LangSmith Custom Apps 正式 GA：用提示词生成智能体数据界面
LangChain 把 LangSmith 的运行数据开放成自定义界面了，写句提示词就能生成标注队列或 trace 审查页，做 Agent 评估的可以试试。
LangChain 宣布 LangSmith Custom Apps 正式发布（GA），核心思路是用一句提示词从智能体运行数据生成任意界面。官方列举了三种典型用法：标注队列（annotation queues）可逐条或批量审查和标注运行记录；实验对比视图可并排查看不同实验的输出和指标；追踪审查（trace reviews）可构建 trace 或会话历史页面来排查应用行为。该功能面向使用 LangSmith 做 LLM 应用观测和评估的团队，把过去需要自建的数据面板变成提示词即得。
A few things you can build: 1️⃣ Annotation queues: Review and label one (or many) runs at a time 2️⃣ Experiment comparisons: Compare outputs and metrics across experiments side by side 3️⃣ Trace reviews: Build trace or thread history views to inspect app behavior LangChain @LangChain Introducing LangSmith Custom Apps Create any interface from your agent data with a prompt. If you can think it, LangSmith can build it. Now GA. langchain.com/blog/langsmith… Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 1 🔄 0 ❤️ 2 👀 889 📊 1 ⚡
