Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

Notra

GEO analytics platform tracking brand visibility in AI answers; a feature flag moves its visibility classifiers onto Jev booleans.

Projectproduction
View on GitHub ↗Live demo ↗

Overview

Notra is a production GEO (generative engine optimisation) platform that asks ChatGPT, Claude, Gemini and Perplexity the questions buyers ask, then measures whether a brand is mentioned or recommended, who appears instead, and which content gaps to fill. It offers mention rates, share of voice, competitor tracking, draft generation, AI-traffic attribution through an SDK, agent-readiness audits, a REST API and an MCP server.

Per the list summaries, a NOTRA_JEV_CLASSIFIERS feature flag routes its brand-visibility classifiers off an LLM and onto Jev boolean decisions at a 0.5 threshold, targeting 300 ms p50. The fetched README excerpt does not describe this integration, so the exact questions are inferred. It is for marketing teams measuring presence in AI-generated answers.

What the decision model decides

TypeQuestionAnswers
Yes / noDoes this AI answer mention or recommend the brand?(inferred)true · false

How it works

  1. Run buyer prompts across AI engines and store the answers.
  2. With the flag on, ask Jev boolean questions about each answer.
  3. Treat probability >= 0.5 as true.
  4. Aggregate into visibility and share-of-voice metrics.

Strengths

  • Replaces slower LLM classifiers with fast boolean decisions (target 300 ms p50 per list summary).
  • Feature flag allows gradual rollout.

Caveats

  • Jev integration details come only from list summaries.
  • A fixed 0.5 threshold may not suit every classifier.

At a glance

Type
Project
Status
production
Language
TypeScript
Runtime
Bun, web app, REST API, MCP server
Has code
yes

Use cases and integrations

How curated lists describe it

  • Marketing analytics: production GEO platform whose `NOTRA_JEV_CLASSIFIERS` flag routes brand-visibility classifiers off an LLM and onto Jev `Boolean` decisions at a 0.5 threshold, targeting 300 ms p50.

    yibie/awesome-jev

  • Marketing analytics platform whose feature flag routes brand-visibility classifiers off an LLM and onto Jev boolean decisions.

    hellogumbo/awesome-jev

Frequently asked questions

Where does Jev fit in Notra?

Per the list summary, behind a feature flag that moves brand-visibility classifiers from an LLM to Jev boolean decisions.

What threshold is used?

The list summary says 0.5.

What is GEO?

Measuring and improving how a brand appears in answers from AI engines.

Related projects

  • jev-seo★ 610

    Live SEO audit from one homepage URL: crawl, 52 rules, Core Web Vitals and Jev page judgments, reported as PDF, XLSX and Markdown.

    PluginbetaPython
  • jev-seo

    Site audit for SEO and AI-search visibility: a deterministic crawl, narrow Jev Choice, Score and Noul questions, and a live dashboard.

    AppbetaTypeScript
  • jevseo

    Scores a page for SEO, answer engines and generative engines, using code for measurable checks and Jev rubric scores for judgment.

    DemoprototypeTypeScript
  • BTK audit studies

    Boring Tools Kit's technical SEO audit cost study, where Jev ranks striking-distance fixes and content gaps by calibrated probability.

    Article
  • jev-classifies-bots

    Event-stream layer labelling signups, logins and checkouts as human, AI agent, crawler or bot, with a bad-intent probability.

    AppprototypeJavaScript
  • Postmark

    Web demo that reads a draft social post and returns Jev's tone choice, a 0-3 virality score and a cringe probability in one call.

    AppprototypeTypeScript