The Claude in Amazon Bedrock Course
As part of an accreditation program created for AWS, Anthropic launched a first-of-its-kind training for AWS employees. Here's the full course so you can follow along.
Module 1: Course Welcome
Welcome to the course! This module will help you:
- Understand the course structure and learning path
- Identify the key skills and knowledge areas covered in the course
- Recognize the intended audience and assess personal readiness for the course
Module 2: Anthropic Overview
By the end of this module, you'll be able to:
- Explain Anthropic's approach to AI research and development
- Describe the key principles of AI safety, alignment, and interpretability
- Identify and differentiate between Anthropic's AI models
Module 3: Anthropic's Models
At the end of this module, you'll be able to:
- Identify and differentiate between Anthropic's AI models
- Understand the benchmarks used to measure generative AI models
Module 4: Generative AI
By the end of this module, you'll be able to:
- Define and explain key terminology in the generative AI field
- Describe the process of LLM development, including pretraining, SFT, RLHF, and fine-tuning
- Understand the concepts of inference and latency in AI applications
Module 5: Working with the API
At the end of this module, you'll be able to:
- Make successful API requests to Claude using best practices
- Format messages effectively for optimal AI responses
- Configure and control API parameters like system prompts, max tokens, and stop sequences
- Work with different input types including streaming, images, and multi-modal requests
Module 5B: Prompting
At the end of this module, you'll be able to:
- Structure effective prompts that get consistent, high-quality responses from Claude
- Apply proven prompt engineering techniques through practical demonstrations
- Evaluate and improve prompts using best practices and troubleshooting methods
- Identify common prompt patterns and when to use them
Module 6: Tool Use
At the end of this module, you'll be able to:
- Design effective prompts that help Claude use tools appropriately
- Structure outputs to ensure reliable tool interactions
- Implement best practices for tool-based workflows with Claude
- Understand and work with different agent architectures
- Successfully guide Claude in computer interactions and tool manipulation
Module 7: Evals
At the end of this module, you'll be able to:
- Understand different types of AI model evaluations and when to use them
- Set up effective human evaluation processes for model outputs
- Implement automated code-based evaluation methods
- Design model-graded evaluation frameworks
- Select and use appropriate evaluation tools for your specific needs
Module 8: RAG and Fine-tuning
At the end of this module, you'll be able to:
- Understand the fundamentals of Retrieval-Augmented Generation (RAG)
- Implement embeddings effectively for information retrieval
- Apply best practices for contextual retrieval in RAG systems
- Optimize RAG performance through proven tips and techniques
- Design and implement fine-tuning strategies for improved model performance
Module 9: Course Wrapup
At the end of this module, you'll be able to:
- Synthesize key learnings from across all course sections
- Identify next steps in your Claude development journey
- Connect with resources for continued learning and support