Building Ambient Agents with LangGraph
Build your own ambient agent to manage your email. You’ll learn the fundamentals of LangGraph as you build an email assistant from scratch, and use LangSmith to evaluate its performance.
Course Overview
Getting Set Up
Module 1 Introduction
Module 1 Resources
LangGraph 101
Module 1 Feedback
Module 2 Introduction
Module 2 Resources
Building Agents
Module 2 Feedback
Module 3 Introduction
Module 3 Resources
Agent Evaluations
Module 3 Feedback
Module 4 Introduction
Module 4 Resources
Human-in-the-Loop
Module 4 Feedback
Module 5 Introduction
Module 5 Resources
Memory
Module 5 Feedback
No. LangGraph is an orchestration framework for complex agentic systems and is more low-level and controllable than LangChain agents. On the other hand, LangChain provides a standard interface to interact with models and other components, useful for straight-forward chains and retrieval flows.
Other agentic frameworks can work for simple, generic tasks but fall short for complex tasks bespoke to a company’s needs. LangGraph provides a more expressive framework to handle companies’ unique tasks without restricting users to a single black-box cognitive architecture.
LangGraph will not add any overhead to your code and is specifically designed with streaming workflows in mind.
Yes. LangGraph is an MIT-licensed open-source library and is free to use.
LangGraph Platform is a platform for deploying AI agents that can scale with production volume. It offers easy-to-use APIs for managing agent state, memory, and user interactions— which makes building dynamic experiences more accessible. Once you're ready to ship to production, use LangGraph Platform to gracefully handle large workloads, with features like retries and cost-efficient execution for reliable performance. LangGraph Platform also includes LangGraph Studio, which lets you gain visibility into how agents act, helping you prototype faster.