Building Multi-Agentic AI Workflows on AWS Bedrock from Udemy

Do you want to harness the power of multi-agentic workflows to create cutting-edge AI applications—and deploy them at scale? This course is your gateway to building a fully operational, production-ready travel planner on AWS Bedrock, where multiple agents collaborate to deliver personalized, real-time recommendations. You’ll see how Supervisor Agents coordinate the flow of tasks, while Collaborator and Helper Agents do the heavy lifting—making database lookups, handling API calls, and processing travel preferences on your behalf. By structuring your AI in this agent-centric way, you’ll develop a scalable, modular system that adapts smoothly to complex, real-world scenarios.

We begin with the fundamentals of multi-agentic design—when to break tasks into specialized agents, how to handle inter-agent communication, and ensuring seamless collaboration for lightning-fast responses. Next, we’ll dive into AWS Bedrock’s Large Language Models (LLMs), showcasing how to customize prompt templates, override default parameters, and optimize your AI’s output for user queries. You’ll learn how to store key travel data in Amazon S3 and build a serverless application layer using AWS Lambda functions—Action Groups—to keep your AI workflow lightweight and cost-effective. Finally, we’ll demonstrate how to go production-ready by deploying via AWS API Gateway, providing a robust interface that can serve live requests from anywhere in the world with built-in scalability and security.

By the end of this course, you’ll have a production-grade, multi-agentic application capable of automatically looking up database records, making API requests, and delivering dynamic travel recommendations. Whether you’re an aspiring AI developer or a seasoned engineer, you’ll gain the hands-on skills to orchestrate Supervisor, Collaborator, and Helper Agents for real-world, enterprise-scale solutions. Join us and start building the next generation of AI with AWS Bedrock—all in a fully production-ready environment.

What's inside

Learning objectives

Understand and implement multi-agent workflows
Deploy multi-agent workflows with aws- using bedrock, lambdas, api gateway, s3 and many more
Leverage aws bedrock for llms
Implement multi-agent collaboration
Deploy production ai systems – set up a scalable ai architecture using aws lambda and api gateway.
Create action groups in aws lambda – build and manage action groups for ai decision-making in serverless environments.
Build ai-powered travel agents – design an intelligent travel assistant that can provide accommodation and restaurant recommendations.
Implement api gateway for external access – expose your ai travel agent to the web using aws api gateway.

Optimize ai requests with api rate limits – learn how to manage api request limits and prevent excessive usage costs.
Implement logging and monitoring – track ai model performance and monitor api usage with aws cloudwatch.
Understand the role of supervisor agents – learn how supervisor agents manage and coordinate tasks efficiently.
Deploy an end-to-end ai system – take your travel agent from concept to production in a real-world aws environment.
Fine-tune aws bedrock llm responses – adjust system parameters to improve the accuracy and relevance of travel recommendations.
Design scalable serverless applications – learn best practices for scaling ai-driven serverless applications in aws.
Show more
Show less

Understand and implement multi-agent workflows
Deploy multi-agent workflows with aws- using bedrock, lambdas, api gateway, s3 and many more
Leverage aws bedrock for llms
Implement multi-agent collaboration
Deploy production ai systems – set up a scalable ai architecture using aws lambda and api gateway.
Create action groups in aws lambda – build and manage action groups for ai decision-making in serverless environments.
Build ai-powered travel agents – design an intelligent travel assistant that can provide accommodation and restaurant recommendations.
Implement api gateway for external access – expose your ai travel agent to the web using aws api gateway.
Optimize ai requests with api rate limits – learn how to manage api request limits and prevent excessive usage costs.
Implement logging and monitoring – track ai model performance and monitor api usage with aws cloudwatch.
Understand the role of supervisor agents – learn how supervisor agents manage and coordinate tasks efficiently.
Deploy an end-to-end ai system – take your travel agent from concept to production in a real-world aws environment.
Fine-tune aws bedrock llm responses – adjust system parameters to improve the accuracy and relevance of travel recommendations.
Design scalable serverless applications – learn best practices for scaling ai-driven serverless applications in aws.
Show more
Show less

Syllabus

Setting Up Our AWS Account

Introduction

What We Are Building Part 1

What We Are Building Part 2

Traffic lights

Read about what's good

what should give you pause

and possible dealbreakers

Provides hands-on experience orchestrating Supervisor, Collaborator, and Helper Agents, which is essential for real-world, enterprise-scale AI solutions

Covers deploying via AWS API Gateway, which provides a robust interface that can serve live requests from anywhere in the world with built-in scalability and security

Explores AWS Bedrock's Large Language Models (LLMs), showcasing how to customize prompt templates and optimize AI output, which is crucial for tailoring AI to specific user needs

