AWS

Cloud

Introduction to Amazon Bedrock

Build real-world generative AI apps with Amazon Bedrock. Learn foundation models, prompt engineering, RAG, Agents, security, monitoring, and AWS integrations through hands-on labs, guided demos, practical projects, and a final capstone.

Alistair Sutherland

AWS consultant and Instructor

Fill this form to get a notification when course is released.

Enroll for Free

Subscribe Now

Enroll Now

Already Subscribed? Log in

Enroll in this Course

Lessons

Challenges

102

Topics

What you’ll learn

Our students work at..

Description

The Introduction to Amazon Bedrock course is designed to help learners build practical skills in developing generative AI applications using Amazon Bedrock. Tailored for cloud engineers, developers, solutions architects, AI practitioners, DevOps professionals, and technology enthusiasts, this course offers a comprehensive introduction to foundation models, prompt engineering, Retrieval-Augmented Generation (RAG), Bedrock Agents, and the broader Amazon Bedrock ecosystem. Through conceptual lessons, guided demonstrations, hands-on labs, practical projects, and real-world implementation scenarios, you'll learn how to build, deploy, secure, and monitor generative AI applications on AWS.

Throughout the course, you'll gain hands-on experience working with Amazon Bedrock, foundation models, Bedrock APIs, Bedrock Knowledge Bases, Bedrock Agents, AWS Lambda, Amazon S3, Amazon Lex, API Gateway, CloudWatch, IAM, and other AWS services commonly used in AI-powered solutions. You'll learn how to interact with foundation models, design effective prompts, implement text generation use cases, build RAG applications, integrate Bedrock with AWS services, apply responsible AI practices, secure AI workloads, and optimize performance and costs. The course culminates in practical application-building exercises and a final project that allows you to apply the concepts learned in the course in a realistic business scenario.

Course Modules & Learning Outcomes

Introduction to Amazon Bedrock

Build a strong foundation in Generative AI, Large Language Models (LLMs), and Amazon Bedrock. Learn how Bedrock is architected, explore supported foundation models, and understand how organizations can leverage managed AI services to accelerate application development.

Getting Started with Amazon Bedrock

Learn how to access and interact with Amazon Bedrock using the AWS Management Console, AWS CLI, APIs, and Python with Boto3. You'll explore inference profiles, understand how Bedrock APIs work, and gain practical experience invoking foundation models.

Foundation Models and Prompt Engineering

Understand the capabilities and use cases of various foundation models available through Bedrock. Learn the fundamentals of prompt engineering, prompt design best practices, and techniques for improving model responses and output quality.

Text Generation and Model Interaction

Explore how foundation models process requests through concepts such as tokens, context windows, and inference parameters. Gain hands-on experience generating text, controlling model behavior, and optimizing outputs for different use cases.

Practical Generative AI Applications

Implement common generative AI workloads including text summarization, question answering, sentiment analysis, and code generation. Learn how to evaluate outputs and select appropriate prompting techniques for different business requirements.

Integrating Amazon Bedrock With AWS Services

Learn how to build cloud-native AI solutions by integrating Bedrock with services such as Amazon S3, AWS Lambda, API Gateway, and Amazon Lex. You'll create end-to-end workflows that combine generative AI capabilities with AWS infrastructure.

Building Real-World Applications

Apply your skills by developing a marketing email generation application. You'll design the solution architecture, implement backend logic, connect Bedrock APIs, and build practical AI-powered workflows.

RAG With Bedrock Knowledge Bases

Learn how to extend foundation models with organizational knowledge using embeddings, vector stores, and retrieval workflows. Explore Bedrock Knowledge Bases and build a simple RAG application that delivers more accurate and context-aware responses.

Governance, Responsible AI, and Security

Understand the principles of ethical AI, data privacy, governance, and compliance. Learn how to implement Bedrock Guardrails, content filtering, fallback responses, IAM access controls, encryption, and network security for enterprise AI workloads.

Monitoring, Optimization, and Operations

Explore observability and operational best practices for generative AI applications. Learn how to use CloudWatch, analyze usage and performance metrics, troubleshoot issues, optimize costs, and maintain reliable AI services in production environments.

Bedrock Agents and Advanced Capabilities

Discover how Bedrock Agents enable foundation models to take actions and interact with external systems. You'll gain hands-on experience building agent-based workflows and explore advanced topics such as multimodal AI, conversational AI, release management strategies, and Bedrock AgentCore.

Final Project

Bring together the concepts learned throughout the course by designing and implementing a complete real-world generative AI application using Amazon Bedrock and AWS services.

Course Features

Hands-on labs and guided demonstrations using the AWS Console, CLI, APIs, and Python to build real-world AI solutions
Practical projects including a marketing email generation application and a comprehensive final project
Comprehensive introduction to Amazon Bedrock, foundation models, and generative AI application development on AWS
Practical coverage of prompt engineering, text generation, summarization, question answering, sentiment analysis, and code generation
Production-focused best practices covering security, governance, responsible AI, monitoring, cost optimization, Bedrock Agents, and advanced AI architectures

Who Should Enroll?

