I tried making a new tool with JEV AI!
Built a virtual human tool with Jev that answers where to click in Adobe Premiere Pro and highlights the spot step by step via text or voice questions.
The original post, translated
I tried making a new tool with JEV AI! "Where should I press on this tool?" In times like that, if you ask the virtual human beside the screen, they will teach you step by step while lighting up the place to press. This time, I prototyped it with Adobe Premiere Pro. ■ What it can do ・You can ask questions by text or voice
Show the original post in its source language ▾
JEV AIで新しいツールを作ってみました！ 「このツール、どこを押せばいいの？」 そんなとき、画面の横にいるバーチャルヒューマンに聞くと、 押す場所を光らせながら一歩ずつ教えてくれます。 今回は Adobe Premiere Pro で試作しました。 ■ できること ・テキストでも音声でも質問できる
The post above is a machine translation from ja; the untranslated text is in the fold-out.
Engagement when collected
Numbers are a snapshot taken from X when the case was added to the library (schema v1, collected 2026-09-19); they will not match today.
Where this case fits
Filed under general Jev builds. In the pattern Jev is built for, the model answers a bounded question per step — and ordinary code acts on the answer, because the answer is already a value rather than a paragraph. Browse the full case library for the work it sits next to.
Keep browsing: all 1173 Jev cases · more from @debichanchan · builders · what Jev is
Last updated: 2026-09-22 · sources & corrections · every card links to its author's original post