Data

Tools

Indexes

Applications

Experiments

Awesome

An open API service indexing awesome lists of open source software.

https://github.com/mauripsale/doc-adk-training

Learn to build, test, and deploy production-ready AI agents with this complete "From Zero to Hero" training course for the Google Agent Development Kit (ADK).
https://github.com/mauripsale/doc-adk-training

agent-development agent-development-kit ai-agents course-materials gemini generative-ai google-adk google-cloud llm python training-course tutorial vertex-ai

Last synced: 2 days ago
JSON representation

Learn to build, test, and deploy production-ready AI agents with this complete "From Zero to Hero" training course for the Google Agent Development Kit (ADK).

Awesome Lists containing this project

README 

          
# 🎓 Google ADK Training: From Zero to Hero 🚀



Welcome! This repository contains a comprehensive, multi-module training course for the **Google Agent Development Kit (ADK)**. Through a series of hands-on modules, you will learn the core and advanced concepts of the ADK to build, test, deploy, and observe your own AI agents.



## 🎯 Our Philosophy: From Zero to Hero



This course was born from a specific need: to create a complete learning path that takes a developer from the foundational concepts of AI agents to building complex, production-ready systems. The goal is to transform you from "Zero" to "Hero" in the world of AI Agent development with the Google ADK, providing not just the theory, but the hands-on practice required to become confident and proficient.



## ✍️ About the Author



This course was created and is maintained by [**Maurizio Ipsale**](https://www.linkedin.com/in/maurizioipsale/), a Google Cloud Authorized Trainer and Google Developer Expert (GDE) in AI and Cloud. This project stems from a passion for empowering developers with the skills needed to build the next generation of AI agents.



## 🚧 Project Status 🚧



**Current Version:** `v0.2.0`



Please be aware that this training course is in its early stages of development. As a "version zero" project, the content is subject to significant changes, additions, and refactoring.



We are working hard to refine and expand the material, but you may encounter typos, errors, or incomplete sections. Your feedback and contributions are highly encouraged! If you find an issue or have a suggestion, please [open an issue on GitHub](https://github.com/mauripsale/doc-adk-training/issues).



## ⏱️ Time Estimation



This comprehensive training course is designed for both self-service and instructor-led delivery. The estimates below provide a realistic guide for pacing, considering the technical depth and hands-on nature of the labs.



*   🧑‍💻 **Self-Service (SS) Duration:** This estimate reflects the time a motivated individual learner would take to read the theory, complete the labs, and account for a 25% troubleshooting/review factor.

*   👨‍🏫 **Instructor-Led Training (ILT) Duration:** This estimate is tailored for a classroom environment (up to 16 participants) with a net delivery time of 6 hours per day. It includes a 75% buffer for instructor guidance, Q&A, and assisting students during labs, plus a 5-minute transition buffer between modules.



---



## ⏱️ Course Outline



### 🌱 Part 1: Foundations (Modules 1-7)

This part covers the absolute basics of AI agents and the ADK, getting your environment set up and guiding you through building and running your first agents, including multimodal capabilities.



*   📖 **[Module 1: Introduction to AI Agents & Google ADK](./training/module01-intro-to-ai-agents/)** (🧑‍💻 35 min / 👨‍🏫 55 min)

*   📖 **[Module 2: Setting Up Your Development Environment](./training/module02-environment-setup/)** (🧑‍💻 40 min / 👨‍🏫 60 min)

*   📖 **[Module 3: Your First Agent: The "Echo" Agent](./training/module03-first-agent-echo/)** (🧑‍💻 35 min / 👨‍🏫 55 min)

*   📖 **[Module 4: Core Agent Concepts: `LlmAgent` Deep Dive](./training/module04-llmagent-deep-dive/)** (🧑‍💻 30 min / 👨‍🏫 50 min)

*   📖 **[Module 5: Running and Interacting with Agents](./training/module05-running-agents/)** (🧑‍💻 30 min / 👨‍🏫 50 min)

*   📖 **[Module 6: Running an Agent Programmatically](./training/module06-programmatic-execution/)** (🧑‍💻 35 min / 👨‍🏫 55 min)

*   📖 **[Module 7: Multimodal and Images 📸](./training/module07-multimodal-and-images/)** (🧑‍💻 40 min / 👨‍🏫 60 min)



### 🛠️ Part 2: Tools & Capabilities (Modules 8-14)

This part focuses on giving your agents "superpowers" by connecting them to tools, from built-in capabilities to custom functions and third-party libraries.



