Skip to main content
CF

AWS Bootcamp: Build AI Apps with AWS Bedrock

15h 17m 44s
English
Paid

AWS Bootcamp: Build AI Apps with AWS Bedrock is a 135-lesson 15 hours 17 minutes self-paced course by Zero To Mastery. Immerse yourself in hands-on generative AI and learn to create scalable AI applications based on AWS Bedrock —a modern cloud platform for working with foundation models.

Course facts

Lessons
135
Duration
15 hours 17 minutes
Level
All levels
Language
English
Updated
Instructor
Zero To Mastery
Price
Premium

Immerse yourself in hands-on generative AI and learn to create scalable AI applications based on AWS Bedrock—a modern cloud platform for working with foundation models. The updated material is structured for better readability and will help you quickly understand key concepts and move on to developing real-world solutions.

What You Will Learn

Basics of AWS Bedrock and Generative AI

You will understand how the modern generative artificial intelligence ecosystem is structured and why AWS Bedrock has become one of the key tools for creating enterprise AI solutions. You will grasp the application architecture and the principles of using foundation models without managing the infrastructure yourself.

Large Language Models (LLM)

Study the capabilities of LLM, their limitations, and key application scenarios: text generation, coding, intelligent chat systems, document analysis, and workflow automation.

Text, Code, and Image Generation

Learn to apply various AWS Bedrock models to create content, automate programming, generate images, and develop multimodal applications.

Fine-Tuning and Reinforcement Fine-Tuning

Master strategies for model improvement through fine-tuning and feedback-based training. Learn to integrate these methods into real AI systems.

Prompt Management and Optimization

Practically learn to design, test, and optimize prompts to create predictable and stable AI solutions.

Intelligent Model Routing

Learn how to automatically select optimal models for various tasks, considering cost, performance, and quality.

Batch Data Processing and Automation

Master Batch Inference and other automation technologies for working with large datasets, document analysis, and repetitive business processes.

Image Generation

Get acquainted with diffusion models and create your own application for image generation for applied tasks.

Quality Assessment and AI Safety

Study model testing methods, quality analysis, error prevention, and ensuring the safe use of AI systems.

Deployment and Scaling of AI Applications

In practice, create serverless infrastructure based on AWS Lambda, API Gateway, S3, and Bedrock. Learn to deploy and scale production AI services.

Creation of Next-Generation AI Agents

Develop intelligent agents based on Bedrock AgentCore that can perform complex tasks, interact with tools, and operate in real scenarios.

AI Agent Memory

Master short-term and long-term memory mechanisms that allow agents to retain context, remember user preferences, and personalize interaction.

Guardrails and Responsible AI

Learn to apply Amazon Bedrock Guardrails for filtering undesirable content, risk management, and adhering to standards for responsible AI use.

Model Comparison and Selection

Understand the differences between foundation models from different providers and learn to choose the best solutions for specific tasks.

AWS Bedrock Quotas and Limits

Understand how quotas and limits work, learn to predict load and design resilient AI systems.

Inference Profiles and Marketplace Models

Master advanced AWS Bedrock capabilities—inference profiles, additional models from the Marketplace, and tools to increase application resilience.

Advanced Features of AWS Bedrock

Dive into tools and practices used in modern corporate AI systems that go beyond just using prompts.

Practical Projects

You will create six complete projects that will form a strong portfolio and help reinforce all acquired knowledge:

  • An AI system for document analysis and summarization;
  • A service for extracting key data and decisions from texts;
  • An application for generating text and software code;
  • An image generation system;
  • A multi-agent intelligent AI assistant;
  • A real-time voice AI agent based on AWS Bedrock Nova Sonic.

Each project includes the full development cycle: architecture, logic implementation, integration with AWS services, testing, and deployment.

Who This Course Is For

The course is suitable for:

  • Developers who want to master generative AI;
  • Cloud solution engineers and architects with AWS;
  • ML and Data Science specialists;
  • Technical leaders and AI enthusiasts;
  • Anyone who strives to create modern AI applications and integrate them into real business processes.

