Claude with Google Cloud's Vertex AI

Working with Anthropic models through Google Cloud's Vertex AI: setup, prompting, tool use, RAG, agents, and production deployment patterns.

66 lessons8.5 hr9 quizzesCompletion badge

Start course Sign in to save progress

What you’ll learnBy the end of this course, you’ll be able to

Set up and configure Claude models through Google Cloud's Vertex AI
Implement multi-turn conversations with proper message handling and context management
Design and evaluate prompts using systematic testing workflows and automated grading techniques
Apply prompt engineering principles including XML tag structuring, example-based learning, and output control
Build tool-use implementations enabling Claude to interact with external functions and APIs
Develop RAG pipelines using text chunking, embeddings, BM25 search, and contextual retrieval techniques
Utilize advanced Claude features including vision capabilities, PDF processing, citation generation, and prompt caching
Implement the Model Context Protocol for creating custom tools, resources, and prompt templates
Configure and deploy Anthropic Apps including Claude Code for automated development tasks and Computer Use for UI automation
Design agent-based workflows with parallelization, chaining, and routing patterns for complex AI systems

Who it’s for

Devs who want to add AI features to their apps

Before you start

Proficiency in Python programming
Basic knowledge of handling JSON data
A Google Cloud account with Vertex AI access

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.

Inside the course

Accessing Claude with the API

10 lessons

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

Prompt engineering techniques

6 lessons

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

Tool use with Claude

14 lessons

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

10 lessons

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

Model Context Protocol

12 lessons

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

Agents and workflows

8 lessons

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