Built a search engine for our network this weekend with Jev.

@utpalnadiger Utpal Nadiger · Sep 21, 2026 · case #805285 · listed via Jev Hub

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

Built a network search engine where Jev evaluates LinkedIn profiles in parallel against a plain-English goal like finding an intro to Sam Altman.

The original post

Built a search engine for our network this weekend with Jev. "Find" evaluates linkedin profiles in parallel against a plain English goal. In this case it was “Who can intro me to Sam Altman” The linkedin account here was just mine, but eventually will be team + captable +

Engagement when collected

Likes3

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