Learning Outcome

Upon completion of the course, you will be able to design, develop, and deploy full-fledged AI applications on AWS Bedrock, utilize modern foundation models, create intelligent agents, ensure model quality and safety, and integrate AI solutions into production environments.

Additional

Who teaches AWS Bootcamp: Build AI Apps with AWS Bedrock? Zero To Mastery

Zero To Mastery thumbnail

Zero To Mastery (ZTM) is a Toronto-based online coding academy founded by Andrei Neagoie, originally a senior developer at large Canadian tech firms before turning to teaching full-time. The academy's signature is the cohort-based bootcamp track combined with a deep self-paced course library, all aimed at career-changers and self-taught developers preparing to land software-engineering roles at top companies.

The instructor roster has grown well beyond Andrei to include other senior practitioners: Daniel Bourke (machine learning), Aleksa Tešić (DevOps), Jacinto Wong, and others. Courses cover the full software-engineering career path: web development with React and Next.js, Python, machine learning and deep learning, DevOps and cloud, system design, mobile, and the algorithm / data-structure interview prep that gates engineering jobs.

The CourseFlix listing under this source carries over 120 ZTM courses spanning that full range. Material is paid; ZTM itself runs on a monthly / annual membership model. The teaching style favours long-form, project-based courses where students build complete portfolio-quality applications rather than disconnected feature tutorials.

What lessons are included in AWS Bootcamp: Build AI Apps with AWS Bedrock?

This is a demo lesson (10:00 remaining)

You can watch up to 10 minutes for free. Subscribe to unlock all 135 lessons in this course and access 10,000+ hours of premium content across all courses.

