Building harnesses is also changing thanks to Jev (

@MAXIMISEART Maksymilian · Sep 18, 2026 · case #474953 · listed via Jev Hub

Still from the clip posted with this case; watch it in the original post on X.

Used Jev for harness routing and automode tool-risk classification, work that previously required classic LLM calls.

The original post

Building harnesses is also changing thanks to Jev ( @typesafeai ) @sydneyrunkle nicely describes in her article how the routing model is changing, as well as automode (classification of how risky it is to use a tool). The things she mentions used to have to be done by the classic

Engagement when collected

Likes2

Bookmarks0

Reposts0

Replies0

Quotes0

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 classification & data extraction. 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. Other posts in the same family are on the classification & data extraction page.

🗂️ Classification & data extraction