Your question gets read before anything gets built.
You write a question in your own words. Before a line of code exists, the pipeline reads what kind of question it is, what field it comes from, and what shape of data it needs — and that reading decides which specialist builds your answer. Here are three real ones:
Why the answer holds up: behind the answer →
Change one word, get a different expert.
Your question carries several signals and each is read on its own. One of them is the field you work in — and you never pick it from a menu, because your own words already say it. Here is the same question three times, changing only the middle:
The statistics underneath don’t change. The expertise in front of them does — and all you did was describe your own business. If the question isn’t phrased for any one field, that’s a real answer too: you get the generalist, not a guess. The whole story →
One question in. A checked analysis out.
In between, the line does something a chat window can’t: it splits. Every card of your report gets its own specialist working at the same time — and nothing reaches you until the whole thing has survived the check.
Delivered — the report, the method, and the code that produced it.
SIMPLIFIED FROM 22 REAL STAGES · 4 INDEPENDENT CHECKS · 2 REPAIR LOOPS
A BUILD THAT CANNOT BE MADE CORRECT IS NEVER DELIVERED — AND NEVER BILLED
The shape is the same at any size — a Snapshot takes a narrower path, a bigger report simply fans wider. You never manage any of it: you asked a question and picked how deep to go. The whole story →
It's a link. And it's yours.
Calculated, not hallucinated — the numbers were computed before a word was written.
- ✓Interactive report — explore the charts and diagnostics, not screenshots.
- ✓The method, stated — what was tested, why that test, whether it held.
- ✓PDF & one-click citation — APA, MLA, Chicago, BibTeX.
- ✓The R source — reproducible by anyone, including you.
Every answer puts another landmark on the map.
An analysis doesn’t just answer your question — it finds ideas in your data: that tenure predicts churn, that margin breaks past a discount band, that one cohort behaves unlike the rest. Each becomes a point on a map of your business. The more you ask, the more of the landscape is charted — and the bigger the questions you can ask next.
This is why the questions get better over time. A brand-new tool can only answer from the data in front of it. A charted business can be asked things that cross several analyses at once — and every answer comes back citing the piece of work that proves it.
And your agents can read the same map. Point whichever AI you use at your library and it navigates by these landmarks — answering from your own verified analyses instead of guessing about your industry. The knowledge layer →
Read the code that talks to your data.
The MCP server, the tool contracts and the transport options are public under an MIT licence — so you can see exactly what connects to your assistant before you connect it, and run it yourself if you’d rather.
The statistical analyst in your AI chat — bring data and a question, own a citable, re-runnable analysis. Works in Claude, Cursor, and any MCP client.