The author argues that browser use and Jev still feel like toys in real GUI automation scenarios, citing their team's 2024 open-source Midscene project that started with a DOM-based approach.
browser use + Jev 在我看来也就是个玩具，大部分人无脑吹 Jev 用来做 GUI automation 的都是没有真正用它在真实场景下跑过多少 GUI automation 任务的。 24 年 gpt 4o 刚出来没多久我们就开源了 https://github.com/web-infra-dev/midscene… ，早期的版本就是基于 dom
LLM holds memory/context, uses agent-desktop to take snapshots and sends them to Jev, which selects the right element to act on for faster Computer Use, with Cursor enabled and headless support.
Riley Brown shares that TypeSafe AI's Jev classified 500 emails in seconds for just 3.5 cents, highlighting its fast and low-cost email classification.
A comprehensive explainer video introducing Jev, an AI that doesn't write text but determines which department to route inquiries to and how urgent they are.