*   🧰 **[Module 8: Introduction to Tools](./training/module08-intro-to-tools/)** (🧑‍💻 35 min / 👨‍🏫 55 min)

*   🧰 **[Module 9: Intro to Custom Function Tools](./training/module09-intro-custom-function-tools/)** (🧑‍💻 45 min / 👨‍🏫 70 min)

*   🧰 **[Module 10: Advanced Function Tools](./training/module10-advanced-function-tools/)** (🧑‍💻 40 min / 👨‍🏫 65 min)

*   🧰 **[Module 11: OpenAPI Tools](./training/module11-openapi-tools/)** (🧑‍💻 35 min / 👨‍🏫 55 min)

*   🧰 **[Module 12: Built-in Tools and Grounding](./training/module12-built-in-tools-grounding/)** (🧑‍💻 30 min / 👨‍🏫 45 min)

*   🧰 **[Module 13: Tool Context](./training/module13-tool-context/)** (🧑‍💻 40 min / 👨‍🏫 65 min)

*   🧰 **[Module 14: Third-Party Tools](./training/module14-third-party-tools/)** (🧑‍💻 30 min / 👨‍🏫 40 min)



### 🤖🤖 Part 3: Multi-Agent Systems (Modules 15-21)

Learn how to go beyond single agents and build complex systems where multiple agents collaborate to solve complex problems, both locally and in a distributed fashion.



*   🤝 **[Module 15: Introduction to Multi-Agent Systems](./training/module15-intro-to-multi-agent-systems/)** (🧑‍💻 15 min / 👨‍🏫 30 min)

*   🤝 **[Module 16: Coordinator Agent](./training/module16-coordinator-agent/)** (🧑‍💻 40 min / 👨‍🏫 60 min)

*   🤝 **[Module 17: Sequential Workflow Agents](./training/module17-sequential-workflow-agents/)** (🧑‍💻 30 min / 👨‍🏫 45 min)

*   🤝 **[Module 18: Parallel Workflow Agents](./training/module18-parallel-workflow-agents/)** (🧑‍💻 40 min / 👨‍🏫 65 min)

*   🤝 **[Module 19: Advanced Multi-Agent Architectures](./training/module19-advanced-multi-agent-architectures/)** (🧑‍💻 45 min / 👨‍🏫 75 min)

*   🤝 **[Module 20: Loop Agents](./training/module20-loop-agents/)** (🧑‍💻 40 min / 👨‍🏫 65 min)

*   🤝 **[Module 21: Agent-to-Agent Communication](./training/module21-agent-to-agent/)** (🧑‍💻 50 min / 👨‍🏫 70 min)



### 🏭 Part 4: Production Readiness (Modules 22-26)

This part covers the essential features for making your agents robust, observable, and reliable in a production environment.



*   🧠 **[Module 22: State and Memory](./training/module22-state-and-memory/)** (🧑‍💻 35 min / 👨‍🏫 55 min)

*   📦 **[Module 23: Artifacts](./training/module23-artifacts/)** (🧑‍💻 40 min / 👨‍🏫 65 min)

*   🧪 **[Module 24: Evaluation](./training/module24-evaluation/)** (🧑‍💻 50 min / 👨‍🏫 75 min)

*   📊 **[Module 25: Observability](./training/module25-observability/)** (🧑‍💻 35 min / 👨‍🏫 55 min)

*   🛡️ **[Module 26: Callbacks](./training/module26-callbacks/)** (🧑‍💻 40 min / 👨‍🏫 65 min)



### 🔌 Part 5: Advanced Integrations & UI (Modules 27-30)

This section covers advanced tooling with the Model Context Protocol (MCP) and strategies for integrating your agents with user interfaces.



