JevMade hello@JevMade.com
← Back to agent workflows videos

JevMade field notes / Video guide

I tested the new JEV Model... and it's insane

Albert Olgaard tests categorical choices, binary criteria, and rating scales in the TypeSafe console. He then combines Jev with Claude for task-complexity routing and a small guardrail demonstration that checks drafted replies for internal prompt disclosure.

Original by Albert OlgaardAgent workflowsBeginner8 min 21 sec Published Source reviewed

Before you press play

What you’ll find in the video

  1. The console supports supplied categories, yes-or-no criteria, and ordered rating scales over explicit state.
  2. The routing example scores incoming task complexity before choosing a smaller or larger generative model.
  3. The guardrail example evaluates a draft against a disclosure rule; passing these few examples does not establish protection from prompt leaks.
Worth knowing

Auto-generated English captions reviewed with Gemini. The speed, low cost, and guardrail decisions shown are subjective ad-hoc UI tests, not formal safety evaluations or controlled latency benchmarks.

I tested the new JEV Model... and it's insane