发生了什么: Jev is now available in LangSmith Evals

Jev, a System One model, is now available as a judge for evaluations in LangSmith to assess agent behavior with typed answers.

为何重要: Jev is now available in LangSmith Evals

Teams evaluating agents at scale should consider this when cost and speed of running many evals limit their testing frequency and coverage.

注意: Jev is now available in LangSmith Evals

Jev works best for narrow, typed decisions at volume; it lacks written reasoning that LLM judges provide, and TypeSafe does not offer zero data retention.

新闻

Jev is now available in LangSmith Evals

LangChain · 发布于 2026年9月21日 · 阅读约3分钟

30秒读懂

发生了什么: Jev, a System One model, is now available as a judge for evaluations in LangSmith to assess agent behavior with typed answers.
为何重要: Teams evaluating agents at scale should consider this when cost and speed of running many evals limit their testing frequency and coverage.
注意: Jev works best for narrow, typed decisions at volume; it lacks written reasoning that LLM judges provide, and TypeSafe does not offer zero data retention.

阅读完整文章

agent
eval

这条新闻背后的模式

Eval-Driven Development (Agent CI)
LLM as Judge
Synthetic User Simulation

每个模式都讲清楚技术如何运作、何时值得投入，以及在哪里会失效。

The Agent Architect

每周一个模式、一个权衡、一个生产事故案例。为构建智能体系统的人准备的每周简报。

每周一封邮件,一键退订。您的地址仅用于发送简报。