Your cart is empty.
Keep shoppingGetting started with Google Agent Development Kit (ADK)
410 students
Getting started with Google Agent Development Kit (ADK)
Build, Deploy, and Orchestrate Production-Ready AI Agents with Google's Open-Source Framework
Created byPritesh Mistry
Last updated 5/2026
English
What you'll learn
- Understand the core architecture of AI agents and multi-agent systems, and explain how Google's Agent Development Kit (ADK) simplifies the full agent developmen
- Build and configure intelligent AI agents using ADK in Python or TypeScript, equipping them with built-in and custom tools to perform real-world, multi-step tas
- Design and orchestrate multi-agent workflows using sequential, parallel, and loop-based patterns, enabling specialized agents to collaborate, delegate, and comm
- Deploy production-ready agents to Google Cloud or containerized environments, and apply ADK's visual debugging and evaluation tools to test, optimize, and monit
Explore related topics
Course content
13 sections • 54 lectures • 4h 12m total length
Requirements
- Basic understanding of Python
- Familiarity with APIs and how to make HTTP requests — understanding REST APIs and JSON responses will help when integrating tools and external services.
Description
The future of AI isn't just smarter models — it's smarter systems. This course introduces you to Google's Agent Development Kit (ADK), an open-source framework designed to help developers build, test, and deploy intelligent AI agents and multi-agent systems with precision and control.
Whether you're a Python or TypeScript developer, this course gives you the hands-on foundation to move beyond simple prompt-and-response interactions and start building autonomous agents that can reason, plan, use tools, and collaborate with other agents to accomplish complex, multi-step workflows.
You'll begin by understanding the core concepts behind AI agents — what they are, how they think, and why multi-agent architectures outperform single monolithic models. From there, you'll dive into ADK's powerful features: defining agent logic, equipping agents with built-in and custom tools, orchestrating workflows using sequential, parallel, and loop-based patterns, and managing context efficiently.
By the end of this course, you'll have built real working agents using ADK, explored the visual debugging UI, and learned how to deploy your agents to Google Cloud or any containerized environment.
No prior agent development experience is required — just a solid understanding of Python or TypeScript and a curiosity to build the next generation of AI applications. What you'll build. What you'll deploy. What the future runs on.
Who this course is for:
- AI/ML enthusiasts and practitioners who understand LLMs and want hands-on experience designing real-world multi-agent workflows using a production-grade framework.
- Google Cloud users and Gemini developers who want to deepen their expertise by combining Gemini models with ADK's orchestration, tooling, and deployment capabilities