Requires familiarity with AWS services like Bedrock, Lambda, API Gateway, and S3, which may necessitate prior experience or additional learning for those new to the AWS ecosystem

Focuses on building a travel planner application, which may limit its direct applicability to other domains without adapting the learned principles and techniques

Relies heavily on AWS-specific tools and services, which may not be transferable to other cloud platforms or environments without significant modifications

Reviews summary

Hands-on aws multi-agent ai workflows

Students say this course provides practical, hands-on experience building multi-agent AI workflows on AWS. A major highlight is building a production-ready travel planner using services like AWS Bedrock Agents, Lambda, and API Gateway. While the course effectively teaches agent collaboration concepts and production deployment, some learners found the initial AWS setup and permission configuration challenging. It is noted that some prior familiarity with AWS services can be helpful for a smoother experience. Overall, students appreciate the real-world application and the focus on building a deployable system.

Explains multi-agent architecture well.

"The course clarifies the concepts of supervisor and collaborator agents."

"Helped me understand how to structure multi-agent workflows."

"I now grasp the fundamentals of agent collaboration and design."

Covers deploying via API Gateway.

"Appreciate the focus on deploying the agent workflow to production."

"The section on API Gateway for external access was very valuable."

"Learning how to deploy the system for real-world use was a highlight."

Covers Bedrock, Lambda, API Gateway use.

"Learned a ton about integrating Bedrock Agents with Lambda and API Gateway."

"The coverage of specific AWS services like S3 and CloudWatch was useful."

"Gained practical experience with Bedrock Agents and their interaction with serverless functions."

Building the travel agent was key.

"The real-world application of building a travel planner was the best part."

"Building the end-to-end travel agent really solidified my understanding."

"Loved building the project; it brought all the concepts together."

Some prior AWS/coding helpful.

"Felt that some prior AWS experience would have been beneficial."

"The course assumes a certain level of comfort with AWS console and services."

"Recommend having basic Python and AWS knowledge before starting."

AWS account setup can be tricky.

"Getting the AWS account configured correctly was a significant hurdle."

"Ran into issues with IAM permissions and service quotas initially."

"Be prepared for some AWS setup challenges before diving into Bedrock."

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 Building Multi-Agentic AI Workflows on AWS Bedrock with these activities:

Review AWS Fundamentals

Show steps

Solidify your understanding of core AWS concepts like IAM, S3, Lambda, and API Gateway to better grasp the course's architecture and deployment strategies.

Show steps

Review AWS documentation on IAM roles and policies.
Practice creating and configuring S3 buckets.
Deploy a simple Lambda function using the AWS console.

Read 'AWS Certified Cloud Practitioner Study Guide'

Show steps

Gain a foundational understanding of AWS services and terminology, which will help you navigate the course material more effectively.

View AWS Certified Cloud Practitioner Study Guide... on Amazon

Show steps

Read the chapters covering IAM, S3, Lambda, and API Gateway.
Complete the practice questions at the end of each chapter.

Build a Simple Serverless API

Show steps

Practice deploying a basic serverless API using AWS Lambda and API Gateway to gain hands-on experience with the technologies used in the course.

Show steps

Create a Lambda function that returns a simple JSON response.
Set up an API Gateway endpoint to trigger the Lambda function.
Test the API endpoint using Postman or a similar tool.

Four other activities

Expand to see all activities and additional details

Show all seven activities

Read 'Building Serverless Python Web Services with Zappa'

Show steps

Deepen your understanding of serverless deployment strategies and best practices, which are essential for building scalable and cost-effective AI applications.

View Hands-on Serverless Computing with Go on Amazon

Show steps

Read the chapters covering Lambda deployment and API Gateway integration.
Experiment with deploying a simple Python application using Zappa.

Document the Multi-Agent Workflow

Show steps

Create a detailed diagram and written explanation of the multi-agent workflow you built in the course to reinforce your understanding of the system's architecture and interactions.

Show steps

Create a diagram illustrating the flow of data and interactions between agents.
Write a detailed explanation of each agent's role and responsibilities.
Document the API endpoints and data formats used for communication.

Contribute to an Open-Source AI Project

Show steps

Apply your knowledge of multi-agent systems and AWS Bedrock by contributing to an open-source project related to AI or cloud computing.

Show steps

Find an open-source project that aligns with your interests and skills.
Identify a bug or feature request that you can contribute to.
Submit a pull request with your changes.

Mentor Junior Developers on AWS Bedrock

Show steps

Reinforce your understanding of AWS Bedrock and multi-agent systems by mentoring junior developers or students who are new to the technology.

Show steps

Offer to help junior developers with their AWS Bedrock projects.
Answer questions on online forums or communities.
Create tutorials or blog posts to share your knowledge.

