CommunityJev Media & Talks
Laya scored against 100 sales leads
Automate with Marc tests Laya, the open decision model people shorthand as Jev for free, on 100 sales leads beside Claude Code.
- Format
- Video
- Published by
- Community
- Author
- Automate with Marc
- Last verified
- Oct 2026
Used inJev for Sales & Marketing
Highlights
- The description says he ran Laya on 100 sales leads.
- He identifies Laya as the open-source decision model from Convai Innovations.
- The clip is about the local stand-in, not a call to the hosted Jev API.
Watch out
Laya is not TypeSafe's model. The description does not publish the per-lead scores.
Questions about this entry
Short answers drawn from the linked project or page.
A different one. The caveats say plainly that Laya is not TypeSafe's model, and the highlights attribute it to Convai Innovations. The description notes only that people shorthand it as Jev for free, which is a community nickname, not an equivalence.
No. The caveats state the description does not publish them, and the captured source page holds only the video title and YouTube boilerplate, so there is no table to audit the ranking against.
Unpublished. Nothing in the entry copy names a labelled set of good and bad leads or explains how lead quality was judged, so a 100-lead run demonstrates motion on sales data, not accuracy.
No. The highlights say the clip is about the local stand-in rather than a call to the hosted Jev API. Putting Laya next to a coding agent in the same demo is not a controlled comparison of accuracy, latency or cost.
Automate with Marc published it, testing Laya, the open decision model, on 100 sales leads.
Convai Innovations. The entry notes that people shorthand Laya as Jev for free, which is a community nickname and not an equivalence.
A local model. The entry says the clip is about the local stand-in rather than a call to the hosted Jev API, and that Laya is not TypeSafe's model.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
YouTube: Automate with Marc runs local Laya, not hosted Jev, on 100 sales leads.
LinkedIn: What multimodal decision models actually change, and what they do not.
LinkedInJevDirectory.org
Hacker News: Decision Index 0.2.1 scores open reproductions of Jev on a frozen suite.
jackbravo4 pointsDecision Index 0.2.1 – 70 open reproductions of TypeSafe Jev's Decision ModelRead the thread on Hacker NewsHacker News: Pointer to a DiffusionGemma plus vLLM tutorial for a Jev-shaped classifier.
1 pointHow to build a Jev-style classifier with DiffusionGemma and vLLMRead the thread on Hacker NewsMore Jev resources like this
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
Yash Thakker's intro to System One, plus 50 open-source demos that compare Jev with a regular LLM, linked from the description.
Jev Media & TalksVideo#community#video#use-cases
Community
Under the Hood AI compares TypeSafe's closed decision model with Laya, the open model Convai released that can run on a laptop.
Jev Media & TalksVideo#community#video#open-models
Community
Automate with Marc on using Jev to sort, tag, or score fixed answers, including a demo that tagged competitor ads.
Jev Media & TalksVideo#community#video#tutorial
Community
TJ Robertson on the jobs that fit a classifier with a confidence score, and the speed and cost he trades against a frontier chat model.
Jev Media & TalksVideo#community#video#routing
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.