You ask something about your data in plain English. What comes back is a piece of work you own — a report with its method stated, its assumptions tested and its code attached, plus the module that made it, yours to run again. This is the shape of what happens in between.
Both give you the same kind of report. The difference is whether your question has been asked before.
You describe a question nobody has answered yet. We work out the method, write the code, verify it, and hand back an analysis you own.
High-quality analyses for the questions people run most — modelled on what the pipeline builds, verified the same way.
The same question can get three sizes of answer — the quick pass, the memo, or the commissioned study. You pick the depth; the pipeline staffs the job.
What the data says, checked — the look-over you'd ask for before a meeting.
~2 minutes Brief The analyst's memoThe computed answer on a single page — chart, numbers, method. The memo that settles the argument.
~7 minutes Deck The data-science team's studyModels, diagnostics, the write-up — a durable, multi-card analysis you can re-run whenever.
30–45 minutes Compare Side by sideWhat each one includes, compared.
An analysis is not a one-off answer. It is something you keep, re-run and change.
Describe what you want to know. We work out the method, write the code and check the result.
RunSame analysis, new file, same method — which is what makes two results comparable.
ModifyIterate without starting over, and keep the lineage of what changed.
Delivered work doesn't scatter into downloads. Every report you've run becomes searchable in plain English — find last quarter's churn number without remembering which report it was in. And you can ask questions across all of it: the answer comes back synthesized from your own delivered analyses, with citations back to each report it drew from.
Every analysis goes through the same sequence, whether it takes two minutes or forty.
The full feature map — every capability, one page deep from here.
Every claim above is something you can check rather than take on faith.
We don't have a language model read your spreadsheet and describe what it seems to say. The numbers in your report come from statistical code that ran on your data — they exist before a word of insight is written — and the code ships with the report so anyone can check it. The writing is generated; the arithmetic is not.
Tell us what went wrong, in your own words. We capture the page you're on automatically, so no need to describe where you are.