Claude with Amazon Bedrock by Anthropic

Building production AI applications with Claude requires more than API access—you need systems that handle retrieval, tool use, caching, and scale. Amazon Bedrock provides the managed infrastructure to build these systems in the AWS ecosystem. This course teaches you to implement Claude's API, create production-ready applications, and apply advanced capabilities including tool use, retrieval-augmented generation (RAG), and autonomous agents.

Get started with core API implementation patterns, then learn how to build RAG systems and conversational AI pipelines. Along the way, find out how to develop autonomous agents for tasks like code generation and debugging, and learn performance optimization techniques including caching and scalable architecture design.

Note: This course requires basic Python programming proficiency and a basic understanding of AWS services and Amazon Bedrock.

Learning objectives
Utilize Anthropic models on Amazon Bedrock for multi-turn conversations and system prompt configuration.
Build and evaluate prompts using structured approaches.
Design and integrate custom tools using JSON Schema for function calling and batch processing.
Develop RAG pipelines with text chunking, embeddings, BM25 search, and contextual retrieval techniques.
Configure and optimize Claude's advanced features including extended thinking, vision capabilities, and prompt caching.
Leverage Claude Code for automated debugging and task execution.
Implement Model Context Protocol (MCP) for defining tools, resources, and prompts in client applications.
Optimize inference through streaming, temperature control, and structured data extraction.
Build evaluation frameworks for prompts using model-based and code-based grading approaches.