What career opportunities can this course help me unlock?

Skills in agentic AI development are highly valuable for roles such as Software Developer, Data Scientist, Machine Learning Engineer, AI Engineer, and Automation Specialist. These positions involve building intelligent systems that use language models to reason, interact with tools, and automate complex workflows. These capabilities are increasingly in demand across industries where adaptive, language-driven automation is transforming how work gets done.

Do I need machine learning experience to take this course?

No prior machine learning (ML) experience is required. If you're comfortable with Python, you're ready to go. This course focuses on building practical agentic AI systems that reflect, improve, and act. No complex ML understanding is required.

How is agentic AI development different from traditional coding or prompt engineering?

Traditional development builds static applications, and prompt engineering fine-tunes LLM responses. But agentic AI development focuses on designing autonomous, stateful systems that can evaluate their outputs, manage memory, and interact intelligently over time. You'll learn how to architect systems that think, adapt, and collaborate, using tools such as LangGraph to build workflows with cycles, conditionals, and inter-agent communication.

When will I have access to the lectures and assignments?

To access the course materials, assignments and to earn a Certificate, you will need to purchase the Certificate experience when you enroll in a course. You can try a Free Trial instead, or apply for Financial Aid. The course may offer 'Full Course, No Certificate' instead. This option lets you see all course materials, submit required assessments, and get a final grade. This also means that you will not be able to purchase a Certificate experience.

What will I get if I subscribe to this Certificate?

When you enroll in the course, you get access to all of the courses in the Certificate, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile.

Agentic AI with LangChain and LangGraph

Agentic AI with LangChain and LangGraph

本课程是多个项目的一部分。

位教师：Faranak Heidari

24,981 人已注册

包含在中

了解更多

3个模块

深入了解一个主题并学习基础知识。

97 条评论

中级等级

推荐体验

1 周完成

在 10 小时一周

灵活的计划

自行安排学习进度

3个模块

深入了解一个主题并学习基础知识。

97 条评论

中级等级

推荐体验

1 周完成

在 10 小时一周

灵活的计划

自行安排学习进度

您将学到什么

Build agentic AI systems using LangChain and LangGraph to support memory, iteration, and conditional logic
Design and implement self-improving agents using Reflection, Reflexion, and ReAct architectures
Apply agent orchestration techniques to build collaborative multi-agent systems
Implement agentic RAG systems that route queries and support retrieval-enhanced reasoning

您将获得的技能

您将学习的工具

要了解的详细信息

可分享的证书

添加到您的领英档案

作业

11 项作业

授课语言：英语（English）

91%

of learners achieved a positive career outcome

了解顶级公司的员工如何掌握热门技能

了解关于 Coursera for Business 的更多信息

Petrobras, TATA, Danone, Capgemini, P&G 和 L'Oreal 的徽标

积累特定领域的专业知识

此课程作为的一部分提供

在注册此课程时，您还需要选择一个特定的合作项目。

向行业专家学习新概念
获得对主题或工具的基础理解
通过实践项目培养工作相关技能
获得可共享的职业证书

该课程共有3个模块

Ready to build intelligent AI agents that can reason, improve, and collaborate? This hands-on course gives you the skills to build agentic AI systems using LangChain and LangGraph in just 3 weeks.

You’ll design stateful workflows that support memory, iteration, and conditional logic. You’ll explore how to build self-improving agents using Reflection, Reflexion, and ReAct architectures, empowering your agents to reason about their outputs and refine them over time. Plus, you’ll work on guided labs where you’ll structure agent feedback, integrate external data, and generate context-aware responses through step-by-step reasoning. You’ll then develop collaborative multi-agent systems that coordinate tasks, retrieve relevant data, and solve complex problems using agentic RAG. Plus, you'll gain experience in agent orchestration, query routing, and governance strategies for building robust, scalable AI applications. By the end of the course, you’ll have built working prototypes of agentic systems and gained hands-on skills to design reliable, adaptable agents. Enroll today and get ready to power up your portfolio!

单元详情

This module introduces LangGraph for building intelligent, stateful AI agents that support memory, iteration, and conditional logic. You’ll explore how nodes, edges, and shared state enable dynamic workflows, and how LangGraph extends LangChain for advanced control. Through foundational concepts and hands-on practice, you’ll learn to design, build, and execute workflows that reflect real-world agentic behavior

涵盖的内容

6个视频2篇阅读材料4个作业1个应用程序项目5个插件

6个视频总计37分钟

Course Introduction3分钟
RAG and Agentic AI Professional Certificate Overview6分钟
Generative versus Agentic AI7分钟
Core Components of LangGraph 4分钟
LangGraph versus LangChain: When to Use What  10分钟
Getting Started with LangGraph 101 7分钟

2篇阅读材料总计6分钟

Course Overview3分钟
Summary and Highlights 3分钟

4个作业总计39分钟

Practice Quiz: Introduction to Agentic AI6分钟
Practice Quiz: LangGraph versus LangChain6分钟
Practice Quiz: Build a LangGraph Workflow 6分钟
Graded Quiz: Introduction to LangGraph 21分钟

1个应用程序项目总计60分钟

Lab: LangGraph 101: Building Stateful AI Workflows60分钟

5个插件总计50分钟

Reading: Helpful Tips for Course Completion5分钟
Reading: Agentic AI 15分钟
Reading: LangGraph Architecture: Designing Effective Workflows10分钟
Reading: LangGraph versus LangChain: Pros, Cons, and Practical Considerations  10分钟
Cheat Sheet: Introduction to LangGraph 10分钟

This module focuses on building self-improving AI agents using LangGraph. You’ll explore and implement Reflection, Reflexion, and ReAct agent architectures to design workflows that evaluate and refine their own outputs. Through guided labs, you’ll gain hands-on experience creating agents that reason, integrate feedback, and improve performance using structured approaches grounded in reflection and prompt engineering.

涵盖的内容

5个视频1篇阅读材料4个作业3个应用程序项目2个插件

5个视频总计42分钟

Overview: Types of AI Agents10分钟
The Art of AI Self-Improvement: Building Reflection Agents 8分钟
Understanding Reflexion Agents6分钟
Building Reflexion Agents8分钟
ReAct: Building Agents that Reason Before Acting  9分钟

1篇阅读材料总计3分钟

Summary and Highlights 3分钟

4个作业总计39分钟

Practice Quiz: Build Reflection Agents 6分钟
Practice Quiz: Advanced Self-Improvement with Reflexion Agents 6分钟
Practice Quiz: ReAct: Integrating Reasoning and Action 6分钟
Graded Quiz: Build Self-Improving Agents with LangGraph 21分钟

3个应用程序项目总计165分钟

Lab: Building a Reflection Agent with LangGraph45分钟
Lab: Building a Reflexion Agent with External Knowledge Integration 30分钟
Lab: ReAct: Build Reasoning and Acting AI Agents with LangGraph90分钟

2个插件总计20分钟

Reading: Structuring LLM Tool Calls with Pydantic and JSON Serialization 10分钟
Cheat Sheet: Build Self-Improving Agents with LangGraph 10分钟

This module focuses on designing and implementing multi-agent systems using LangGraph. You’ll explore how specialized agents can collaborate to solve complex problems through structured orchestration. Key topics include core principles of multi-agent systems, collaboration patterns, and governance considerations. Through hands-on practice, you’ll build a multi-agent RAG system that dynamically routes queries to relevant data sources, gaining practical experience in coordinating specialized agents to enhance retrieval and reasoning. 