Products

LangSmith 新增 3 项 trace 数据权限管控功能

Why we picked it

LangSmith 新增了 trace 输入输出的权限控制,默认大家只能看到调用统计,敏感内容要审批后才能看。做 LLM 应用运维的团队可以参考这套分层授权思路,不用在"全开放"和"全屏蔽"之间二选一。

LangChain 在 LangSmith 中新增 3 项管控功能,用于处理 trace 数据中可能包含的敏感信息:1️⃣ 控制谁能查看 trace 的输入和输出;

Body

2️⃣ 通过用户组(user groups)按团队分配权限;3️⃣ 基于 metadata 设置 trace 级别的访问策略。

Harrison Chase 建议的默认做法是:trace 全量记录到 LangSmith,但默认限制对 inputs/outputs 的访问,团队成员仍能看到调用次数、被调用的工具等元信息。当客户投诉时,在获得客户同意后,可以让一小批工程师临时查看该问题 trace 的完整输入输出。

这套方案的核心思路是把"可观测性"和"敏感数据可见性"拆开:调用指标对全员开放,敏感内容按需授权,兼顾调试效率与数据安全。

Original · Harrison Chase

trace data contains a ton of valuable insights to mine, but also a lot of sensitive data you need to manage carefully these three new controls stack up nicely to enable responsible trace governance: - by default, trace everything to langsmith, but restrict access to inputs/ouputs. this lets people see number of calls, tools getting invoked, etc; but restricts any sensitive info - when a customer complains, get their permission and enable a small set of engineers to see inputs/outputs for their bad traces sounds simple/basic/boring, but security and governance is really important to get right for data like traces which can contain sensitive info! LangChain @LangChain We’re adding 3 new controls in LangSmith to help your team manage sensitive trace data. 1️⃣ Control who can see trace inputs and outputs 2️⃣ Manage team-by-team permissions with user groups 3️⃣ Set trace-level access policies using metadata

Industry Coordinates & Source Verification

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, LangChain, AI safety, observability.

Source attribution: curated from Harrison Chase (@hwchase17).