Benchmarks
The same question means different things to a billing analyst and a data engineer. FactRule understands what you are working on — not just the words you typed. Below is what that is worth, measured the hard way: weights frozen, then evaluated once on questions and entities the system had never seen. We publish the losses alongside the wins, because a benchmark you can only quote selectively is marketing, not measurement.
1,112 questions in a wording register the system was never tuned on, over a real 39,830-document data estate. Recall@10 — how often the right memory is in the top ten.
Both systems saw identical questions, an identical corpus and an identical context budget. On the development set the gap holds across two independently-written question wordings at p < 10⁻⁷, paired per question — it is not a lucky phrasing.
96 questions about entities no tuning run ever touched — the long tail every real schema has. This is where retrieval products actually differ.
Plain similarity finds 2% of the right memories; FactRule finds a quarter. Not because it embeds better — because it understands your estate and what you are working on, not just the words in the question.
24 executable questions where a bare table name exists in two schemas and only the analyst's stated context says which — the ambiguity every warehouse has. Answers graded by running the SQL and comparing result signatures. No judgement calls.
Exact McNemar p = 0.031, and the discordant count is 0/6: plain search never wins a question FactRule loses. It even picks the empty table when the user's context calls for it — the case every popularity heuristic gets wrong.
An evaluator will find these in their first hour, so here they are first.
Our numbers were measured on our estate. Yours has its own homonyms, its own empty decoy tables, its own tribal knowledge. The collector runs inside your network — Windows or Linux — builds a portable memory from your schema, code and documents, and tells you the cost before spending a call: on our estate it projected 119 model calls and the build made exactly 119. Nothing leaves your network until you decide it should.
sign up → download the collector from your account → preflight → estimate → build — no admin rights, nothing leaves your network
Method: DEV/TEST split by entity hash · paraphrase control (worse of two wordings reported) · frozen weights before holdout · answers graded by result-signature equality on a live read-only database · retrieval harness fully deterministic.