Career center

Learners who complete Building Multi-Agentic AI Workflows on AWS Bedrock will develop knowledge and skills that may be useful to these careers:

Cloud Solutions Architect

A Cloud Solutions Architect designs and implements cloud computing solutions. This course directly aligns with the responsibilities of a Cloud Solutions Architect by teaching how to deploy multi-agentic workflows on AWS. A Cloud Solutions Architect can benefit from the practical demonstrations of using AWS Bedrock, Lambda functions, and API Gateway to create scalable AI applications. Furthermore, the focus on serverless architecture and cost optimization provides crucial skills for designing efficient and robust cloud-based AI solutions. This course helps a Cloud Solutions Architect build a foundation for deploying end-to-end AI systems in a real-world AWS environment.

See salaries and explore the career path for Cloud Solutions Architect

Solutions Architect

A Solutions Architect designs and oversees the implementation of technology solutions. This course is directly relevant to a Solutions Architect as it demonstrates how to build and deploy multi-agentic AI workflows using AWS Bedrock. A Solutions Architect will find the practical examples of using AWS Lambda, API Gateway, and S3 to create scalable AI applications extremely valuable. The course also emphasizes the importance of serverless architecture and cost optimization, which are essential considerations when designing efficient cloud-based solutions. This course offers insights into deploying end-to-end AI systems.

See salaries and explore the career path for Solutions Architect

AI Application Developer

An AI Application Developer builds and maintains AI-powered applications. This course helps an AI Application Developer learn to construct multi-agentic workflows using AWS Bedrock. The course teaches how to create collaboration among agents, which is useful for designing scalable and modular AI systems. It also dives into customizing prompt templates and optimizing the AI's output for user queries using AWS Bedrock’s Large Language Models. Because it provides insights into serverless application layers using AWS Lambda functions and deploying via AWS API Gateway, this course offers practical knowledge for developing and deploying AI applications.

See salaries and explore the career path for AI Application Developer

Software Engineer

A Software Engineer designs and develops software applications. This course is useful as it demonstrates how to build and deploy AI-powered applications using AWS Bedrock. A Software Engineer can learn how to structure AI in an agent-centric way, creating scalable and modular systems. The course provides hands-on experience with AWS Lambda functions and API Gateway, which are essential components for developing robust, cloud-based applications. By understanding how to orchestrate Supervisor, Collaborator, and Helper Agents, a Software Engineer can build more complex and adaptive AI solutions.

See salaries and explore the career path for Software Engineer

Cloud Engineer

A Cloud Engineer implements, manages, and supports cloud computing environments. This course helps a Cloud Engineer learn about deploying multi-agentic AI workflows on AWS Bedrock. The course includes instruction on leveraging AWS Lambda, API Gateway, and S3, enabling a Cloud Engineer to implement scalable and cost-effective AI solutions. A Cloud Engineer may find the focus on serverless architecture and production-ready environments practical for streamlining cloud deployments. The skills acquired during this course may be relevant to automating and optimizing cloud-based AI systems.

See salaries and explore the career path for Cloud Engineer

DevOps Engineer

A DevOps Engineer automates and streamlines software development and deployment processes. This course assists a DevOps Engineer in deploying multi-agentic AI workflows on AWS. The course emphasizes using AWS Lambda, API Gateway, and S3 to build scalable AI solutions. A DevOps Engineer can gain practical experience in setting up CI/CD pipelines for AI applications, managing API request limits, and implementing logging and monitoring. Learning how to deploy via AWS API Gateway, a DevOps Engineer can enhance the deployment process.

See salaries and explore the career path for DevOps Engineer

AI Consultant

An AI Consultant advises organizations on how to implement AI solutions. This course provides an AI Consultant with valuable insights into building and deploying multi-agentic AI workflows on AWS. The course helps develop an understanding of how Supervisor Agents coordinate tasks, how to handle inter-agent communication, and how to ensure collaboration. The course's focus on practical implementation and real-world deployment scenarios equips an AI Consultant with the knowledge to guide clients in creating scalable, cost-effective AI solutions. An AI Consultant may find the emphasis on production-ready environments, AWS Lambda, and API Gateway makes this course worthwhile.

See salaries and explore the career path for AI Consultant

Backend Developer

A Backend Developer is responsible for the server-side logic and databases of applications. This course can help a Backend Developer to enhance their skills in building scalable and efficient AI-driven applications. The course shows how to use AWS Lambda functions and API Gateway to create serverless application layers. A Backend Developer can learn to build scalable, modular systems by structuring AI in an agent-centric way. This course demonstrates how to store key data in Amazon S3, which can be beneficial for optimizing data storage and retrieval.

