VOOZH about

URL: https://www.coursera.org/learn/multi-agent-systems-with-langgraph

⇱ Multi-Agent Systems with LangGraph | Coursera

Multi-Agent Systems with LangGraph

Keep adding new skills with 10,000+ programs for $239 (usually $399). Save now.

Multi-Agent Systems with LangGraph

Instructor: Edureka

Included with

Ask Coursera

Gain insight into a topic and learn the fundamentals.
Intermediate level

Recommended experience

1 week to complete
at 10 hours a week
Flexible schedule
Learn at your own pace
Gain insight into a topic and learn the fundamentals.
Intermediate level

Recommended experience

1 week to complete
at 10 hours a week
Flexible schedule
Learn at your own pace

What you'll learn

  • Explain how LangGraph executes workflows and manages state using reducers, typed state, and checkpoints.

  • Implement stateful agent pipelines with conditional routing, parallel execution, and recovery mechanisms.

  • Analyze agent behavior using execution logs, snapshots, and time-travel debugging techniques.

  • Design human-in-the-loop and multi-agent systems using supervision, planning, and consensus reasoning.

Details to know

Shareable certificate

Add to your LinkedIn profile

Recently updated!

February 2026

Assessments

14 assignments¹

AI Graded see disclaimer
Taught in English

Build your subject-matter expertise

This course is part of the Agentic AI Engineering Specialization
When you enroll in this course, you'll also be enrolled in this Specialization.
  • Learn new concepts from industry experts
  • Gain a foundational understanding of a subject or tool
  • Develop job-relevant skills with hands-on projects
  • Earn a shareable career certificate

There are 4 modules in this course

This program introduces Building Stateful & Multi-Agent Systems with LangGraph for developers and AI engineers who want to move beyond single-prompt agents and build reliable, production-ready workflows. You’ll begin by learning how LangGraph executes agent workflows and why state management is critical for correctness, debuggability, and long-running tasks.

Next, you’ll work with state reducers, typed state objects, and checkpointing mechanisms that allow agents to persist progress, recover from failures, and resume complex multi-step executions. Through hands-on demonstrations, you’ll implement conditional routing, parallel execution paths, and modular subgraphs to enable dynamic, decision-driven workflows. As you progress, you’ll design human-in-the-loop systems with approvals and interrupts, apply debugging and time-travel analysis using execution logs and snapshots, and build multi-agent systems using supervisor–worker and consensus-based reasoning models for scalable, collaborative agent workflows. By the end of the program, you will be able to: - Explain how LangGraph executes workflows and manages state across agent nodes. - Design stateful agent pipelines using typed state objects and reducer patterns. - Implement checkpointing and recovery mechanisms for long-running agent workflows. - Control execution flow using conditional routing, parallel execution, and subgraphs. - Build human-in-the-loop workflows with approvals, interrupts, and state inspection. - Debug agent systems using execution logs, snapshots, and time-travel analysis. - Design multi-step planner–executor workflows for complex task execution. - Orchestrate multi-agent systems using supervisor–worker and consensus-based models. This program is ideal for AI engineers, backend developers, and system architects who want to build agent systems that are not only intelligent, but also predictable, auditable, and production-ready. Prior experience with Python, LLM fundamentals, and basic agent concepts will help maximize your learning experience. Learners need a reliable internet connection, a modern web browser, and access to Python development tools. The course uses LangGraph and modern LLM APIs, which do not require specialized hardware. Familiarity with LangChain or agent-based workflows is recommended. Join us to learn how to design stateful, multi-agent systems that can plan, recover, coordinate, and reason reliably in real-world applications.

Explore the core execution model behind LangGraph and learn how state enables reliable, controllable agent workflows. This module builds a strong foundation in reducer-based state design, typed state objects, and deterministic state updates across graph executions. You’ll gain hands-on experience implementing persistent checkpoints, restoring execution from failures, and managing multi-branch workflows.

