# Jev as a Model?

**URL:** <https://community.pickaxe.co/t/jev-as-a-model/8865>\
**Category:** General\
**Created:** [September 25, 2026, 2:48am UTC](https://community.pickaxe.co/t/jev-as-a-model/8865 "2026-09-25T02:48:06Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![motheraigaia](https://yyz2.discourse-cdn.com/flex004/user_avatar/community.pickaxe.co/motheraigaia/32/4246_2.png) [@motheraigaia](https://community.pickaxe.co/u/motheraigaia)\
**Post date:** [September 25, 2026, 2:48am UTC](https://community.pickaxe.co/t/jev-as-a-model/8865/1 "2026-09-25T02:48:06Z")

</div>

Do you guys have any plans on integrating Jev as a model that we can build with? Might open up some interesting products if we can use it. Thoughts?

---

<div class="post-metadata">

**Author:** ![kenlyle](https://avatars.discourse-cdn.com/v4/letter/k/ac8455/32.png) [@kenlyle](https://community.pickaxe.co/u/kenlyle)\
**Post date:** [September 25, 2026, 3:01pm UTC](https://community.pickaxe.co/t/jev-as-a-model/8865/2 "2026-09-25T15:01:51Z")

</div>

AbsoFnlutely should happen - it seems complicated. I see it as an extension to, maybe a post-process for Wingman: “Wingman, review the transcripts for this Agent, and create and insert Jev checks that should be called before calling a full LLM”. Ironically, it may require an LLM call to determine which of the Jev checks might be sufficient at each step. Still, I think that something like DeepSeek Flash 4.1 could do this cheaply and quickly, and the net would be improvements in speed, reproducibility (yes/no), and cost ESPECIALLY if you are using higher cost (Anthropic) models as your main model. Challenge to the team, starting with @nathaniel