View Pricing
0:00
/
#1: The AWS Bootcamp: Build AI Apps with AWS Bedrock
All Course Lessons (135)
#Lesson TitleDurationAccess
1
The AWS Bootcamp: Build AI Apps with AWS Bedrock Demo
01:56
2
Course Overview
08:45
3
Capstone Project 1: Building Multi Agentic Workflows
10:13
4
Capstone Project 2: Building Interruptible Voice Agents
06:57
5
Setting Up our AWS Account
05:25
6
Login to IAM User Account
04:24
7
Introduction to Bedrock Foundation Models
15:41
8
Deep Dive Into Inference Configurations
26:38
9
Inference Profiles, Model Catalog, Provisioned Throughput and More Theory
18:04
10
Prompt Management, Optimization, and More
18:51
11
Exploring the Playground in AWS Bedrock
16:20
12
Exploring Modal Providers, Modalities, API Invocation and Pricing
15:32
13
Quotas, Model Comparison, Guardrails, and More
27:34
14
Image Generation in the Playground with Diffusion Models
02:55
15
Setting Up the Code Generation Project
01:06
16
Coding our Lambda Function and Integrating with AWS Bedrock
17:52
17
Setting up API Gateway and our Serverless Stack
05:35
18
Testing our Live Endpoint
05:58
19
Creating our Boto3 Lambda Layer
02:24
20
Attaching our Lambda Layer to our Function
02:25
21
Testing our Bedrock Model
06:29
22
Verifying Final Output of Bedrock
02:25
23
Setting up our Lambda Function with Bedrock for Content Summarization
08:44
24
Finishing our Lambda Function for Meeting Summarisation
14:11
25
Creating new API Gateway Endpoint for this Lambda Function
02:16
26
Invoking our Serverless Meeting Notes Summarisation Endpoint
06:31
27
Analyzing the Final Results
01:40
28
Project Introduction
10:58
29
Stability AI Update Lecture
01:43
30
Setting up API Gateway Route (Serverless) for New Generative AI Model Invocation
01:07
31
Invoking our Stable Diffusion model for Image Generation
03:49
32
Analysing our Final Output
00:47
33
Set up Evaluation Job for Anthropic's Claude model
04:38
34
Evaluating our Results
05:26
35
Introduction to AWS Bedrock Knowledge Base
02:58
36
Retrieval Augmented Retrieval (RAG) Overview
06:41
37
Setting Up Our Own Knowledge Base - Part 1
08:09
38
Setting Up Our Own Knowledge Base - Part 2
00:51
39
Testing our Bedrock Knowledge Base with Antropic's Claude Model
07:21
40
Clean Up Resources
01:11
41
API Resources
00:43
42
A Little Cleanup and Congratulations!
03:17
43
Architecture Diagram of Our Multi Agentic Workflow
06:42
44
LLM Model Access, API Rate Limits, Quotas, and AWS Regions
07:48
45
Introduction to AWS Bedrock Agents
01:05
46
Creating the Restaurant Agent
17:34
47
Creating our AWS S3 Bucket To Store Our Data
04:05
48
Uploading Restaurant Data to AWS S3
00:49
49
Creating an Action Group For Our Restaurant Agent
13:02
50
Finishing Our Lambda Function for our Restaurant Agent
12:27
51
Testing Our Restaurant Agent
14:39
52
Setting Up the Accommodation Agent
08:46
53
Uploading Our Hotel and Airbnb Data to AWS S3
01:15
54
Creating The Lambda Function Action Group For The Accommodation Agent
17:41
55
Finishing Our Accommodation Agent
09:50
56
Testing the Accommodation Agent
08:21
57
Creating and Testing The Supervisor Agent
09:01
58
Explaining Agent Collaborators
04:42
59
Multi Agent UI Enhancement, Timing Agents
02:52
60
Serverless Invocation of the Supervisor Agent using AWS Lambda
11:52
61
Setting up AWS API Gateway to Deploy Our Worfklow Through the Internet
03:25
62
Testing Our Endpoint Through The Internet with Postman
05:15
63
Cleaning Up Resources
02:30
64
What is AWS Bedrock Agent Core
10:52
65
Accessing AgentCore via Sagemaker AI Setup
01:33
66
Finishing SagemakerAI Setup
02:54
67
Creating our Test Agent
14:52
68
Testing Our Agent
05:21
69
Configuring the AgentCore Runtime
09:10
70
Deploying the Agent to AgentCore
08:37
71
Tracing the Agent Logs in CloudWatch for Observability
15:47
72
Don't forget to shutdown the SagemakerAI Server
00:34
73
Session Management for Agents
07:52
74
Understanding AgentCore Sessions
05:57
75
Lifecycle Management for AgentCore Sessions
04:14
76
Cost Calculations for AgentCore Runtime
03:09
77
Understanding Short Term Memory
10:07
78
Short Term Memory Imports
07:54
79
Create the Resources for Short Term Memory
06:43
80
Verify Agent Memory Creation in the UI
00:55
81
Implementing Memory Hooks
11:08
82
Creating the Duck Duck Go Web Search Agent
01:24
83
Testing our Short Term Memory Agent
12:19
84
Understanding the Pricing of Short Term Memory
01:37
85
Introduction to Long Term Memory
02:36
86
Long Term Memory Strategies: Semantic, Preferences and Summaries
05:52
87
Inspecting Short Term Memory
06:38
88
Inspecting Long Term Memory
06:50
89
Testing our Agent with a Combined Short and Long Term Memory
12:00
90
Long Term Memory Pricing
01:30
91
Prompt Management with AWS Bedrock
14:40
92
Watermark Detection, Was this image Created with AI?
01:53
93
Reinforcement Fine Tuning with AWS Bedrock
18:25
94
Data Automation, Intelligent Document, Video, Image, and Audio Processing Part 1
14:02
95
Data Automation, Intelligent Document, Video, Image, and Audio Processing Part 2
06:08
96
Data Automation, Intelligent Document, Video, Image, and Audio Processing Part 3
05:46
97
Intelligent Prompt Routing with AWS Bedrock
10:39
98
Using LLMs in Batch Inference Mode in AWS Bedrock
12:27
99
Setting Up AWS Access Keys
08:36
100
Setting Up Files
02:32
101
Understanding Speech-to-Speech Models
02:47
102
Understanding Bidirectional Streaming
06:04
103
Creating Audio Configurations
03:25
104
Setting Up Debugging Functions
04:25
105
Non-Blocking Asyncio Python
05:12
106
Eventloop and Multithreads in Python
09:28
107
Getting Guests, Dynamodb Call
02:49
108
Getting Reservations, Dynamodb Call
07:29
109
Updating Reservations, Dynamodb Call
09:42
110
Event Templates Part 1
07:31
111
Event Templates Part 2
08:26
112
Exploring Tools Our Model Has Access To
06:27
113
Tool Result Event
01:38
114
Initialising the Bedrock Stream Manager Class
06:15
115
Initialising the Bedrock Stream
06:24
116
Sending Raw Events to Bedrock
02:29
117
Processing Audio Input
03:04
118
Sending Events to the Bedrock Stream
07:29
119
Processing Incoming Responses From Bedrock
07:11
120
Handling Tool Requests + Completions
03:52
121
Executing Tools + Gracious Closing and Shutting Down
02:51
122
Separate Input and Output Streams
04:15
123
Finishing the Audio Streamer Class
08:40
124
Ending the Stream Clarification
00:56
125
Finishing Up Our Final Script
03:07
126
AWS Quotas and Credentials
02:00
127
Installing Necessary Libraries
03:26
128
Setting up DynamoDB
05:02
129
First Test of Our Agent
04:47
130
Testing Reservation Updates
03:07
131
Testing with the Debug Flag
02:20
132
Testing the Final Product
07:04
133
Cleaning Up
02:11
134
Congratulations!
00:49
135
Thank You!
01:18
Unlock unlimited learning

