Browser Use + Jev
Gregor Zunic이 공개한 항공편 검색 데모입니다. 화면의 DOM에 맞춰 가능한 동작을 구성합니다.
A FIELD GUIDE TO JEV / VOL. 01
인터넷 곳곳의 Jev 프로젝트, 실용적인 가이드와 놀라운 아이디어를 한곳에서.
Gregor Zunic이 공개한 항공편 검색 데모입니다. 화면의 DOM에 맞춰 가능한 동작을 구성합니다.
01 / 실제 제작자의 실험에서 시작하세요.
94 개 자료 / 자료 보관함
필터 초기화요약·번역에 AI를 활용합니다. 원문과 성능 주장은 출처에서 확인하세요.
영상·이미지 생성 요청에 맞는 AI 모델을 Jev가 고르는 Higgsfield의 공개 데모입니다.
입력 중인 프롬프트의 난이도를 평가하고, 간단한 요청에는 빠른 모드를 제안하는 데모입니다.
Jev와 통합된 SuperX는 빠른 포스트 점수 매기기를 가능하게 하며, 61개의 질문을 1초 미만으로 분석하고 높은 바이럴 가능성 예측 정확도를 제공합니다.
Screen a folder of CVs with the TypeSafe Jev decision model: typed judgments, an editable policy, free re-scoring.
A GitHub Action using Jev for automated PR triage and classification.
A .NET 10 and React 19 application for fast, structured AI-powered ticket triage using TypeSafe Jev.
A project classifying 1,018 AI research papers using Jev, achieving low cost and fast processing for organizing academic work.
A setup where Jev selects between different AI models for specific tasks, streamlining model usage in a single terminal.
GitHub Action for issue triage that abstains: label, spam, needs-info and duplicate in one call, each applied only above a threshold you set, and nothing at all below it.
Short practical intro with a Python ticket-triage example.
Jev classifies 500 emails quickly and inexpensively, demonstrating its efficiency in processing tasks.
SQL with natural-language predicates, powered by TypeSafe's Jev. Filter, rank, classify and score rows by meaning — batched, cached and cost-guarded.
A 26-sheet construction plan set was classified in 2.9 seconds using Jev with an LLM pipeline, costing $0.0052 and matching GPT-4.1 and GPT-6 Astra performance.
A real-time computer assistant using Jev and local Whisper to process voice input, classify actions, and interact with the screen through a Swift app for accessibility.
Not every coding task needs your best model. Experimental Jev-powered model routing for Claude Code — V3 prototype runs today, V4 routes at the task boundary.
A Jev-powered system that analyzes PDFs page by page to determine which require OCR processing.
A system tested on 1,500 emails for classification effectiveness. Demonstrates potential for automated email management.
GitHub project for content moderation with category-specific probability thresholds. Enables automated content filtering.
Diffusion-style pixel art out of a classifier: 256 parallel per-pixel Jev questions plus refinement passes.
Async LangGraph workflow that gets a typed Jev Choice (invoice or general) and routes each inbound email to the matching handler.
Three composable judgment pipelines on TypeSafe's Jev: support-ticket triage, observability alert triage, and a deploy-risk gate.
An image classifier using OCR and Jev processes 900 images in 40 seconds.
A GitHub project routing tasks by selecting model tier, tools, skill, and effort.
Calibration and confidence-based routing measured on Banking77: 80.2% accuracy at $0.103 per 500 decisions.