Skip to main content
Search

# LangSmith

3 related articles

Subscribe to updates
  1. langchain.com

    LangSmith adds three access gates to production traces: engineers see run trees, not customer names or payment details

    LangSmith has added three access controls to its Enterprise plans for production traces: admins can hide trace inputs and outputs, assign permissions by user group, and set trace-level policies from root run metadata. Previously teams either built custom observability setups with duplicated traces and multiple workspaces, which cost platform teams more to configure and maintain, or kept traces out of observability platforms, which left agent engineers without visibility. The controls layer together so engineers can inspect run trees, latency and cost while sensitive inputs and outputs stay with the people who need them.

  2. langchain.com

    LangSmith rebuilds around the agent: cross-framework agents get one owner, one ID and one governance view

    LangSmith has been reorganized around an agent record that ties the build, run, improve and govern stages to a single agent identity. Previously, traces sent to LangSmith sat in a flat project hierarchy with no association to a particular agent, and traces from one agent across environments were not linked, so platform teams struggled to say which agents existed, who owned them, and what they cost or how they performed. Each agent record now carries an owner, a globally unique immutable ID and a type, and agents on other platforms can register through OpenTelemetry Protocol and be measured the same way.

  3. langchain.com

    LangSmith BYOC lands on AWS, Azure and Google Cloud: data stays in your account, updates stay with LangChain

    LangChain has extended LangSmith's BYOC deployment from AWS to Azure and Google Cloud, with AWS generally available and Azure and Google Cloud in Beta. Until now, teams with strict compliance boundaries ran self-hosted LangSmith, which required dedicated platform engineers to patch stateful services, configure databases and run schema migrations; BYOC keeps the control plane with LangChain and places the data plane holding traces, prompts, datasets and agent deployments in the customer's own cloud account and virtual network, while LangChain handles scaling, schema updates and runtime dependencies.

You’re all caught up