What it does
It judges the task description, not the work itself, and sends that text to TypeSafe. Flags to clarify a request or seek confirmation are advice, not enforced safeguards.
Agent tooling
jev-router
A Claude Code hook uses Jev to choose a model for each subagent task, with stricter checks before choosing a cheaper one.
Bookmark: jev-router
Keep this in your collection.
Leave a noteWhat would you try with this?
: jev-router
Only you can see your notes.
Screenshot unavailable. Open the experiment ↗
How you can use it
Ask your developer to borrow its rule for choosing a cheaper AI. Require stronger evidence before moving a job to the cheaper option. Try this on clearly described jobs and check the choices yourself. A short or vague request can hide hard work, so do not assume that fewer words mean an easier job.