VOOZH about

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

⇱ Building Multi-Agent Systems using LangGraph and Autogen | Coursera

Building Multi-Agent Systems using LangGraph and Autogen

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

Building Multi-Agent Systems using LangGraph and Autogen

Instructor: Edureka

Included with

Ask Coursera

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

Recommended experience

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

Recommended experience

8 hours to complete
Flexible schedule
Learn at your own pace

What you'll learn

  • Design and build multi-agent systems that reason, plan, and collaborate on shared goals.

  • Implement communication and coordination strategies using LangGraph and Autogen.

  • Evaluate system performance through structured tasks and adaptive reasoning loops.

  • Optimize multi-agent workflows for reliability, scalability, and autonomous execution.

Details to know

Shareable certificate

Add to your LinkedIn profile

Assessments

14 assignments¹

AI Graded see disclaimer
Taught in English

Build your subject-matter expertise

This course is part of the Autonomous AI Agent Systems and Orchestration 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 course introduces the essentials of multi-agent AI systems using LangGraph and Autogen, combining architectural understanding with hands-on development of intelligent, collaborative agents. Designed to give you both conceptual foundations and practical experience, it explores how agent-based systems are redefining automation, decision-making, and AI-powered problem-solving.

Through guided lessons and coding demonstrations, you’ll learn how to construct multiple AI agents that communicate, plan, and execute tasks autonomously. You will work with LangGraph to structure agent workflows and use Autogen to enable dynamic interaction between agents. The course covers key topics such as agent communication, reasoning loops, task decomposition, and coordination for real-world applications like research, analysis, and workflow management. By the end of this course, you will be able to: • Understand the architecture, behavior, and lifecycle of multi-agent systems. • Build intelligent agents using LangGraph and Autogen for collaborative problem-solving. • Implement reasoning and communication strategies for effective task orchestration. • Evaluate and optimize multi-agent performance for scalability and reliability. This course is ideal for developers, data scientists, and AI practitioners who want to learn how to design and deploy intelligent multi-agent systems that can perform complex workflows autonomously. A basic understanding of Python programming and familiarity with machine learning or AI concepts will be helpful, but no prior experience with LangGraph or Autogen is required. Join us to explore the future of autonomous AI systems and learn how to build, coordinate, and optimize agents that think, collaborate, and act intelligently.

This module explores how real-time data and advanced tooling empower autonomous agents to make dynamic financial decisions. You’ll learn to integrate live data sources, validate inputs, and build multi-tool ensembles for complex reasoning. Finally, you’ll apply RAG techniques to index, query, and analyze financial data in real time.

What's included

12 videos5 readings4 assignments

12 videos•Total 55 minutes
  • Specialization Introduction•5 minutes
  • Course Introduction•2 minutes
  • From Static Content to Real-Time Financial Decisioning•5 minutes
  • Hands-on: The Observer Agent•7 minutes
  • Hands-on: Integrating Real-Time Data Sources•4 minutes
  • Hands-on: Data Validation and Pre-Processing for LLMs•6 minutes
  • Hands-on: Building the Fundamental Analysis Tool•4 minutes
  • Hands-on: Creating the Execution Tool with Strict Schema Guardrails•4 minutes
  • Hands-on: Using Multiple Tools in a Single Reasoning Step•7 minutes
  • Hands-on: RAG for Financial Knowledge - Indexing SEC Filings and Reports•5 minutes
  • Hands-on: Handling Numerical Data in RAG•3 minutes
  • Hands-on: The Research Agent •3 minutes
5 readings•Total 50 minutes
  • Course Outline: Building Multi-Agent Systems using LangGraph and Autogen•10 minutes
  • Foundations of Real-Time Agents•10 minutes
  • Tool Ensemble Design•10 minutes
  • RAG for Financial Data•10 minutes
  • Real-Time Data and Advanced Tooling•10 minutes
4 assignments•Total 33 minutes
  • Practice Quiz: Foundations of Real-Time Agents•6 minutes
  • Practice Quiz: Tool Ensemble Design•6 minutes
  • Practice Quiz: RAG for Financial Data•6 minutes
  • Knowledge Check: Real-Time Data and Advanced Tooling•15 minutes

This module delves into multi-agent collaboration, where specialized agents work together to analyze data and make informed decisions. You’ll design coordinated agent roles and communication protocols for seamless teamwork. The module culminates in building a full collaborative workflow that generates trading signals and balances investment risk.