What's included

14 videos5 readings4 assignments

14 videos•Total 69 minutes
  • Specialization Introduction•6 minutes
  • Course Introduction•4 minutes
  • What is LangGraph?•4 minutes
  • Designing Decision-Driven Agent Workflows with LangGraph•4 minutes
  • LangGraph StateReducer Fundamentals•4 minutes
  • Demonstration: Creating a Typed State Object•5 minutes
  • Demonstration: Managing Graph State Updates and Stateful Variables•6 minutes
  • Checkpointer Engines and Recovery Logic•4 minutes
  • Demonstration: Implementing Persistent Checkpoints - I•7 minutes
  • Demonstration: Implementing Persistent Checkpoints - II•3 minutes
  • Demonstration: Restoring State and Resuming Multi-Branch Execution•6 minutes
  • DAG Execution and Conditional Routing Techniques•3 minutes
  • Demonstration: Building a Conditional Router Node•6 minutes
  • Demonstration: Implementing Parallel Execution and Subgraph Invocation•8 minutes
5 readings•Total 75 minutes
  • Course Syllabus•15 minutes
  • State Machine Patterns in LangGraph: Managing Typed State and Stateful Variables•15 minutes
  • Recovery and Fault Tolerance in State Machines•15 minutes
  • Graph Routing Models: DAG Execution, Conditional Routing, and Parallelism•15 minutes
  • Module Summary: State Management, Checkpointing, and Graph Architecture•15 minutes
4 assignments•Total 33 minutes
  • Practice Assignment: State Machines and Reducer-Based Workflow Design•6 minutes
  • Practice Assignment: Checkpointing Mechanisms and Recovery Workflows•6 minutes
  • Practice Assignment: Graph Execution Flow and Conditional Routing•6 minutes
  • Knowledge Check: State Management, Checkpointing, and Graph Architecture•15 minutes

Learn how to design agent workflows that balance automation with human oversight. This module focuses on human-in-the-loop (HITL) patterns, approval workflows, and controlled interruptions using LangGraph’s execution hooks. You’ll explore time-travel debugging, execution logs, and snapshot-based branch analysis to inspect and resume complex pipelines. Through hands-on demonstrations, you’ll build planner–executor workflows and multi-stage task chains, gaining the skills to debug, audit, and govern agent behavior

What's included

13 videos4 readings4 assignments

13 videos•Total 79 minutes
  • Human Approval Workflow Patterns•6 minutes
  • Demonstration: Implementing HITL Approval and State Editing•7 minutes
  • Demonstration: Designing a Multi-Stage Approval Workflow - I•6 minutes
  • Demonstration: Designing a Multi-Stage Approval Workflow - II•7 minutes
  • Time-Travel Debugging and Snapshot Analysis•4 minutes
  • Demonstration: Using Execution Log and Resuming from Checkpoints•7 minutes
  • Demonstration: Performing Branch Analysis with Snapshots - I•6 minutes
  • Demonstration: Performing Branch Analysis with Snapshots - II•5 minutes
  • Planner & Executor Task Model•7 minutes
  • Demonstration: Creating a Planner Node with a Structured Executor - I•7 minutes
  • Demonstration: Creating a Planner Node with a Structured Executor - II•7 minutes
  • Demonstration: Building Multi-Step Task Chains - I•6 minutes
  • Demonstration: Building Multi-Step Task Chains - II•4 minutes
4 readings•Total 60 minutes
  • Human Oversight Through Middleware•15 minutes
  • Failure Patterns in Long-Running Agent Workflows•15 minutes
  • Trust, Explainability, and Human Confidence in Agents•15 minutes
  • Module Summary: Multi-Step Task Planning and Execution•15 minutes
4 assignments•Total 33 minutes
  • Practice Assignment: Human-in-the-Loop (HITL) Agent Workflows•6 minutes
  • Practice Assignment: Debugging Pipelines and Time-Travel Analysis•6 minutes
  • Practice Assignment: Multi-Step Task Planning and Execution•6 minutes
  • Knowledge Check: Multi-Step Task Planning and Execution•15 minutes

Dive into advanced multi-agent system design using LangGraph’s orchestration capabilities. This module explores supervisor–worker architectures, inter-agent communication, and message-passing models for distributed reasoning. You’ll design debate agents that reach consensus, build modular multi-agent subgraphs, and coordinate complex workflows across specialized agents.

