We may earn an affiliate commission when you visit our partners.

AI Agents in LangGraph

LangChain, a popular open source framework for building LLM applications, recently introduced LangGraph. This extension allows developers to create highly controllable agents.

In this course you will learn to build an agent from scratch using Python and an LLM, and then you will rebuild it using LangGraph, learning about its components and how to combine them to build flow-based applications.

LangChain, a popular open source framework for building LLM applications, recently introduced LangGraph. This extension allows developers to create highly controllable agents.

Additionally, you will learn about agentic search, which returns multiple answers in an agent-friendly format, enhancing the agent’s built-in knowledge. This course will show you how to use agentic search in your applications to provide better data for agents to enhance their output.

In detail:

1. Build an agent from scratch, and understand the division of tasks between the LLM and the code around the LLM.

2. Implement the agent you built using LangGraph.

3. Learn how agentic search retrieves multiple answers in a predictable format, unlike traditional search engines that return links.

4. Implement persistence in agents, enabling state management across multiple threads, conversation switching, and the ability to reload previous states.

5. Incorporate human-in-the-loop into agent systems.

6. Develop an agent for essay writing, replicating the workflow of a researcher working on this task.

Start building more controllable agents using LangGraph!

Enroll now

Or subscribe to Coursera Plus

And get unlimited access to Coursera

Two deals to help you save

Save money when you learn. Here are two deals and offers that may be relevant to this course.

All coupon codes, vouchers, and discounts are applied automatically unless otherwise noted.

Valid until December 2

Annual Subscription

Invest in your career growth and save. Start your annual subscription to Coursera Plus and access 10,000+ programs.

Valid until March 12, 2027

Save 40% Off 3 Months

Access thousands of top-rated learning programs with a Coursera Plus monthly subscription and take 40% off 3 months for a limited time.

What's inside

Syllabus

Traffic lights

Read about what's good

what should give you pause

and possible dealbreakers

Explores the popular LangChain framework and its new extension, LangGraph, for building controllable agents using Python and an LLM

Teaches agentic search, which provides multiple answers in a format suitable for agents, enhancing their built-in knowledge

Instructs learners on implementing persistence in agents, enabling state management and conversation switching

Provides hands-on experience in building an essay-writing agent, replicating the workflow of a researcher

Taught by instructors Harrison Chase and Rotem Weiss, who are recognized for their work in agent development

Highly relevant to practitioners in AI and natural language processing who want to build more controllable agents using LangGraph

Covers foundational concepts of agent development using LangGraph

Introduces human-in-the-loop concepts for agent systems design

Requires students to come in with some foundational knowledge of Python and LLMs

May be more suitable for intermediate learners who have a basic understanding of agent development

Save this course

Create your own learning path. Save this course to your list so you can find it easily later.

Save

Reviews summary

Mastering ai agents with langgraph

According to students, this course provides a solid and practical foundation for building highly controllable AI agents using LangGraph. Learners particularly value the hands-on labs and coding exercises, which are described as excellent and directly applicable to real-world projects. The course offers deep dives into critical concepts like state management, human-in-the-loop, and agentic search, with clear and concise explanations from the instructor. However, a recurring point is the high level of assumed prior knowledge, especially in LangChain and advanced Python, which can make the pace feel fast for some learners. Some also noted occasional minor technical hurdles in labs due to library versions.

Instructor provides clear and understandable explanations.

"The instructor's explanations were clear and concise."

"The clear explanations from the instructor made even complex topics understandable."

"Instructor's teaching style is excellent."

"The instructor does a good job explaining complex ideas."

Content is directly useful for current LLM projects.

"The content is up-to-date and directly applicable to real-world projects."

"This is exactly what I needed to enhance my LLM projects."

"I've already started applying these techniques to my personal projects."

Thorough explanations of core LangGraph and agent concepts.

"I appreciated the deep dive into state management and human-in-the-loop concepts."

"The explanation of agentic search was particularly insightful."

"The deep dive into agentic search and state management was invaluable."

"The concepts are explained with clarity, and the practical exercises solidify understanding."

Strong emphasis on coding labs and practical application.

"The hands-on labs were excellent, especially the essay writing agent project."

"Excellent practical guide to LangGraph. The step-by-step approach from building an agent from scratch to using LangGraph was brilliant."

"The hands-on coding exercises reinforced the concepts. The practical application, like the essay writing agent, made it very clear how to implement these ideas."

"A fantastic deep dive into building agents with LangGraph. The hands-on nature of the course is its biggest strength."

Occasional issues with code or environment stability.

"Some of the code snippets provided in the labs occasionally have subtle bugs or rely on very specific library versions, which can lead to frustrating debugging sessions."

"I spent a lot of time debugging environment issues and understanding the underlying LangChain concepts before I could even grasp the LangGraph specifics."

"The rapid evolution of LangChain and its ecosystem means some of the material might quickly become slightly outdated or require minor adjustments."

Assumes advanced knowledge in Python and LangChain.

"Some parts felt a bit fast-paced, assuming a high level of prior knowledge in advanced Python and LLM concepts."

"I found the prerequisites to be higher than stated. If you're not already very comfortable with LangChain... you might struggle."

"I came in hoping to learn LangGraph from a relatively beginner perspective but was immediately lost... Not for intermediate learners, definitely advanced."

