Building Agents with the Google Agent Developer Kit

Course details

The Google Agent Development Kit (ADK) is an open-source, code-first framework for building, evaluating, and deploying AI agents. In this course, instructor Fikayo Adepoju outlines the skills you need to build and test your own agents using the ADK. Fikayo covers how to define agents, equip them with various tools including custom functions and third-party integrations, and configure their underlying language models. Along the way, he also covers the essentials of managing input, output, and context within agents to enhance their functionality. Explore the concept of workflow agents—including sequential, loop, and parallel agent systems—and learn how to leverage built-in and MCP tools within the ADK. By the end of this course, you’ll be prepared to use the ADK to develop powerful agents and multiagent systems.

Learning objectives
Set up an ADK project and build your first agent.
Define agents with persona to take on specialized tasks.
Configure your agent’s use of models and manage input and outputs.
Understand and utilize different workflow agents.
Use tools through functions, built-in utilities, third-party services, and MCP.

Concepts

Introduction

Create your first AI agent with the Google ADK

Building Your First Agent

Set up your first project
Creating tools
Creating your agent
Testing your agent
All about the Google ADK

Creating Agents

Understanding agents
Defining an agent
Giving your agent tools
Configuring your model
Managing inputs and outputs
Managing context

Workflow Agents

What are workflow agents
Sequential agents
Parallel agents
Loop agents
Multiagent systems
A2A communucation

Working with Tools

Introduction to tools
Using functions as tools
Using built-in tools
Using third-party tools
MCP

Conclusion

Next steps