Context and definitions
What you tell it, what it learns, and what a number means. Everything else reads this first.
Most of what makes an answer right isn't in the data. It's that net revenue means after refunds, that Tom does the reconciliation, that March was strange because of the warehouse move. Overscore keeps those as facts, each with a source, a date and a level of trust: heard, or confirmed by a named person.
Where facts come from
- The interview. A short conversation when you start, and any time after. One question at a time; it never asks what it already knows.
- Your corrections. Every "no, it means this" is kept.
- Cards you approve. Things it heard from email, notes or agents, confirmed by you.
- What it notices. A number that moved, a definition used two ways, a fact going stale.
What a definition is
Not just a name and a query. A definition has parts: what it means in the owner's words, where it lives, how it adds up, which date decides the month, the always-on filter (test orders out), what it's safe to split by, an example, and an owner, a version, who confirmed it and when.
Two ways of calculating the same thing are two named definitions. The name settles the argument, not the SQL. A change is a new version; every answer and dashboard stamps the version it used, so "the June deck used the old definition" is a fact you can say.
It gets better as you go
Every question, correction, card and dashboard adds to this. The system you have after six months knows things the one you started with didn't, and every agent you connect reads the same memory.