Developers looking to build generative AI applications using Amazon Bedrock
Cloud engineers and solutions architects interested in AI-powered application development on AWS
AI practitioners seeking hands-on experience with foundation models and prompt engineering
DevOps and platform engineers supporting AI workloads in cloud environments
Technology professionals interested in RAG, Bedrock Agents, and modern AI application architectures
Anyone looking to gain practical experience building, deploying, securing, and monitoring generative AI solutions on AWS

Build the practical skills needed to develop, integrate, secure, and operate generative AI applications using Amazon Bedrock while gaining hands-on experience with foundation models, prompt engineering, RAG architectures, Bedrock Agents, and production-ready AWS AI workflows.

About the instructor

Alistair is a seasoned AWS consultant and instructor with over 20 years of experience in the IT industry. He has worked across a wide range of sectors, from startups to global enterprises, bringing a deep understanding of real-world infrastructure and cloud challenges.

For the past two years, Alistair has been focused on helping enterprise retail banks productionize their SageMaker platforms—working hands-on with data scientists and platform teams to build scalable, reliable ML solutions. This practical experience translates directly into the course, ensuring learners gain insights grounded in reality, not just theory.

Known for his clear, structured teaching style, Alistair excels at breaking down complex topics so they’re accessible to everyone, regardless of background.

He holds multiple AWS certifications, including:

AWS Certified DevOps Engineer – Professional
AWS Certified Solutions Architect – Professional
AWS Certified Machine Learning – Specialty

No items found.

