Give your agent its own computer
LangSmith sandboxes provide secure, isolated environments for agents to execute untrusted code, manage state, and run workflows, enabling efficient and controlled execution of tasks like model-generated scripts or data analysis. These sandboxes offer persistent storage, network access, and package management, allowing agents to run multi-step processes without exposing production infrastructure. They support scalable execution, burst capacity for training, and secure access to resources, making them essential for agents that require state persistence, dynamic code execution, or GPU utilization.
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