"This course assumes too much prior knowledge. As someone relatively new to LangChain, I found myself constantly lost."

Activities

Be better prepared before your course. Deepen your understanding during and after it. Supplement your coursework and achieve mastery of the topics covered in AI Agents in LangGraph with these activities:

Review Python coding skills

Show steps

Review Python's syntax and semantics before the course begins to get up to speed quickly

Browse courses on Python

Show steps

Go through online tutorials on Python fundamentals
Solve easy coding exercises on platforms like HackerRank or LeetCode

Python Refresher

Show steps

Review Python basics to ensure you have a strong foundation for building agents with LangGraph.

Browse courses on Python

Show steps

Review Python syntax and data structures
Complete Python coding exercises

Review Python basics

Show steps

Refresh your understanding of basic Python concepts to strengthen your foundation for building LLM applications.

Browse courses on Python

Show steps

Review Python data types, variables, and operators.
Practice writing simple Python functions and loops.
Complete a few coding exercises to test your understanding.

12 other activities

Expand to see all activities and additional details

Show all 15 activities

LangChain Basics Review

Show steps

Review the basics of LangChain to ensure a foundational understanding of the LLM framework used in this course.

Browse courses on LangChain

Show steps

Review LangChain documentation
Complete LangChain tutorials
Build a simple agent using LangChain

LangGraph Workshop

Show steps

Attend a workshop to delve deeper into LangGraph and its applications in agent development.

Browse courses on LangGraph

Show steps

Register for the workshop
Attend the workshop sessions
Participate in hands-on exercises

Practice building agents using LangChain

Show steps

Build several simple agents to practice using LangChain before covering the more complex LangGraph

Browse courses on LangChain

Show steps

Create a new LangChain project
Create a simple agent that responds to user input

Build a simple agent using LangChain

Show steps

Follow guided tutorials to build a basic agent using LangChain, reinforcing your understanding of the framework's core concepts.

Browse courses on LangChain

Show steps

Find a beginner-friendly LangChain tutorial.
Set up your development environment and install the necessary tools.
Follow the tutorial step-by-step to build your agent.
Test your agent and make any necessary adjustments.

Agentic Search Exploration

Show steps

Explore agentic search techniques to enhance the accuracy and relevance of your agent's responses.

Show steps

Follow tutorials on agentic search
Implement agentic search in your LangGraph agent
Analyze the impact of agentic search on agent performance

Practice using agentic search

Show steps

Practice using agentic search to find answers for your agents

Show steps

Create a new agentic search query
Review the results and identify the most relevant answers

LLM Prompt Engineering Exercises

Show steps

Practice writing effective prompts for LLMs to improve your ability to create controllable agents.

Browse courses on LangGraph

Show steps

Analyze existing LLM prompts
Write prompts for various agent tasks
Evaluate the effectiveness of different prompts

Develop an agent for a specific task

Show steps

Building an agent for a specific task will allow you to apply your skills and knowledge in a practical setting

Browse courses on LangGraph

Show steps

Identify a specific task for your agent
Design the architecture of your agent
Implement your agent using LangGraph
Test and evaluate your agent

Develop an essay-writing agent

Show steps

Challenge yourself by developing an essay-writing agent using LangGraph, applying your knowledge of agentic search and persistence.

Browse courses on Essay Writing

Show steps

Define the requirements and specifications for your agent.
Design the architecture of your agent, including the components and their interactions.
Implement the agent using LangGraph, incorporating agentic search and persistence.
Evaluate the performance of your agent and make improvements as needed.

LangGraph Peer Mentorship

Show steps

Mentor other students in LangGraph to solidify your understanding and help others succeed.

Browse courses on LangGraph

Show steps

Volunteer as a mentor
Meet with mentees regularly
Provide guidance and support on LangGraph topics

LangGraph Agent Project

Show steps

Build a complete agent using LangGraph to demonstrate your understanding of agent design and implementation.

Browse courses on LangGraph

Show steps

Design the agent's architecture and functionality
Implement the agent using LangGraph
Test and evaluate the agent's performance
Document the agent's development process

Summarize key concepts from the course

Show steps

Writing a summary of the course's key concepts will reinforce your understanding and help you retain information better

Show steps

Review course materials and lectures
Identify the key concepts, definitions, and examples
Write a clear and concise summary of each concept
Use visuals, diagrams, or examples to illustrate your points

Career center

Learners who complete AI Agents in LangGraph will develop knowledge and skills that may be useful to these careers:

Reading list

We've selected 50 books that we think will supplement your learning. Use these to develop background knowledge, enrich your coursework, and gain a deeper understanding of the topics covered in AI Agents in LangGraph.

The Complete LangGraph Blueprint

Save

Is specifically dedicated to LangGraph and building AI agents using this framework. It provides a comprehensive guide with practical examples and resources for building dynamic AI agents. This book is highly relevant for anyone focusing on LangGraph and offers in-depth knowledge and practical skills.

AI Agents in LangGraph

Two deals to help you save

What's inside

Syllabus

Traffic lights

Save this course

Reviews summary

Mastering ai agents with langgraph

Activities

Career center

Reading list

Share

Similar courses

Coursera Buyer Protection & Guarantee

7-Day Free Trial & Free Audit

14-Day Refund Guarantee

Verified Academic & Industry Partner