Why managed agents are the next big thing in agent building
Harrison Chase discusses the evolution of agent building, highlighting the transition from early AI frameworks to more advanced tools like LangGraph, Google ADK, and Vercel’s AI SDK, which gave developers greater control over LLMs. These tools enabled the creation of complex AI applications, with models becoming powerful enough to power agents in 2025. Managed agent experiences, such as Deep Agents, simplify the development process by bundling the harness with infrastructure, focusing on business logic, runtime reliability, and user experience. The launch of Managed Deep Agents aims to make agent development more accessible and efficient, offering configurability and production-ready infrastructure with features like LangSmith Deployments and sandboxes.
More from Langchain
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
How many of your agent's calls actually need a frontier model?
We benchmarked NVIDIA NeMo Switchyard on 145 agent tasks. Only 7% of turns needed a frontier model, and routing cut cost 74% for six points of accuracy.
langchain.com··Mads Kristian Nylund·Open Source AIAI ToolsAI Infrastructure