Google ADK Masterclass – Free Tutorials & Crash Course

Course by Arjun Prabhulal • ADK Masterclass

Overview

A free, hands-on series to master Google's Agent Development Kit (ADK). Learn to build, evaluate, and deploy AI agents from zero to production through step-by-step tutorials.

20 modules•100% free•Code included for every module

View Code on GitHub

Quick Start

New to ADK? You can have your first agent running in under two minutes:

pip install google-adk
adk create my_agent
adk web

Then start with Module 1 — Getting Started, or jump to any topic below.

What You'll Learn

  • ✓  Build, configure, and run agents via CLI, web UI, and Python
  • ✓  Design LLM agents and Sequential, Loop & Parallel workflows
  • ✓  Compose multi-agent systems with hierarchical patterns
  • ✓  Use built-in tools: Google Search, Code Executor, Vertex AI RAG & Search
  • ✓  Create custom function tools and OpenAPI tools with authentication
  • ✓  Connect MCP servers, GitHub, Firecrawl, and PostgreSQL via MCP Toolbox
  • ✓  Manage sessions, state, memory, callbacks, artifacts, and events
  • ✓  Cut token costs with context caching and compaction

Modules

1. Build 2. Orchestration 3. Tools 4. Protocols 5. Core Components
1. Build — Foundations of Agent Development

Open-source toolkit for building, evaluating, and deploying AI agents.

Module 1: ADK Getting Started - Introduction to ADK, environment setup, and building your first agent

1. Google ADK - Getting Started

Introduction to ADK – Overview, environment setup, and your first agent.
Module 2: Setting Up ADK Agents via Web, CLI, and Programmatic methods

2. Google ADK - Setting Up Agents (Web, CLI, Programmatic)

Different ways to create and interact with agents.
Module 3: Build AI Agents with ADK Visual Builder - no-code interface

3. Google ADK - Build Agents with Visual Builder

Build agents with Visual Builder.
2. Orchestration — Agent Types and Behavior

Learn how to design, compose, and scale agents.

Module 4: Building LLM Agents - intelligent, model-powered agents

4. Google ADK - Building LLM Agents

Build intelligent, model-powered agents.
Module 5: Workflow Agents - Sequential, Loop, and Parallel patterns

5. Google ADK - Workflow Agents (Sequential, Loop, Parallel)

Create dynamic task flows with sequential, loop, and parallel workflows in Google ADK.
Module 6: Multi-Agent Systems - hierarchical agent composition patterns

6. Google ADK - Multi-Agent Systems

Compose multiple agents into hierarchical systems for complex applications using agent composition patterns.
3. Tools — Built-in, Cloud, and Custom Integrations

Extend your agents with APIs, services, and custom tools.

Module 7: Built-in Tools - Google Search and Code Executor

7. Google ADK - Built-in Tools (Google Search, Code Executor)

Explore the Google Search and Code Executor built-in tools.
Module 8: Vertex AI RAG Engine - create grounded agents with your data

8. Google ADK - Built-in Tools (Vertex AI RAG Engine)

Learn how to use the Vertex AI RAG Engine built-in tool to create grounded agents with your own data.
Module 9: Vertex AI Search - enterprise data search integration

9. Google ADK - Built-in Tools (Vertex AI Search)

Build agents that can search across your enterprise data using the Vertex AI Search built-in tool.
Module 10: Custom Function Tools - build specialized Python tools

10. Google ADK - Custom Function Tools

Build custom functions that add specialized capabilities to your agents beyond built-in tools.
Module 11: OpenAPI Tools with Authentication - REST API integration

11. Google ADK - OpenAPI Tools with Authentication

Transform OpenAPI-defined APIs into agent tools and configure authentication for secure access.
Module 12: Multi-Tool Agents - combining multiple tools for complex tasks

12. Google ADK - Multi-Tool Agents

Build agents that leverage multiple tools together to accomplish complex tasks.
Module 13: Third Party Tools - GitHub and Firecrawl integration

13. Google ADK - Third Party Tools (GitHub, Firecrawl)

Connect your agents to external services for version control and web content extraction.
Module 14: MCP Toolbox for Databases - PostgreSQL integration

14. Google ADK - MCP Toolbox for Databases (PostgreSQL)

Connect your ADK agents to PostgreSQL databases using MCP Toolbox for enterprise-grade data access.
4. Protocols & Communication

Enable context and multi-agent collaboration.

Module 15: Model Context Protocol (MCP) - architecture and patterns

15. Google ADK - Model Context Protocol (MCP)

Understanding the Model Context Protocol - architecture, connection types, and production patterns.
5. Core Components

Understand internal mechanisms for robust, scalable agent design.

Module 16: Session, State and Memory - conversation history management

16. Google ADK - Session, State & Memory

Manage conversation history, state, and memory for multi-turn interactions.
Module 17: Context Management - caching and compression techniques

17. Google ADK - Context Management

Optimize agent performance with context caching and compression techniques.
Module 18: Callbacks - intercept and customize agent behavior

18. Google ADK - Callbacks

Intercept and customize agent behavior at various execution points.
Module 19: Artifacts - store and manage files and data

19. Google ADK - Artifacts

Store and manage files, images, and data produced by agents.
Module 20: Events - real-time streaming and debugging

20. Google ADK - Events

Understand the event system for real-time streaming and debugging.

Comments