Level up with LangChain Academy
Dive into self-paced, comprehensive courses designed to help you gain the relevant skills and knowledge to build, test, deploy, and monitor agents.
Learn how to build long-running agents for complex workflows with Deep Agents, LangChain’s open-source agent harness. You’ll explore what an agent harness is, how it accelerates development, and how to use LangSmith to improve your agents.
Learn the essentials of LangSmith — the comprehensive platform for agent engineering that helps teams use live production data for continuous testing and improvement.
Learn to deploy, manage, and control your agents with LangSmith Deployment.
Start with either Introduction to LangChain - Python, Introduction to LangGraph - Python, or Introduction to Deep Agents under the "Build" course category if you're just getting started on your agent building journey. For agent observability and improvement, go to Quickstart: LangSmith Essentials.
Our course content is always free! Our paid offering is the LangChain Certified Agent Engineer certification exam.
LangSmith is an agent engineering platform developed by LangChain, allowing you to build, test, deploy, and monitor your agents.
No, you don't need a LangSmith account to access course content. However, some courses contain optional LangSmith exercises. If you want to follow along you can create a free account at smith.langchain.com.
LangGraph is an agent runtime, LangChain is an agent framework, and Deep Agents is an agent harness. The runtime offers the most control and the least abstraction; the harness offers the inverse. Together, they are the three layers of our open source agent stack. You can own every part of the agent: the chosen model, the context it sees, and the harness that runs it. Each layer essentially plays a different role and offers a different amount of control. You can also move between layers instead of picking one.