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

Intent detection with decision models

Picking the user's intent from a fixed set so a bot, workflow or UI can respond appropriately.

97 public projects · page 4 of 4

  • Patterns

    TypeSafe docs page on decision patterns: speculative fan-out, confidence-gated routing, composite scoring and intent routing.

    Articleproduction
  • Jev Classifier

    Web tool that analyses Telegram channel JSON exports locally for intent, quality, sentiment and speaker tone with Jev.

    Articleprototype
  • Is Jev as Accurate as Frontier Models at Classification?

    OpenRouter benchmark of Jev 1.13 vs Claude Opus 5 on Banking77: 81.0% vs 84.4% accuracy at a fraction of the latency and cost.

    Articleresearch
  • We Tested Jev on 791 Labeled Decisions Against Four LLMs

    Independent benchmark of Jev versus four LLMs on Banking77 routing and prompt injection, plus a gated cascade.

    Articlediscussion
  • Jev in production at treg

    Post reporting the treg team runs Jev in production for traffic classification, onboarding and reranked search.

    Discussionproduction
  • First Jev use case in a Mac app

    X post about a shipped Mac app that routes setup and troubleshooting questions to Jev when no local language model is loaded.

    Discussiondiscussion
  • Tabletop MMORPG action mapper

    Post evaluating Jev for mapping free-text player intent into typed server actions in a tabletop MMORPG.

    Discussiondiscussion