See salaries and explore the career path for Backend Developer

Technical Lead

A Technical Lead guides and mentors a team of software developers. This course is helpful for a Technical Lead who wants to guide their team in building and deploying multi-agentic AI workflows on AWS Bedrock. This course demonstrates how to create collaboration among agents, which is useful for designing scalable and modular AI systems. A Technical Lead may find the insights into the architecture of multi-agent systems, the use of AWS Lambda and API Gateway, and the optimization of AI requests useful for guiding a team.

See salaries and explore the career path for Technical Lead

AI Product Manager

An AI Product Manager oversees the strategy, roadmap, and execution of AI-powered products. This course provides an AI Product Manager with a deeper understanding of the technical aspects of building and deploying multi-agentic AI workflows on AWS Bedrock. An AI Product Manager may find the insights into system architecture, agent collaboration, and scalability useful for making informed decisions about product development. The course provides a practical perspective on how to create production-ready AI solutions, which can inform product strategy and roadmap.

See salaries and explore the career path for AI Product Manager

Machine Learning Engineer

A Machine Learning Engineer develops, tests, and deploys machine learning models. This course highlights AWS Bedrock and helps a Machine Learning Engineer learn to build multi-agentic workflows, which are useful for creating modular AI systems. This course may be useful for understanding how to customize prompt templates and optimize AI output. A Machine Learning Engineer may find the techniques for storing data in Amazon S3, building serverless applications, and deploying via AWS API Gateway particularly useful, as they align with deploying models in a scalable environment.

See salaries and explore the career path for Machine Learning Engineer

Data Engineer

A Data Engineer builds and maintains the infrastructure for data storage and processing. This course provides a Data Engineer with the skills to deploy and manage AI-driven applications on AWS. The course helps a Data Engineer learn how to store data in Amazon S3, build serverless application layers using AWS Lambda functions, and deploy via AWS API Gateway. The course may also be useful for understanding how to ensure seamless collaboration among agents for lightning-fast responses. A data engineer can play a role in building AI.

See salaries and explore the career path for Data Engineer

Data Scientist

A Data Scientist analyzes data and develops machine learning models. While this course focuses on deploying AI solutions, a Data Scientist may find the sections on customizing prompt templates and optimizing AI output with AWS Bedrock useful. The course demonstrates how to build serverless application layers using AWS Lambda functions, which can be helpful for integrating models into scalable applications. A Data Scientist may find the deployment via AWS API Gateway information beneficial for understanding how to make models accessible.

See salaries and explore the career path for Data Scientist

CTO

A Chief Technology Officer is responsible for a company's overall technology strategy and direction. This course may provide the CTO with a practical overview of deploying AI solutions on AWS Bedrock. A CTO may be able to formulate strategy based on the scalable and cost-effective AI solutions utilizing AWS Lambda, API Gateway, and S3. Moreover, knowledge gained may be useful for optimizing data storage and retrieval and ensuring seamless collaboration among agents.

See salaries and explore the career path for CTO

AI Research Scientist

An AI Research Scientist conducts research to advance the field of artificial intelligence. While this course focuses on the deployment of multi-agent systems, the fundamental knowledge of AWS Bedrock may be helpful. Also, the concepts of Supervisor, Collaborator, and Helper Agents may be useful for designing theoretical AI systems. While this course is not directly focused on AI research, it may provide a practical context for theoretical work.

See salaries and explore the career path for AI Research Scientist

Reading list

We've selected two 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 Building Multi-Agentic AI Workflows on AWS Bedrock.

AWS Certified Cloud Practitioner Study Guide with...

Save

Provides a comprehensive overview of AWS cloud services and concepts, making it an excellent resource for those new to the AWS ecosystem. It covers the fundamental knowledge required to understand the architecture and services used in the course. While not directly focused on multi-agent systems, it provides essential background knowledge. This book is commonly used as a study guide for the AWS Certified Cloud Practitioner exam.

AWS Certified Cloud Practitioner Study Guide with...

Paperback

$$$

Hands-on Serverless Computing with Go

Save

Provides a practical guide to building serverless web services using Python and Zappa, which can be helpful for understanding the serverless architecture used in the course. It covers topics such as deploying Python applications to AWS Lambda and API Gateway. While the course uses AWS Bedrock, the underlying principles of serverless deployment are similar. This book is valuable as additional reading to deepen your understanding of serverless technologies.

Hands-on Serverless Computing with Go

Paperback

Check price

Hands-on Serverless Computing with Go

Kindle Edition

Check price

Building Multi-Agentic AI Workflows on AWS Bedrock

What's inside

Learning objectives

Syllabus

Traffic lights

Save this course

Reviews summary

Hands-on aws multi-agent ai workflows

Activities

Career center

Reading list

Share

Similar courses