The author processed 6,214 DMs with three agents: OpenAI Dots read the inbox, Jev decided what was worth an answer, and Opus 5.5 wrote replies. Jev filtered out 2,907 bots, 1,388 scams, and 1,316 spam messages before Opus saw a single one.
which of my 6,214 DMs are real money? i gave the question to three agents last night and went to sleep. OpenAI Dots read the X inbox, Jev decided what was worth an answer, Opus 5.5 wrote the replies Jev threw out 2,907 bots, 1,388 scams and 1,316 spam before Opus saw a single
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.