Get instant access to all 134 lessons in this course, plus thousands of other premium courses. One subscription, unlimited knowledge.

Learn more about subscription

Books

Read Book AWS Bootcamp: Build AI Apps with AWS Bedrock

#TitleTypeOpen
1Possible CORS Error PDF
2AWS Bedrock Agent Core Architecture Diagram PDF

What courses are similar to AWS Bootcamp: Build AI Apps with AWS Bedrock?

More courses by Zero To Mastery

Frequently asked questions

What prerequisites are needed to enroll in this course?
Participants should have a basic understanding of cloud computing and familiarity with AWS services, as the course involves setting up AWS accounts and working with AWS Bedrock. Prior experience with programming and machine learning concepts will be beneficial, though not mandatory.
What projects will I build in this course?
The course includes two capstone projects: building multi-agent workflows and creating interruptible voice agents. These projects allow learners to apply AWS Bedrock's capabilities in real-world scenarios, leveraging AI for workflow automation and voice interaction solutions.
Who is the target audience for this course?
The course is designed for developers and IT professionals interested in leveraging AWS Bedrock for AI applications. It is particularly suited for those looking to enhance their skills in generative AI and apply AI solutions in enterprise environments.
How does the course compare in depth to other AI courses?
This course offers a comprehensive exploration of AWS Bedrock and its application in generative AI, covering foundational models, fine-tuning techniques, and intelligent model routing. It provides practical, hands-on experience with AWS tools, differentiating it from more theoretical courses.
What specific AWS tools will I learn to use?
You will learn to use AWS Bedrock, focusing on its foundation models for generative AI. The course covers using Lambda functions, API Gateway, AWS S3, and Boto3 for deploying and managing AI applications.
What topics are not covered in this course?
The course does not cover the basics of machine learning algorithms or data science fundamentals. It focuses specifically on applying AWS Bedrock for AI application development, assuming some prior knowledge of AI concepts.
What is the estimated time commitment for completing the course?
With a total of 135 lessons, participants should expect to dedicate several weeks to complete the course, depending on individual pace. The course includes practical exercises and projects that require active engagement and time to thoroughly understand and implement.