LangSmith 新增 AI Search：用自然语言检索 Agent 追踪记录
LangChain 给 LangSmith 加了 AI Search，直接用一句话描述就能搜出对应的 Agent 运行记录，不用再配 evaluator 或翻几小时日志。
LangChain 在 Interrupt 大会上宣布 LangSmith 上线 AI Search 功能。此前要回答"用户是否感到沮丧""Agent 在哪一步任务失败""用户在哪试图取消订阅"这类问题，需要配置 evaluator 或人工阅读大量对话。现在直接用自然语言描述，LangSmith 就能返回符合条件的 traces。该功能面向 Agent 追踪数据的排查与分析场景。
ICYMI: AI Search in LangSmith! LangChain @LangChain 🔎 Announced at Interrupt: AI Search in LangSmith You used to need an evaluator or read hours of conversations to find traces that answer questions such as: 💬 Does the user seemed frustrated?" 💬 Where did the agent fail to complete the task? 💬 Where is the user trying to cancel their subscription? Now, just describe it. LangSmith returns the traces where it happen langchain.com/blog/agent-tra… uCT9 Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 0 🔄 0 ❤️ 2 👀 1007 ⚡