AWS Security Essentials

Course Objectives:

1. Understand the relationship between generative AI and machine learning
2. Assess the significance of generative AI while evaluating its potential risks and benefits
3. Identify business opportunities derived from generative AI use cases
4. Explore the technical foundations and essential terminology of generative AI
5. Develop a plan for executing a generative AI project
6. Recognize potential risks associated with generative AI and strategies to mitigate them
7. Comprehend the workings of Amazon Bedrock
8. Gain familiarity with the fundamental concepts of Amazon Bedrock
9. Identify and appreciate the advantages of Amazon Bedrock
10. List common use cases for Amazon Bedrock
11. Describe the typical architecture associated with an Amazon Bedrock solution
12. Understand the cost structure of Amazon Bedrock
13. Implement a demonstration of Amazon Bedrock in the AWS Management Console
14. Master prompt engineering and adhere to best practices when interacting with foundation models (FMs)
15. Identify various types of prompt techniques, including zero-shot and few-shot learning
16. Apply advanced prompt techniques as per specific use cases
17. Evaluate potential misuse of prompts and address any biases in FM responses
18. Understand the components of a generative AI application and how to customize a foundation model (FM)
19. Describe Amazon Bedrock foundation models, inference parameters, and key Amazon Bedrock APIs
20. Utilize Amazon Web Services (AWS) offerings for monitoring, securing, and governing Amazon Bedrock applications
21. Integrate LangChain with large language models (LLMs), prompt templates, chains, chat models, text embedding models, document loaders, retrievers, and Agents for Amazon Bedrock
22. Describe architecture patterns that can be implemented with Amazon Bedrock for building generative AI applications
23. Apply the concepts to build and test sample use cases leveraging various Amazon Bedrock models, LangChain, and the Retrieval Augmented Generation (RAG) approach