Demo data. These numbers are illustrative, so you can see how the Research Center works. Real findings appear once enough members have opted in. How this works
Research Center · Findings
What the engine has surfaced.
Here is what a published finding will look like. Each card below is drawn from seeded demo data, not real practitioners, so you can see how a finding is presented before real ones exist. We list the data window, the sample size, and the model that produced it. If the slice was smaller than ten members, you won't see it — not because it isn't interesting, but because we promised.
Pulling the latest findings…
How a finding gets here
- Members opt in to the research pool. Default is off.
- An extract job builds a de-identified, bucketed warehouse from operational data.
- A small set of well-defined models runs against the warehouse.
- Each model emits draft findings; an admin reviews them before they appear here.
- Anything below the k=10 threshold is silently refused at every layer.
The full contract lives at /research/methodology.