Jev CEO Diogo Almeida argues that although writing software is faster, the software itself still leaves routine work to humans. For true automation, systems must perform tasks correctly, not just be trained to give preferred answers.
Jev CEO, Diogo Almeida, on why training models to give preferred answers may be the wrong target for automating work: “We’ve made it faster to write software, but the software itself still leaves routine work to humans.” “For automation, the system has to do the task correctly,
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.
