Classification & Routing

Daily pipeline that reads Spain's official gazette with Jev, scoring relevance, tagging categories and picking a summary paragraph.

Next.js and Python demo where one Jev call per email returns spam probability, category and urgency on Enron-Spam.

E-commerce support sandbox where Jev classifies intent, emotion and escalation and blocks risky agent replies before sending.

Three Spanish-language demos where Jev decides and Claude reasons: Jira triage, code pre-flight and a PR review router.

Customer-service chatbot that asks every level of a routing tree in one Jev call and hands off on human requests or low confidence.

Browser playground: configure a pool of OpenRouter models, let Jev pick one for a task, then judge whether its pick was right.

CLI ticket system where one Jev call answers category, priority, escalation and refund questions and Python routes the ticket.

Incident-scoping tool that starts from one malicious process and asks Jev which linked telemetry belongs to the same incident.

Minimal demo that uses Jev to set a support ticket's priority and routing.

Minimal demo that matches a user goal to the best MCP server or capability in a catalogue using Jev, in two stages for large catalogues.

Small Next.js mood tracker where Jev classifies a daily check-in into one of five moods and a 1-5 energy score.

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.

Small web demo that makes clinic triage decisions with Jev, falling back to heuristics when no key is set.

Small demo that routes a task to a research, code, browser, support or writer agent with Jev and shows a visual swarm map.

Bulgarian blog categoriser comparing Jev and local Laya on 50 posts, with a small local LLM naming new topics.

Experiment that makes 16x16 pixel art by asking Jev 256 parallel per-pixel color Choice questions, plus refinement passes.

Portuguese-language Go proof of concept that tests whether Jev's confidence is calibrated enough to auto-route support tickets.

Public demo repository for Jev shared on X; the README gives no further detail.

Desktop dictation and meeting-notes app with optional Jev fast judgments for citation checks, history search and live meeting cues.

Jev-style skill router for OmO: frozen Qwen2.5-0.5B plus a small head scores the skill catalog and trims the system prompt to top-K.

Research router where a Qwen3-1.7B belief model scores intent candidates and a small policy decides to commit, retrieve more or hand off.

Library, CLI and app that classify PDFs, DOCX and PPTX with Jev and split document packets at predicted boundaries.

Claude Code plugin that routes each prompt, step and subagent to the cheapest capable Claude model with effort caps and a live band.

grep by meaning: pipe text in, ask a yes/no question in plain English, and Jev returns matching lines, even behind tail -f.

OpenAI/Anthropic-compatible Go gateway where Jev or Laya rates topic, complexity, risk and privacy to pick the cheapest adequate LLM.

Benchmark asking Jev and a local LLM whether each collusion.wiki page was agent-written; neither beats the majority baseline.

Fifteen runnable Node recipes using Jev via OpenRouter for triage, dedupe, PII scanning, reranking and a browser agent.

Marketing and voice-agent platform with an experimental TypeSafe module that picks specialisation labels for agent roles.

Go event bus whose optional routing layer asks Jev a Choice to pick an event projection only for ambiguous cache misses.

Hosted checker where Jev reads a software idea and says whether plain code, Jev or a reasoning LLM fits it best.