新闻
Search agent traces by behavior with AI Search in LangSmith
LangChain · 发布于 · 阅读约3分钟
30秒读懂
- 发生了什么
- LangSmith added AI Search, letting engineers find agent traces by describing behaviors in plain language like "did PII leak?" or "user got frustrated."
- 为何重要
- Matters for teams debugging agents in production, finding edge cases, building eval datasets, or discovering patterns across thousands of traces.
- 注意
- Search uses an 8K token budget per trace, prioritizing user messages and agent replies, so subtle behavioral differences in tool outputs may be missed.
- agent
这条新闻背后的模式
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。