Agents need their own computer. Here's how to give them one safely.
LangSmith Sandboxes offer secure, isolated environments for agents to run code, ensuring safety and control by isolating each agent's execution. These sandboxes use hardware-virtualized microVMs with their own kernels, persisting state across sessions, and preventing unauthorized access. They provide resource limits, credential management, and lifecycle control to prevent excessive resource consumption. Agents must treat output as untrusted and avoid passing raw output back to models, with non-agentic reads recommended for sensitive workflows. Sandboxes support snapshots, forks, and logging, and managed sandboxes offer a simplified interface for reliable and secure execution.
More from Langchain
Why managed agents are the next big thing in agent building
Managed Deep Agents gives developers a managed way to build, run, and deploy Deep Agents with built-in runtime, streaming, sandboxes, evals, memory, and auth.
langchain.com··Mads Kristian Nylund·AI InfrastructureAI-agents
LangSmith BYOC on AWS is generally available
LangSmith Bring Your Own Cloud is now generally available on AWS, giving Enterprise teams managed observability, evaluation, and deployment inside their own VPC.
langchain.com··Mads Kristian Nylund·AI DevelopmentAI InfrastructureAI Platforms
What is an AI agent?
Learn what AI agents are, how they work in an LLM loop, and where workflows fit so you can build reliable, production-ready autonomous systems.
langchain.com··Mads Kristian Nylund·AI DevelopmentAI InfrastructureAI-agents