.ai understands files with multiple tabs and databases with multiple tables, joins related data automatically, and with a multi-source Workbook answers one question across every connected source at once.
Does it write and run the query automatically?
Yes. The engine writes the query from your plain-English question — SQL for relational databases, the right query for a document store like MongoDB — runs it, and returns the answer with a chart. No SQL knowledge is required.
What chart types does it support?
tableArth.ai auto-selects the right visual across bar, line, area, pie/donut, scatter, stacked bar, funnel, and plain table. You don't configure chart types — the engine picks the one that fits the question.
How does it handle ambiguous questions?
It suggests relevant questions for your data so you always have a starting point, and asks a clarifying question when a request is ambiguous — so you get to the right answer faster and with more confidence.
What happens if a generated query is wrong?
The engine has retry intelligence — it detects a failed or invalid query and self-corrects, retrying up to three times before falling back gracefully, so a single bad query doesn't surface an error.
Get started
Connect your data. 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.
AI native by design · MCP previewYour data.
Your data.
Your AI workspace.
Keep the conversation where you work. MCP brings authorized tableArth workbooks into compatible clients such as Claude, ChatGPT, and Cursor.
From Tally and spreadsheets to databases, cloud bills, and ad reports: connect the source once, then explore its workbook context through the tools you choose.
Ask your dataExplore dashboardsCreate new views
Explore MCP access Staged preview. Availability depends on your client, deployment, and plan. Creating or updating dashboards requires write permission.
One workbook. More ways to work.MCP
Your connected dataOne authorized workbook
Imagine asking in ClaudeExample
“Explore my workbook, explain what changed, and help me build a dashboard for the next review.”
Workbook context → governed analysis → a dashboard you can return to.