For analysts
Answers you can turn into work products.
You already have the data and the questions. BumbleB Crunch does the investigation with you, shows how each figure was counted, and turns what you find into a story, a dashboard or a sheet your stakeholders can use.
Live — “Revenue's flat quarter over quarter. Overall, what changed underneath — the number of orders or their size — and in which region is the order size moving?”
From a question to something you can hand over
Investigate in a conversation
Ask in plain words over any dataset you pick. Each answer says how your question was read and how it counted — the window, the unit, the denominator — so you can check it before it ships.
Share this as a story, dashboard or sheet
Under an answer with a chart, Share this as turns it into a story, a dashboard, or the data as a sheet. Pin more charts to a dashboard from any conversation.
A sheet with a co-pilot
Ask the co-pilot to group, split, sort or filter, add a column from your words, save a view as a table, or explain the sheet.
Start from + New
A new sheet, doc or dashboard. Add tables and tiles from your data, paste rows, or copy in another sheet’s table.
The tools you’d expect
SQL console
Draft and run SQL over your datasets, and see each result as a table or a chart.
Data home and lineage
Datasets, sheets, docs, dashboards and saved queries in one place, with how each dataset was built.
Postgres and Iceberg, in place
Link tables from your Postgres database or Iceberg REST catalog and read them where they are, nothing copied first.
Data on your computer
With Acorn for VS Code, ask about the Postgres, MongoDB and files on your own machine — read-only, every query logged.
Or in a desktop app
BumbleB Crunch Desktop reads the same local sources, outside the editor.
Questions to start with
Ask in your own words. Every answer comes with how BumbleB Crunch™ read the question and how it counted.
“The quarter looks flat. Split it by region and product and tell me what moved.”
“Which customers churned after their second support ticket?”
“What share of customers bought again within 60 days, by first product?”
“Open the orders behind this chart as a sheet and group them by month.”
Watch it work
Investigations on any dataset
A flat quarter split open, and insider buying that clusters.
The flat quarter, split
“Revenue's flat quarter over quarter. Overall, what changed underneath — the number of orders or their size — and in which region is the order size moving?”
An orders table, no tracking involved: orders rose from 8,000 to 8,800 while the average order shrank — and it's all the West, down $40 an order while every other region rose.
When insiders buy together
“Counting open-market purchases from January through May 2026 by directors and officers: which five company-months had the most different insiders buying — and for those companies, how many bought, in how many months, on how many days?”
Real SEC Form 4 filings — 108,302 filings, three tables joined. The Plan agent splits it into four asks; the Analyst runs them: Taiwan Semiconductor leads with 28 insiders buying in both April and May, then F&M Bank, Everforth and Vital Farms. Speeded up — the full run took about 14 minutes.
Which plan
The tools analysts lean on — your own data lake, the lineage explorer and the rich data tools — are on the Team plans.
Compare plans →Bring your next question
Sign up free, pick a dataset, and turn the answer into something to share.
Sign up free