What's included

10 videos4 readings4 assignments

10 videos•Total 55 minutes
  • Beyond Single Agent: Principles of Collaborative Agent Teams•5 minutes
  • Hands-on: Designing Agent Roles - Researcher, Analyst, and Portfolio Manager•6 minutes
  • Hands-on: Setting Up the Orchestrator Agent•4 minutes
  • Hands-on: Communication Protocols Enabling Agents to Pass Structured Messages•6 minutes
  • Hands-on: The Analyst Agent's Role•4 minutes
  • Hands-on: Transitions Between Different Agents•6 minutes
  • Hands-on: Implementing a Consensus Mechanism for Investment Decisions•5 minutes
  • Hands-on: Generating a Trading Signal•5 minutes
  • Hands-on: The Full Collaborative Analysis •6 minutes
  • Hands-on: Integrating Autogen and Gemini in Existing Workflow•7 minutes
4 readings•Total 40 minutes
  • The Multi-Agent Architecture•10 minutes
  • Collaborative Analysis Workflow•10 minutes
  • Signal Generation and Risk•10 minutes
  • Multi-Agent Collaboration and Decision-Making•10 minutes
4 assignments•Total 33 minutes
  • Practice Quiz: The Multi-Agent Architecture•6 minutes
  • Practice Quiz: Collaborative Analysis Workflow•6 minutes
  • Practice Quiz: Signal Generation and Risk•6 minutes
  • Knowledge Check: Multi-Agent Collaboration and Decision-Making•15 minutes

This module focuses on building secure, auditable, and scalable AI agent systems for real-world deployment. You’ll implement guardrails, logging, and fail-safes to ensure responsible financial execution. Finally, you’ll package, deploy, and scale your multi-agent trading system using production-ready infrastructure.

What's included

10 videos4 readings4 assignments

10 videos•Total 57 minutes
  • The Irrevocable Action Problem: Guardrails for Financial Execution•5 minutes
  • Hands-on: Implementing Pre-Execution Checks•6 minutes
  • LLM Jailbreak Prevention: Techniques to Stop Unauthorized Actions•5 minutes
  • Hands-on: Logging Every Thought and Action for Compliance•6 minutes
  • Hands-on: The Emergency Stop Node•4 minutes
  • Hands-on: Forcing Decisions on Strict Market Deadlines•5 minutes
  • Hands-on: Integrating the Final Review Queue for Execution•7 minutes
  • Hands-on: Packaging the Multi-Agent System for Containerization•7 minutes
  • Hands-on: Deploying the Autonomous Trading Agent API•8 minutes
  • Scaling Real-Time Systems and Advanced Portfolio Management•5 minutes
4 readings•Total 40 minutes
  • Production-Grade Security & Guardrails•10 minutes
  • Advanced LangGraph Control•10 minutes
  • Deployment and Scaling •10 minutes
  • Security, Auditability, and Deployment•10 minutes
4 assignments•Total 33 minutes
  • Practice Quiz: Production-Grade Security & Guardrails•6 minutes
  • Practice Quiz: Advanced LangGraph Control•6 minutes
  • Practice Quiz: Deployment and Scaling•6 minutes
  • Knowledge Check: Security, Auditability, and Deployment•15 minutes

This module provides learners with an opportunity to synthesize their knowledge and demonstrate mastery of single-agent AI workflows. Learners will review key concepts from multi agent systems, , MCP and LangGraph orchestration. They will complete graded assessments, including scenario-based exercises and end-of-course knowledge checks, to apply their understanding in practical contexts. By the end of this module, learners will be able to confidently design, implement, and evaluate a fully functional single AI agent capable of reasoning, tool use, and executing grounded tasks.

What's included

1 video1 reading2 assignments

1 video•Total 2 minutes
  • Course Summary•2 minutes
1 reading•Total 30 minutes
  • Practice Project: Real-Time Multi-Agent Orchestrator•30 minutes
2 assignments•Total 60 minutes
  • End Course Knowledge Check: Building Multi Agent Systems using LangGraph and Autogen•30 minutes
  • Real-Time Financial Decisioning Agent - Scenario Assignment•30 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

Explore more from Software Development

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 aims to teach how to design, build, and deploy autonomous financial agents capable of real-time decision-making, collaborative reasoning, and secure execution within live trading or analysis environments.

A foundational understanding of Python, APIs, and basic AI or LLM concepts is recommended. Familiarity with financial data or market terminology helps but is not mandatory.

The course primarily uses LangGraph for agent orchestration, LLMs for reasoning and communication, RAG for financial data retrieval.

Unlike typical data analysis courses, this one focuses on autonomous decision systems — where multiple AI agents operate collaboratively, process real-time inputs, and make market-driven choices securely and audibly.

By the end of the course, learners will have built a multi-agent financial system capable of real-time data ingestion, collaborative analysis, signal generation, and safe deployment in production-like conditions.

Security is a key focus. Learners implement guardrails, pre-execution checks, audit logs, and jailbreak prevention mechanisms to ensure all agent actions are safe, compliant, and transparent.

Each module concludes with ungraded hands-on exercises and quizzes, followed by a graded module quiz assessing understanding of real-time tooling, multi-agent workflows, and deployment best practices

The course prepares learners for roles in AI-driven finance, algorithmic trading, autonomous analytics, and enterprise agent design, where AI systems must process dynamic data securely and collaboratively.

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.