Course Content

Expand All

Introduction to Gen AI and LLMs

Topics

Lesson Content

Module Content

Course Introduction04:44

Gen AI and LLMs – Introduction - Part 109:55

Gen AI and LLMs – Introduction - Part 210:57

Gen AI and LLMs – Introduction - Part 309:22

How to Reach Out to KodeKloud and Engage with the Community

Introduction to Amazon Bedrock

Topics

Lesson Content

Module Content

Amazon Bedrock – Introduction - Part 110:59

Amazon Bedrock – Introduction - Part 211:37

Basic Bedrock Architecture - Part 111:28

Basic Bedrock Architecture - Part 212:00

Supported Foundation Models15:12

Getting Started With Amazon Bedrock

Topics

Lesson Content

Module Content

Accessing the Bedrock Console - Part 111:29

Accessing the Bedrock Console - Part 209:44

Lab: accessing the Amazon Bedrock console

Accessing Bedrock With Command Line - Part 110:23

Accessing Bedrock With Command Line - Part 210:28

Demo: Accessing Bedrock With Command Line - Part 310:22

Inference Profiles09:42

Bedrock API - Part 110:43

Bedrock API - Part 211:39

Demo: Bedrock API - Part 308:51

Lab: Accesing Bedrock with Python Boto3

Foundation Models in Amazon Bedrock

Topics

Lesson Content

Module Content

Available Models14:57

Lab: experiments with foundation models

Basic Concepts of Prompt Engineering

Topics

Lesson Content

Module Content

What Is a prompt?11:25

Components of a Prompt10:48

Lab: Using best practices for effective prompts

Introduction to Text Generation With Amazon Bedrock

Topics

Lesson Content

Module Content

Bedrock Playground and API – Demonstrations12:19

How Foundation Models Process Input

Topics

Lesson Content

Module Content

Understanding Tokens11:47

Understanding Context Window15:45

Controlling Model Parameters13:55

Lab: Experimenting with model input processing

Extract Insights Using Prompt Engineering

Topics

Lesson Content

Module Content

Demonstration of Prompt Engineering - Part 111:36

Demonstration of Prompt Engineering - Part 209:54

Lab: Practicing various prompt engineering techniques

Lab: Analyzing and improving model outputs

Working With Different Task Types

Topics

Lesson Content

Module Content

Exploring Text Summarization08:35

Implementing Question Answering10:12

Obtaining Sentiment Analysis09:58

Understanding Code Generation14:35

Lab: implementing summarization, Q&A, and sentiment

Integrating Amazon Bedrock With Other AWS Services

Topics

Lesson Content

Module Content

Integrating Bedrock With Amazon S3 - Part 110:20

Integrating Bedrock With Amazon S3 - Part 209:38

Lab: Using Bedrock with Amazon S3

Integrating Bedrock With AWS Lambda15:02

Lab: Combining Bedrock with AWS Lambda

Exposing Your Bedrock App Using API Gateway - Part 115:02

Exposing Your Bedrock App Using API Gateway - Part 212:10

Combining Bedrock With Amazon Lex15:26

Build a Marketing Email Generation Application

Topics

Lesson Content

Module Content

Application Development Requirements Marketing Email Generator04:08

Lab: Creating a practical application using Bedrock

Lab: Implementing user interfaces and backend logic

Introduction to Retrieval Augmentation With Bedrock Knowledge Bases

Topics

Lesson Content

Module Content

Extending a Model With Knowledge12:07

Embeddings and Vector Stores - Part 109:40

Embeddings and Vector Stores - Part 209:11

RAG End-to-End Workflow11:39

Bedrock Knowledge Bases – Introduction - Part 109:31

Bedrock Knowledge Bases – Introduction - Part 208:16

Bedrock Knowledge Bases – Introduction - Part 309:45

Lab: Building a simple RAG application

Best Practices and Optimization

Topics

Lesson Content

Module Content

Managing Costs and Optimizing Performance - Part 111:07

Managing Costs and Optimizing Performance - Part 208:25

Managing Costs and Optimizing Performance - Part 308:58

Managing Costs and Optimizing Performance - Part 409:20

Handling Errors, Troubleshooting, and Edge Cases - Part 111:20

Handling Errors, Troubleshooting, and Edge Cases - Part 210:26

Handling Errors, Troubleshooting, and Edge Cases - Part 308:49

Governance, Safety in Responsible AI

Topics

Lesson Content

Module Content

Ethical AI – Introduction - Part 108:19

Ethical AI – Introduction - Part 208:30

Data Privacy and Protection - Part 110:31

Data Privacy and Protection - Part 209:34

Compliance Features Including Guardrails - Part 109:01

Compliance Features Including Guardrails - Part 210:19

Compliance Features Including Guardrails - Part 307:28

Lab: Input filtering, content fltering, and fallback responses

Security

Topics

Lesson Content

Module Content

Controlling Access to Bedrock Using IAM - Part 109:33

Controlling Access to Bedrock Using IAM - Part 214:02

Controlling Access to Bedrock Using IAM - Part 311:09

Lab: Implementing restricted access with IAM

Ensuring Encryption in Transit - Part 108:31

Ensuring Encryption in Transit - Part 207:27

Integrating Bedrock With VPC13:23

Monitoring and Logging

Topics

Lesson Content

Module Content

Observability for Bedrock – What You Need05:31

Using Amazon CloudWatch With Bedrock - Part 109:42

Using Amazon CloudWatch With Bedrock - Part 209:05

Using Amazon CloudWatch With Bedrock - Part 310:28

Using Amazon CloudWatch With Bedrock - Part 405:16

Using Amazon CloudWatch With Bedrock - Part 510:09

Using Amazon CloudWatch With Bedrock - Part 608:06

Lab: Analyzing usage and performance metrics

Understanding and Optimizing Cost - Part 110:54

Understanding and Optimizing Cost - Part 207:03

Taking action with Bedrock Agents

Topics

Lesson Content

Module Content

Bedrock Agents – Introduction - Part 110:46

Bedrock Agents – Introduction - Part 207:24

Bedrock Agents – Introduction - Part 310:46

Managed Abstraction With Bedrock Agents - Part 108:58

Managed Abstraction With Bedrock Agents - Part 207:22

Managed Abstraction With Bedrock Agents - Part 308:19

Lab: Agent Connecting to SWAPI API

Comparison With MCP12:11

Final Project

Topics

Lesson Content

Module Content

Requirements for Final Project03:17

Lab: Design and implement a real-world application

Wrap Up

Topics

Lesson Content

Module Content

Wrap Up12:12

Frequently Asked Questions

Who are KodeKloud courses for?

KodeKloud courses are designed for learners at different skill levels, from beginners to experienced IT professionals looking to develop or strengthen their technical skills.

Do KodeKloud courses include hands-on practice?

Yes. Many KodeKloud courses include hands-on labs and practical exercises that let you apply what you learn in real-world environments.

Do I need any prior experience to take a KodeKloud course?

Prerequisites vary by course. Each course page provides information about the recommended knowledge or experience you may need before starting.

Can I learn at my own pace?

Yes. KodeKloud courses are designed for self paced learning, so you can learn according to your schedule and revisit lessons and practice activities as needed.

Can I access KodeKloud courses on mobile devices?

Yes. KodeKloud can be accessed through supported web browsers and mobile devices, allowing you to learn from different devices.

Do KodeKloud courses provide certificates?

Certificate availability depends on the course and your KodeKloud plan. Check the individual course page or your account for the applicable certificate details.

How long does it take to complete a KodeKloud course?

Course completion time varies depending on the course length, your prior experience, and how much time you spend on hands-on practice.

Can I practice while taking the course?

Yes. Courses that include hands-on labs allow you to practice concepts as you progress through the lessons.

How do I start learning a KodeKloud course?

Choose a course that matches your learning goals, review its requirements and curriculum, and select the available subscription option to start learning.

Fill this form to get a notification when course is released.