Using Jev to call OpenCode2 API's fs.read/fs.find from Todoist information to generate candidates and determine the most suitable working directory, with high accuracy.
OpenCode2 + Jev + Todoist を使った Todoist 駆動開発、Todoist の情報から OpenCode2 API の https://fs.read/fs.find を叩いて候補作って、どのディレクトリで作業するのが一番適切かを判断させるのに Jev を利用。めっちゃ精度いい
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.
