The developer uses Jev to score what types of fixes speech-to-text dictation needs, then passes the result to a small LLM to fix punctuation or rewrite errors, aiming for cheaper and more accurate dictation.
To improve Suzu dictation, and make it cheaper and more accurate, I used Jev to score what kind of fixes the Speech To Text dictation needs, then pass it to a cheap LLM (Haiku 5.5) to fix the punctuation mistakes or the "I want something red, oh no actually blue => I need
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.
