Claude on Google Cloud

This course covers using Claude models on Google Cloud. You'll implement core API features like streaming and tool use, build systematic prompt evaluation pipelines, understand RAG systems, and investigate agent architectures.

Syllabus

Getting started with Claude

Start here for the fundamentals. Covers API authentication, basic requests, conversation management, system prompts, and structured output generation.

Prompt engineering & evaluation

Learn to write prompts that actually work. Focuses on prompting strategies, evaluation frameworks, and systematic testing approaches.

Tool use with Claude

Extend Claude with custom tools and functions. Build apps with function calling, multi-turn tool interactions, batch tool calling, and leverage built-in utilities.

Retrieval augmented generation

Implementation guide for production RAG systems. Covers text chunking, embeddings, hybrid search with BM25, multi-index architectures, reranking, and contextual retrieval.

Model Context Protocol (MCP)

The protocol for building modular AI applications. Define custom tools and resources, implement MCP servers and clients, handle the full integration lifecycle.

Claude Code & Computer Use

Two powerful Anthropic tools in action. Claude Code accelerates development workflows, Computer Use automates UI interactions. Includes MCP integration patterns.

Agents and workflows

Architecture patterns for autonomous AI systems. Understand parallel execution, operation chaining, conditional routing, and effective debugging strategies.