Course Overview

Welcome to the course on Google’s Agent Development Kit (ADK). We’re excited to guide you through the next phase of AI-powered applications. In recent years, large language models (LLMs) have demonstrated a remarkable ability to understand and generate human-like text, transforming industries and our interaction with technology.

However, their true potential emerges when we move beyond simple question-and-answer exchanges and enable them to act autonomously toward complex goals. This evolution marks the shift from generative AI to agentic AI. An AI agent is a system that can perceive its environment, reason, make decisions, and use tools to proactively accomplish a given objective.

To build these sophisticated systems, we need robust, engineering-driven frameworks. While several tools have emerged, this course focuses on Google’s ADK, a powerful, open-source framework designed for building flexible, multi-agent systems ready for production environments.

Why take this course

As generative AI becomes a standard component of modern software, the demand has shifted from engineers who can simply get an answer from an AI to those who can build systems that reliably achieve a specific outcome. This requires a structured approach to designing, building, and managing AI components that can act.

This course is designed to provide a deep, practical understanding of these principles. Rather than focusing on abstract theory, we will build a complete “Research Assistant” from the ground up. This hands-on project will provide a systematic framework for analyzing problems, designing robust agents, and orchestrating them to perform complex tasks, using the same production-grade toolkit that powers agents within Google’s own products.

Intended audience

This course is tailored for technology professionals who are ready to move from using AI to building with AI. Our ideal learners include:

• Generative AI engineers: These are professionals looking to move beyond prototyping and master the skills needed to build production-grade, autonomous agentic systems.

• Python developers: These are developers who want to integrate advanced AI capabilities into new or existing applications and need a systematic framework for building and managing agents.

Prerequisites

To get the most out of this course, we expect you to have a solid foundation in a few key areas. No prior experience in AI agent development is required.

• Python proficiency: You should have a solid understanding of Python programming, including functions, classes, and package management.

• API concepts: You should have a general familiarity with what an API is and the conceptual flow of a client-server request to understand how agents use tools.

What you will learn

We have logically structured this course to take you on a journey from foundational principles to advanced, production-level operations. Here is a brief look at what we will cover in each chapter:

• Foundations of Google ADK: We will learn the fundamental concepts and core components of the Google Agent Development Kit.

• Building the Research Assistant: We will build and progressively enhance our “Research Assistant,” as it evolves from a single agent to a coordinated, specialized multi-agent team.

• Evaluation and Deployment: We will learn how to professionally evaluate our agent’s performance and prepare it for real-world deployment using containerization.

• Orchestrating Workflows: We will orchestrate complex agent interactions using deterministic, sequential, parallel, and loop-based workflows.

• Exercise: We will apply our knowledge in a final hands-on exercise to solidify the concepts learned.

Now that we have a clear understanding of our goals, let’s explore the core concepts of Google ADK in the next lesson.