Use after any web or API search, before opening results or spending another round. Jev picks which results to read, whether the evidence is enough, and which query to run next from ones you wrote.
Use when driving a desktop GUI through a computer-use driver — windows, menus, native apps, OS dialogs. You build a table of safe actions; Jev picks the next one in about 0.4 seconds.
Use when Jev is not working yet, a Jev tool reports no_key or auth_failed, or the person asks to connect or fix Jev. Gets their TypeSafe or OpenRouter key into the secret store, unseen by you.
Use when driving a web page in a browser — clicking, typing, navigating, logged-in or JS-rendered pages. Jev picks each step from the elements observed, under a host allowlist and a step budget.
Use when a task is already judged hard — pick which paid frontier seat takes it, then keep Jev watching the delegated run so it interrupts you only when the run needs a decision.
Use to pick the cheapest good-enough model or effort for a turn or a delegated task (lanes small to escalate), to decide continue/retry/verify/escalate/complete after each cycle, or to tune routing.
Use when unsure which of many installed skills applies to a request, if any, or when asked to make skill loading cheaper or more accurate. Jev ranks the whole catalog and may say no skill is needed.
Use when researching social posts, creators, reactions, or trends. Jev ranks discovery cards and decides when opened, source-linked evidence is enough for a bounded report.