AI · Official
LangSmith Adds Controls to Limit Access to Sensitive Data in Agent Traces
LangChain blog ·

At a glance
LangChain added three new controls to LangSmith that let teams limit who can see sensitive data in agent traces. Engineers can still debug performance problems without viewing customer inputs and outputs. Admins can set access by group or by trace metadata.
Key points
- Admins can hide trace inputs and outputs while still showing run trees, latency, and token usage.
- Users can be sorted into groups, each with its own permissions on top of existing role-based and attribute-based access controls.
- Admins can set trace-level rules based on root run metadata, such as a customer ID or a user ID.
Why it matters
Agent traces often contain customer data like health or payment details, and laws and contracts can require strict access limits. These controls let teams keep debugging going without exposing that data.
Original source
Protect sensitive data in your traces: new controls in LangSmith
LangChain blog · Nov 18, 03:00 KST
Read on LangChain blog ↗AI summarized the original article. Check the original for accuracy. Copyright belongs to LangChain blog.
More from this field
- Amazon Releases SMART Toolkit to Simplify WhatsApp AI Agents on AgentCore
Amazon has released SMART, an open source Python toolkit and Terraform setup that handles the WhatsApp connection for AI agents built on Amazon Bedrock AgentCore. Developers keep control of their agent's logic while SMART takes care of messages, media, memory, and scheduling. The article says one command deploys the whole infrastructure to an AWS account.
Amazon AWS Machine Learning blog · Nov 18, 03:48 KST - Google Extends Gemini Chat Retention to Two Months, Even With History Off
Google is extending how long it keeps temporary Gemini chats, including those made with chat history turned off, to about two months. Before, it kept them for 72 hours. Google says the change is meant to improve safety and security as AI systems grow more capable.
TechCrunch · Nov 18, 03:48 KST - OpenAI Demos GPT-6.2 Astra Rebuilding a 3D Room From Two Video Frames
OpenAI shows how its GPT-6.2 Astra model can recreate a room from just two video frames. The model builds the set in Blender, changes the decor and lighting, and turns it into an interactive space and a virtual webcam background. The video is a demo of the model's coding and 3D skills.
OpenAI 공식 YouTube · Nov 18, 03:41 KST - Edge for Business Adds Agentic Browsing and Skills Recorder at Ignite 2026
Microsoft shared new features for its Edge for Business browser at its Ignite 2026 conference. Agentic browsing, which lets AI agents finish multi-step tasks across websites, is now part of Cowork and is generally available. A skills recorder for turning workflows into reusable steps is coming in preview, and faster agent performance is being tested.
Microsoft Edge blog · Nov 18, 03:40 KST