What it is
Notra is a generative engine optimization (GEO) platform that runs buyer questions across AI engines, tracks mentions, citations, and competitors, and turns content gaps into drafts.
How it uses Jev
The README does not describe how Jev is used; only the summary states that `NOTRA_JEV_CLASSIFIERS` routes brand-visibility classifiers off an LLM and onto Jev `Boolean` decisions at a 0.5 threshold, targeting 300 ms p50.
Primitives:choice
Technique worth stealing
Route brand-visibility classification from an LLM to a fast typed classifier behind a flag.
Try it
Bun monorepo: `bun install`, configure `.env`, then `bun run dev --filter=dashboard`.
Evidence
Each line is one question put to Jev about the README. ≥ 0.60 reads as yes, ≤ 0.40 as no; in between Jev is not making a call.
- Jev-centricno0.09
- Shows a System One patternunclear0.55
- Handles uncertaintyyes0.65
- Measuredunclear0.46
- Runnableunclear0.53
- Worth recommendingno0.22
- Model replicano0.11
- Problem scopescore on a 0–2 scale1.10
- About Jevyes0.77
Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 20 Sept 2026.