Revenue workspace
Revenue$318.1KSeptember 2026 · Sample
Understand the revenue mix across markets.
Explore dashboard
AI native · Workbook
One workbook.
One workbook.
Your AI native data workspace.
Keep sources, business context, questions, and dashboards together. Analyze live database queries or imported snapshots, then use the same authorized workbook context in the MCP preview.
Growth Workbook
Ask
3 sources
Marketing sheet
MySQL · signups
MongoDB · events
You
Which campaigns drove the most activated signups last month?
Spring Launch led with 1,240 activated
signups, ahead of Referral (910) and
Webinar (640). Spend came from the sheet,
signups from MySQL, activation events from MongoDB.
Activated signups by campaign
Last 30d
LaunchRefWebSEOAds
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.
Fulfillment workspace
Orders dispatched25.2KSeptember 2026 · Sample
Put fulfillment workload and timeliness in context.
Explore dashboardSubscription workspace
Subscription revenue$232.5KSeptember 2026 · Sample
Focus subscription reviews on the plans that matter.
Explore dashboardPayments workspace
Processed value$542.8KSeptember 2026 · Sample
Understand payment activity before reviewing costs.
Explore dashboardInventory workspace
Units moved62.4KSeptember 2026 · Sample
Review the product categories driving warehouse work.
Explore dashboardCustomer support workspace
Tickets created16.4KSeptember 2026 · Sample
Plan support capacity around actual workload.
Explore dashboardProduct analytics workspace
Product events5.2MSeptember 2026 · Sample
Explore the behaviors behind product engagement.
Explore dashboardEngineering workspace
API requests8.6MSeptember 2026 · Sample
Direct reliability reviews toward heavily used endpoints.
Explore dashboardProcurement workspace
Purchase value$316.4KSeptember 2026 · Sample
Understand purchasing concentration.
Explore dashboardBookings workspace
Booking value$290.3KSeptember 2026 · Sample
Review your booking mix before adjusting channel plans.
Explore dashboardAdoption workspace
Feature sessions355.2KSeptember 2026 · Sample
Identify workflows to investigate for product improvements.
Explore dashboardOperations workspace
Transactions239.5KSeptember 2026 · Sample
Understand operational throughput and activity peaks.
Explore dashboardEvery preview opens a full dashboardTake the question into your AI tools
Cloud cost intelligence
See the signal.
See the signal.
Know what to ask next.
A spike. A missing owner. A growing workload.
Explore the dashboards that turn cloud bills
into better questions and clearer next steps.
tableArth / cloud intelligence
Interactive example
aws
01 – 30 Sep 2026
AWS Billing / Spend & anomalies
Know where every dollar goes.
Month-to-date spend
$64,800
11.1% above baseline
Budget remaining
$5,200
of $70,000 monthly budget
Highest-spend day
$4,320
22 September
Daily spend. One spike stands out.
USD · September 2026
Daily spend
Illustrative baseline
What’s driving the bill?
Share of monthly cost
$64.8k
Total spend
EC2
50%
RDS
24%
S3
15%
Other
11%
Spend signal
A $4,320 day deserves a second look.
Daily spend is 150% above the $1,728 reference. Start with the services behind the increase.
tableArth / cloud intelligence
Interactive example
AZ
01 – 30 Sep 2026
Azure Billing / Allocation & accountability
Give every cost an owner.
Monthly billed cost
$48,200
Across 4 allocation groups
Allocated spend
$41,452
86% assigned to an owner
Ownership gap
$6,748
14% of total monthly spend
Your cloud bill, by team.
Illustrative allocation using owner tags
Core platform
$18,316
38% of spend
Data & AI
$13,014
27% of spend
Customer apps
$10,122
21% of spend
Unallocated
$6,748
14% of spend
Area represents each team’s share of total billed cost.
Ownership coverage
Billed cost with an owner assigned
86%
Spend with an owner
$6,748 still needs an owner
Allocation signal
Find the owner of $6,748.
Review unallocated costs before the next budget conversation. Start with missing or inconsistent owner tags.
tableArth / cloud intelligence
Interactive example
GC
01 – 30 Sep 2026
Google Cloud Billing / Services & project hotspots
Make your next investigation count.
Monthly usage cost
$36,900
Services & project costs
Largest service
$14,760
BigQuery · 40% of the bill
Top project
$14,760
analytics-prod
Start with the biggest cost driver.
Usage cost by service · USD
September spend
Illustrative baseline
Where is the spend landing?
