LangSmith LLM Gateway enforces cost limits and PII redaction for AI agents

LangChain Blog

LangSmith LLM Gateway is now in private beta, preventing agents from burning through $10k overnight by enforcing spend limits. It requires only a one-line base_url swap to intercept requests and apply policies, with violations surfaced directly in LangSmith traces. The gateway also redacts sensitive data like social security numbers before they reach the model.

LangChain

See 14 more sources

LangSmith: Redesigned product homepage and Resource Tags for better organization5 days ago

Announcing LangSmith is now a transactable offering in the Azure Marketplace6 days ago

Introducing Open SWE: An Open-Source Asynchronous Coding Agent5 days ago

Introducing LangSmith’s No Code Agent Builder3 days ago

Monte Carlo: Building Data + AI Observability Agents with LangGraph and LangSmith5 days ago

How Factory used LangSmith to automate their feedback loop and improve iteration speed by 2x5 days ago

Introducing Langsmith Engine19 days ago

Managed Deep Agents is built for agents that need to work over long time horizons, use tools,...25 days agoLangChain

LangSmith Sandboxes lets you run untrusted code safely. @MukilLoganathan’s TLDR on Auth Proxy....6 days agoLangChain

Most agent team runs the same manual improvement loop: Trace → find failure patterns → fix prompts...17 days agoLangChain

You don’t need new infrastructure to get started with Engine. It’s built on top of your current...6 days agoLangChain

.@hwchase17 explains LangSmith LLM Gateway in <90 seconds.12 days agoLangChain

LangSmith is now available as a fully managed SaaS offering in the @awscloud Marketplace: ✅Deploy...6 days agoLangChain

LangSmith Engine: The agent's agent.5 days agoLangChain

LangChain Blog

Jun 15, 3:00 PM