What's included

11 videos4 readings4 assignments

11 videos•Total 62 minutes
  • Multi-Agent Roles and Communication Models•6 minutes
  • Demonstration: Implementing a Supervisor Node and Worker Agents - I•7 minutes
  • Demonstration: Implementing a Supervisor Node and Worker Agents - II•4 minutes
  • Demonstration: Message Passing Across Agent Nodes - I•6 minutes
  • Demonstration: Message Passing Across Agent Nodes - II•5 minutes
  • Models for Debate, Consensus, and Opinion Aggregation•5 minutes
  • Demonstration: Designing Debate Agents with Consensus Voting•8 minutes
  • Modular Subgraph Architecture•5 minutes
  • Subgraph Communication and Message Passing•5 minutes
  • Demonstration: Building a Multi-Agent Subgraph Workflow - I•5 minutes
  • Demonstration: Building a Multi-Agent Subgraph Workflow - II•7 minutes
4 readings•Total 60 minutes
  • Designing Supervisor–Worker Agent Systems with LangGraph•15 minutes
  • Consensus Modeling Techniques•15 minutes
  • Building Distributed Agent Workflows Using Subgraphs•15 minutes
  • Module Summary: Multi-Agent Orchestration and Distributed Reasoning•15 minutes
4 assignments•Total 33 minutes
  • Practice Assignment: Supervisor–Worker Architectures•6 minutes
  • Practice Assignment: Debate Agents and Consensus-Based Reasoning•6 minutes
  • Practice Assignment: Multi-Agent Subgraphs and Distributed Workflows•6 minutes
  • Knowledge Check: Multi-Agent Orchestration and Distributed Reasoning•15 minutes

This final section is designed to assess your mastery of building stateful and multi-agent systems with LangGraph. You’ll apply everything you’ve learned in a comprehensive practice project, designing a multi-agent research assistant that integrates state management, human-in-the-loop controls, debugging, and orchestration patterns.

What's included

1 video1 reading2 assignments1 discussion prompt

1 video•Total 3 minutes
  • Course Summary•3 minutes
1 reading•Total 30 minutes
  • Practice Project: Building a Stateful Multi-Agent Research Assistant•30 minutes
2 assignments•Total 60 minutes
  • End Course Knowledge Check: Building Stateful & Multi-Agent Systems with LangGraph•30 minutes
  • Designing a Stateful, Multi-Agent Workflow System with LangGraph•30 minutes
1 discussion prompt•Total 5 minutes
  • Describe Your Learning Journey•5 minutes

Earn a career certificate

Add this credential to your LinkedIn profile, resume, or CV. Share it on social media and in your performance review.

Instructor

Edureka
203 Courses•185,285 learners

Why people choose Coursera for their career

👁 Image

Felipe M.

Learner since 2018
"To be able to take courses at my own pace and rhythm has been an amazing experience. I can learn whenever it fits my schedule and mood."
👁 Image

Jennifer J.

Learner since 2020
"I directly applied the concepts and skills I learned from my courses to an exciting new project at work."
👁 Image

Larry W.

Learner since 2021
"When I need courses on topics that my university doesn't offer, Coursera is one of the best places to go."
👁 Image

Chaitanya A.

"Learning isn't just about being better at your job: it's so much more than that. Coursera allows me to learn without limits."

Frequently asked questions

This course is designed for AI engineers, backend developers, and system architects who want to build stateful and multi-agent systems using LangGraph. Learners with Python experience and basic knowledge of LLMs or agent concepts will benefit most.

You will learn how to design stateful agent workflows, manage execution state, implement checkpointing and recovery, debug long-running pipelines, and orchestrate multi-agent systems using LangGraph.

The course uses LangGraph, Python, modern LLM APIs, and agent orchestration patterns. You’ll work with typed state objects, reducers, checkpoints, and multi-agent communication models.

No prior LangGraph experience is required. Familiarity with Python and basic agent or LLM concepts is recommended to follow the hands-on workflow demonstrations.

Yes. The course includes hands-on demos, practice assignments, and role-play exercises where you build, debug, and govern stateful and multi-agent workflows.

You’ll learn to debug agent workflows using execution logs, snapshots, checkpoints, and time-travel analysis, and apply recovery strategies for long-running tasks.

Yes. The course covers approval workflows, interrupts, state inspection, and controlled execution to balance automation with human oversight.

Yes. You’ll design supervisor–worker systems, debate agents, consensus-based reasoning models, and distributed workflows using modular subgraphs.

The course is structured to be completed in approximately 4 weeks, with a recommended pace of 3–4 hours per week. You can learn at your own pace.

Unlike single-agent courses, this program focuses on stateful execution, debugging, governance, and multi-agent coordination using LangGraph’s graph-based architecture.

You will design a complete stateful, multi-agent research assistant that integrates state management, debugging, human oversight, and agent orchestration.

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.

When you enroll in the course, you get access to all of the courses in the Specialization, 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.

Yes. In select learning programs, you can apply for financial aid or a scholarship if you can’t afford the enrollment fee. If fin aid or scholarship is available for your learning program selection, you’ll find a link to apply on the description page.

Financial aid available,

¹ Some assignments in this course are AI-graded. For these assignments, your data will be used in accordance with Coursera's Privacy Notice.