Introduction
Welcome to the course
()
Overview of Claude models
()
1. Working with the API
Accessing the API
()
Making a request
()
Multiturn conversations
()
Chatbot exercise
()
System prompts
()
System prompt exercise
()
Temperature
()
Streaming
()
Controlling model output
()
Structured data
()
Structured data exercise
()
2. Prompt Evaluations
Prompt evaluation
()
A typical eval workflow
()
Generating test datasets
()
Running the eval
()
Model-based grading
()
Code-based grading
()
Exercise on prompt evals
()
3. Prompt Engineering
Prompt engineering
()
Being clear and direct
()
Being specific
()
Structure with XML tags
()
Providing examples
()
Exercise on prompting
()
4. Tool Use
Introducing tool use
()
Tool functions
()
JSON schema for tools
()
Handling tool use responses
()
Running tool functions
()
Sending tool results
()
Multiturn conversations with tools
()
Adding multiple tools
()
Batch tool use
()
Structured data with tools
()
Flexible tool extraction
()
The text editor tool
()
5. Retrieval-Augmented Generation (RAG)
Introducing retrieval-augmented generation (RAG)
()
Text chunking strategies
()
Text embeddings
()
The full RAG flow
()
Implementing the RAG flow
()
BM25 lexical search
()
A multisearch RAG pipeline
()
Reranking results
()
Contextual retrieval
()
6. Features of Claude
Extended thinking
()
Image support
()
PDF support
()
Citations
()
Prompt caching
()
Rules of prompt caching
()
Prompt caching in action
()
7. Model Context Protocol (MCP)
Introducing MCP
()
MCP clients
()
Project setup
()
Defining tools with MCP
()
The MCP Inspector
()
Implementing a client
()
Defining resources
()
Accessing resources
()
Defining prompts
()
Prompts in the client
()
MCP review
()
8. Agents
Agents overview
()
Claude Code setup
()
Claude Code in action
()
Enhancements with MCP servers
()
Parallelizing Claude Code
()
Automated debugging
()
Computer use
()
How computer use works
()
Qualities of agents
()
Conclusion
Course wrap-up
()
Ex_Files_Claude_Amazon_Bedrock.zip
(5.5 MB)