Developing Modern Applications with AWS AI and Generative AI Services
2h 50mBeginner2025-06-06
Authors
Saravanan Dhandapani
Course details
This course introduces concepts of AI and GenAI and how to leverage the services offered by AWS in building cutting-edge applications. Learn fundamental concepts like foundation models, large language models, generative and discriminative models, transformer architecture, and diffusion models, as well as prompt engineering concepts. You will be introduced to all the AI services AWS offers to process text, image, video, and speech. Additionally, learn how to use Amazon Q and build a generative AI-powered application. By the end of this course, you’ll be fully equipped with the skills you need to leverage the various AWS services in building enterprise applications.
Learning objectives
Understand how AI and GenAI relate to data science and ML and their data and compute requirements.
Explain the core concepts and technologies of generative AI, including foundation models, large language models, and model architectures.
Define the AWS AI and GenAI services, their use cases, and cost considerations.
Describe the importance of crafting effective prompts for desired outputs using a prompt framework.
Learning objectives
Understand how AI and GenAI relate to data science and ML and their data and compute requirements.
Explain the core concepts and technologies of generative AI, including foundation models, large language models, and model architectures.
Define the AWS AI and GenAI services, their use cases, and cost considerations.
Describe the importance of crafting effective prompts for desired outputs using a prompt framework.
Skills covered
Amazon Web Services (AWS)AI Productivity ToolsAmazonArtificial Intelligence for BusinessBusiness Software and ToolsOne-Off
Concepts
0. Introduction
- 01 - Modern applications of generative AI and AWS
1. Introduction to AI and Generative AI Concepts
- 02 - Fundamentals of AI
- 03 - Fundamentals of generative AI
- 04 - Architecture behind generative AI
- 05 - Effective prompt engineering
2. Introduction to AI Services on AWS
- 06 - Overview of AWS AI and generative AI services
- 07 - Services to process documents and text
- 08 - Services to process image and video
- 09 - Services to build chatbots and voice assistants
- 10 - Services to process speech and vision
- 11 - Developing domain-specific generative AI applications
3. Processing Text and Documents with AWS AI Services
- 12 - Amazon Comprehend
- 13 - Extracting entities, sentiments, and key phrases using Amazon Comprehend
- 14 - Amazon Translate
- 15 - Translate between languages using Amazon Translate
4. Processing Image and Video with AWS AI Services
- 16 - Amazon Rekognition
- 17 - Detecting labels, text, and PPE using Amazon Rekognition
- 18 - Amazon Textract
- 19 - Analyze documents using Amazon Textract
5. Building Chatbots and Voice Assistants with AWS AI Services
- 20 - Amazon Lex
- 21 - Create a bot using Amazon Lex
- 22 - Amazon Kendra
- 23 - Build an enterprise search service using Amazon Kendra
6. Processing Speech and Vision with AWS AI Services
- 24 - Amazon Polly
- 25 - Convert text to lifelike speech using Amazon Polly
- 26 - Amazon Transcribe
- 27 - Convert speech to text using Amazon Transcribe
7. Getting Started with Amazon Bedrock
- 28 - Overview of Amazon Bedrock
- 29 - Choosing the right base foundation model
- 30 - Evaluating a foundation model
- 31 - RAGs and knowledge base in Amazon Bedrock
- 32 - Amazon Bedrock Guardrails
8. Build a Custom Generative AI Assistant with Amazon Q
- 33 - Overview of Amazon Q
- 34 - Creating a chat application using Amazon Q Business
- 35 - Introducing Amazon Q Developer
- 36 - Integrate Amazon Q with an IDE
Conclusion
- 37 - Next steps