Usage cost by project
analytics-prod
$14,760
customer-app
$9,963
data-platform
$7,380
Other projects
$4,797
Cost driver signal
BigQuery accounts for 40% of the bill.
Compare BigQuery costs by SKU and project, then review the workloads driving the largest charges.
AWS dashboard, 1 of 3.
The idea
A Workbook is your analysis, with its data attached.
Instead of exporting data into a file that goes stale the moment you save it, a Workbook connects to the real sources and keeps them together. Three things make it work.
Multiple sources, one place
Add Google Sheets, Excel files, and databases like MySQL and MongoDB to the same Workbook — no warehouse, no ETL, no flattening everything into one sheet first.
Source-aware refresh
Databases query the source on demand. Sheets, cloud billing, and advertising use refreshed snapshots. Uploaded files and Tally imports stay at their imported state until updated.
One question, one answer
Ask in plain English and tableArth.ai works out which sources the question needs, joins them, and returns a single unified answer — with the right chart.
Google Sheets
Excel
MySQL
MongoDB
19 supported sources
Connected context
Your sources. A clearer picture.
Keep connected sources and imported snapshots together. Databases query on demand; Sheets, cloud billing, and advertising refresh as snapshots. Check each source’s refresh status before asking your next question.
- Direct database queries — analyze the connected source on demand
- Refreshable snapshots — bring updated source data into your analysis
- Reusable context — keep your questions and dashboards with their sources
Marketing spendGoogle Sheets · snapshot
SignupsMySQL · live
Activation eventsMongoDB · live
Growth Workbook
Connected
Marketing spend ✓ snapshot
Signups ✓ live
Activation events ✓ live
Before & after
From stitched-together exports to one connected answer.
Export, stitch, repeat
- Step 1Export each source to a file
- Step 2Flatten tabs, align columns by hand
- Step 3VLOOKUP the sources together
- Step 4Build the chart — from stale data
- Next weekDo it all again from scratch
VS
Connect once, ask again
- OnceConnect the sources
- 0sAsk a question in plain English
- +4sAnswer + chart across all sources
- AnytimeRefresh your source, ask again
- AlwaysKeep your analysis together
How to build one
Add sources. Review the data. Ask.
Step 01
Add your sources
Connect a Google Sheet, an Excel file, or a database — or several at once. tableArth.ai reads each source's structure automatically.
Sheets · Excel · Databases
Step 02
Review your source status
Refresh supported snapshots, query connected databases, or update imported files before analyzing changes.
Source-aware refresh
Step 03
Ask across everything
Pose one question and get a unified answer, with suggested and clarifying questions to guide you.
Unified answer
FAQ
Workbooks, answered.
What is a Workbook?
A Workbook keeps related sources, questions, charts, and dashboards together. Source type determines whether analysis uses live queries or an imported snapshot. Configure relationships where supported and review the source status before analyzing updates.
Which data sources can a Workbook hold?
Google Sheets, Excel, CSV, PostgreSQL, MySQL, MongoDB, SQL Server, Oracle, Snowflake, ClickHouse, Apache Druid, Supabase, AWS, Azure, Google Cloud billing, Google Ads, Facebook Ads, and Tally. A private connector reaches approved sources inside your network. See the full list on the data sources page.
Does a Workbook stay in sync automatically?
Databases query the source on demand. Sheets, cloud billing, and advertising use refreshed snapshots. Uploaded files and Tally imports stay at their imported state until updated.
Can I ask one question across all the sources in a Workbook?
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. More on the multi-source analytics guide.
Do I need to combine my data into one sheet first?
No. tableArth.ai understands files with multiple tables or tabs and databases with multiple tables, and joins related data when a question needs it. Your data no longer needs to be flattened into a single sheet.
EXPORT
&
IMPORT
Keep the work. Move the workbook.
Export a complete package or a smaller definition-only version. Review its contents before importing into a new workbook.
What travels
Table definitions, relationships, dashboard layouts and filters, saved workbook settings, assigned skill definitions, and optional stored snapshots and original uploads.
What you reconnect
Passwords, OAuth permissions, sharing recipients, and chat history are excluded. Live database definitions need a matching authorized destination connection. Imported schedules begin in manual mode.
Full packages carry their bundled data. Definition-only and live database imports require compatible destination definitions. Imports create a new workbook; they do not overwrite an existing one.
Get started
Build a Workbook. Ask across all of it.
Connect your first sources and ask a question that spans them — one answer, all in context.
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.