Agents & browsers

🔮 He construido una predicción de clic en tiempo real sobre el DOM usando JEV que parece una bola de cristal. Funciona con jev-latest para predecir el siguiente elemento clicable y la intención del usuario en 345 ms por consulta, resaltando los candidatos en pantalla. Es extremadamente barato de usar y ayuda a anticipar la intención del usuario con un 83% de acierto en las pruebas. Usos que se me

One of the craziest use cases I’ve found for Jev: verifiers. I am so excited about this that I at least wanted to share the high-level idea. I used Jev to build a custom verifier for the /goal feature in my agent harness. It checks whether the goal is actually complete after every turn, making continuous verification cheap enough to scale. This means I can run more of these verifiers (previously h

Seeing how many people are using Jev to control browsers I wanted to try too. Wrote the wrapper for 'dev-browser' and called it 'jev-browser'. And then tried to put it to a test: "Find the best pricing model for WP Multitool for someone who runs 3 sites, spends 3h/yr on each, and has $50/hr rate and will run them for 2 years." I saw that it did the right steps until the last one. Was adding the Lite version to the cart. That's how I discovered that while my Pricing page LOOKS good it's structurally awful and definitely nor readable for BOTS or SCREEN READERS. Learned something = PR

judge jev is the law. score two browser agents w/ different models on task completion, using jev to judge which was more efficient at the job. scored on correctness, time, actions, and cost. https://t.co/8M7JBou6O1

Built something really cool with Jev for my Agentic Inbox setup on Cloudflare. @sunilpai @thomasgauvin this was fun to put together. https://t.co/oXoVcD566W

Implemented this exact thing today in the @knocklabs agent harness using Jev based on the common types of requests we see from live traces.

I built a Chrome extension for agentic browsing using Jev by @typesafeai, https://t.co/Xa9toMieqT including AI Gateway by @vercel. Now agents can browse, click, and interact with websites directly in your browser. Cost effective and fassst. Decision-making by Jev. https://t.co/bIqkUbCkvc

Vibe coded a parallel search using jev for agents, planning to hook up a local LLM to this to get human output. Discovers new pages and adds them to a BFS queue, jev consumes pages in parallel, reranks and adds to the queue. https://t.co/EkpZhuYmRB