Building a Harness with Jev

Learn all about Jev, a new System One model from TypeSafe AI, and how you can use it in your agent harness. Jev is up to 200x faster and 400x cheaper than LLMs on classification style tasks, which makes it great for applications like model routing and "jev as a judge" online evals.

Chapters:
0:00 Building a harness with a new model called Jev
0:12 The agent loop everyone already knows
1:02 Why tool calling and structured outputs exist
1:38 What Jev actually is
1:45 Jev as a System 1 model
2:46 Where the System 1 name comes from
3:27 Demo: Jev vs an LLM head to head
4:11 The three question types Jev answers
5:35 Using Jev inside LangChain
6:04 Use case: model routing
6:47 Use case: auto mode for risky tool calls
7:28 Use case: Jev as a judge for evals
8:47 How to get started with Jev

Resources:
→ Building a Harness with Jev: https://www.langchain.com/blog/building-a-harness-with-jev
→ Jev-as-a-Judge for Agent Evals: https://www.langchain.com/blog/jev-agent-evals-langsmith
→ LangSmith: https://www.langchain.com/langsmith
→ LangChain Academy: https://academy.langchain.com