CommunityJev Media & Talks
Jev AI explained, with an ad-tagging demo
Automate with Marc on using Jev to sort, tag, or score fixed answers, including a demo that tagged competitor ads.
- Format
- Video
- Published by
- Community
- Author
- Automate with Marc
- Last verified
- Sep 2026
Works forJev for Classification
Used inJev for Sales & Marketing
Highlights
- Treats Jev as a decision model that cannot write a sentence: data in, a question with fixed answers, a sort, tag, or score out.
- The description says one demo tagged more than 700 competitor ads in about 40 seconds for 9 cents.
- Names sorting leads, support tickets, and ad copy as the jobs he would use it for.
Watch out
The 700-ad timing and 9-cent cost are the creator's description. The video also points at OpenRouter and Claude Code for the surrounding build.
Questions about this entry
Short answers drawn from the linked project or page.
It is the creator's own description. The captured source is the title plus YouTube's footer, with no transcript, request log, or accuracy check behind the figures. What they imply is throughput and price, not whether the tags were right.
Unknown from the capture. Nothing fetched reports a hit rate, gold labels, or a sample of the tags it produced. Tagging competitor ads against a fixed option list is a reasonable fit for the model, but the demo as described never checks its own output.
Only the sort. The framing is that Jev cannot write a sentence — data in, a question with fixed answers, a sort, tag, or score out. Producing the actual copy still needs a generative model, which the build reaches through OpenRouter and Claude Code.
A walkthrough. The entry names sorting leads, support tickets, and ad copy as the target jobs and points at the surrounding tooling, but the capture has no code listing or transcript, so there is nothing here to reconstruct a pipeline from.
Automate with Marc published it, pointing at OpenRouter and Claude Code for the surrounding build while Jev handles the decision.
Sorting leads, support tickets, and ad copy, according to the entry's recording of the description.
More than 700 competitor ads tagged in about 40 seconds for 9 cents. The entry records those as the creator's own description, with no accuracy check behind them.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
YouTube: Marc tags more than 700 competitor ads with Jev in about 40 seconds for 9 cents.
More Jev resources like this
Automate with Marc tests Laya, the open decision model people shorthand as Jev for free, on 100 sales leads beside Claude Code.
Jev Media & TalksVideo#community#video#open-models
Community
Neural Breakdown with AVB livestreams against the TypeSafe Jev API, walking parallel constrained decoding and System One call shapes in code.
Jev Media & TalksVideo#community#video#tutorial
Community
Patrick Desjardins wires Jev into Cursor for deterministic decisions from the public docs, with blog posts on hundreds of text rules under two seconds.
Jev Media & TalksVideo#community#video#tutorial
Community
Aditya Arya signs into early access and tours the UI, tying Jev to RLCD training and 70–500 ms structured decisions instead of chat.
Jev Media & TalksVideo#community#video#tutorial
Community
Codevolution's walkthrough of state, questions, and answers, then a customer-message demo in the TypeSafe playground and the TypeScript SDK.
Jev Media & TalksVideo#community#video#tutorial
Community
WitWireAI recreates a spreadsheet that asks Jev to score customer messages by meaning, and labels the clip as a demo rather than a benchmark.
Jev Media & TalksVideo#community#video#classification
Community
From the Jev community
Posts from builders shipping with Jev right now.