*   🔗 **[Module 27: Introduction to MCP](./training/module27-intro-to-mcp/)** (🧑‍💻 40 min / 👨‍🏫 65 min)

*   🔗 **[Module 28: Building MCP Tools](./training/module28-building-mcp-tools/)** (🧑‍💻 40 min / 👨‍🏫 65 min)

*   🖼️ **[Module 29: UI Integration Intro](./training/module29-ui-integration-intro/)** (🧑‍💻 35 min / 👨‍🏫 55 min)

*   🖼️ **[Module 30: Custom Streaming Client](./training/module30-custom-streaming-client/)** (🧑‍💻 45 min / 👨‍🏫 65 min)



### ☁️ Part 6: Deployment & Enterprise (Modules 31-36)

Learn how to deploy your agents and their components to various scalable cloud environments, including enterprise-grade platforms.



*   🚀 **[Module 31: Production Deployment Strategies](./training/module31-production-deployment-strategies/)** (🧑‍💻 15 min / 👨‍🏫 25 min)

*   🚀 **[Module 32: Deployment to Cloud Run](./training/module32-deployment-cloud-run/)** (🧑‍💻 35 min / 👨‍🏫 50 min)

*   🚀 **[Module 33: Deployment to GKE](./training/module33-deployment-gke/)** (🧑‍💻 60 min / 👨‍🏫 95 min)

*   🚀 **[Module 34: Deploying an MCP Server to Cloud Run](./training/module34-deploying-mcp-server-cloud-run/)** (🧑‍💻 70 min / 👨‍🏫 105 min)

*   🚀 **[Module 35: Deployment to Agent Engine](./training/module35-deployment-agent-engine/)** (🧑‍💻 60 min / 👨‍🏫 90 min)

*   🚀 **[Module 36: Gemini Enterprise](./training/module36-gemini-enterprise/)** (🧑‍💻 15 min / 👨‍🏫 25 min)



### 🏆 Part 7: Capstone Project & Best Practices (Modules 37-38)

Apply everything you've learned in a final capstone project and review the essential best practices for building production-ready agents.



*   ✨ **[Module 37: Advanced Personalized Shopping Agent](./training/module37-advanced-personalized-shopping-agent/)** (🧑‍💻 85 min / 👨‍🏫 120 min)

*   ✨ **[Module 38: Best Practices](./training/module38-best-practices/)** (🧑‍💻 35 min / 👨‍🏫 50 min)



---

## Detailed Timetables



For a detailed breakdown of the time required for each module, please see the following timetables:



*   **[🧑‍💻 Self-Service (SS) Detailed Timetable](./timetable-self-service.md)**

*   **[👨‍🏫 Instructor-Led Classroom (ILC) Detailed Timetable](./timetable-ilt.md)**



---

## 📚 Course Variants



While this repository contains the full, comprehensive "From Zero to Hero" track, we also offer shorter, focused delivery variants for different training needs:



*   **[Variant A: 1-Day Workshop (ILC)](./variant-a-1-day-workshop.md)**: A high-impact, 6-hour workshop focused on building your first tool-powered agent.

*   **[Variant B: Standard 2-Day ILT](./variant-b-2-day-ilt.md)**: A comprehensive 2-day course covering all foundational and key intermediate skills.

---



## ▶️ Getting Started



Before you begin, please ensure you have the following prerequisites installed:

*   Git

*   Python 3.11+

*   A Google Cloud Project with billing enabled

*   The Google Cloud CLI (`gcloud`)



To get started with the course:

1.  **Clone the repository:** `git clone https://github.com/mauripsale/doc-adk-training.git`

2.  **Navigate to the directory:** `cd training`

3.  **Begin with Module 1** and proceed through the modules in order. Each lab builds upon the concepts and code from the previous one.



Happy building!



---



## 🤝 Contributing



Contributions are welcome! If you find an issue, have a suggestion for a new module, or want to improve the existing content, please see our **[Contributing Guidelines](./CONTRIBUTING.md)** to get started.



---



## 📜 Licensing



The documentation and textual content of this training course are licensed under the **Creative Commons Attribution 4.0 International License (CC BY 4.0)**.



Software components, such as the code in the `sample-agents` directory, are licensed under the **Apache License, Version 2.0**. Please see the `LICENSE` file within those directories for full details.



## 🙏 Acknowledgements



This training course was inspired by the structure and content of the original ADK Training Hub created by Raphael Mansuy. While all content has been originally rewritten and adapted, we gratefully acknowledge his foundational work.