LangSmith 新增看板:统一衡量各编程 Agent 的 ROI
工程团队同时用 Claude Code、Cursor、Copilot 时,这个看板能直接算出每个 PR 花了多少钱、哪些钱打水漂了。采购编程 Agent 时终于有数据可依,管理多工具的团队值得装上试试。
LangChain 为 LangSmith 推出 coding agent ROI 看板,可将团队使用的多个编程 Agent 的追踪数据汇总到同一视图,覆盖 Claude Code、Codex、Cursor、GitHub Copilot 和 Deep Agents,且不受 harness 和模型供应商限制。
新功能把 Pull Request 与对话线程关联起来,团队可以看到一次已合并的 PR 实际花了多少钱,以及哪些花费最终没有产出任何 PR。接入流程分三步:为团队使用的每个编程 Agent 安装 LangSmith 插件,连接 GitHub,然后在 LangSmith 打开编程 Agent 总览页。
此前企业往往在 Claude Code、Cursor 等工具间分散采购,成本与产出难以对账;这一看板让工程管理者能在同一处比较各工具和模型的实际投入产出,采购决策可以直接引用合并 PR 成本等数据。
How to get started 1️⃣ Install the LangSmith plugin for each coding agent your team uses. Available for: ✅ Claude Code ✅ Codex ✅ Cursor ✅ GitHub Copilot ✅ Deep Agents 2️⃣ Connect GitHub 3️⃣ Open the coding agent overview page in LangSmith LangChain @LangChain New in LangSmith: Measure coding agent ROI 📊 Our new dashboard pulls every coding agent you trace into one view, across harnesses + model providers ✅ Pull requests are now linked to threads, so you can see what a merged PR cost & how much spend never led to one langchain.com/blog/langsmith… B
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include LangSmith, Claude Code, Cursor, GitHub Copilot.
Source attribution: curated from LangChain (@LangChainAI). Cross-source corroboration: 11 independent sources have covered this development (including Ate-a-Pi, shao__meng, openclaw), confirming industry-wide signal strength.