Browser Use + Jev
Demo di ricerca voli di Gregor Zunic con spazio di azione dinamico DOM.
A FIELD GUIDE TO JEV / VOL. 01
Il meglio di Jev: progetti reali, guide pratiche e idee da tutto il web.
Demo di ricerca voli di Gregor Zunic con spazio di azione dinamico DOM.
01 / A small decision engine. A whole new way to build.
94 risorse / La raccolta
Reimposta filtriAI-assisted summaries and translations. Check original sources for context and performance claims.
Demo che mostra Jev che seleziona i modelli AI più adatti per compiti di generazione video e immagini su Higgsfield.
Classificatore che valuta in tempo reale la difficoltà delle istruzioni, permettendo un modo rapido per migliorare l'interazione con l'utente.
SuperX integrato con Jev consente una valutazione rapida dei post, analizzando 61 domande per post in meno di un secondo con alta accuratezza nella previsione del potenziale virale.
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.