Challenge 1: Getting Started with ADK

Next Challenge

Introduction

Before building advanced features, you need to understand the foundation. The Agent Development Kit (ADK) is an open-source framework designed to help developers build, test, and run production-ready AI agents.

In this challenge, you will configure your local development environment by running an ADK agent inside Cloud Shell before we scale our architecture to the cloud.

Description

We’ve already prepared a code base for you and put it in a Git repository (your coach will provide you the link). Clone that on Cloud Shell, create a virtual environment, activate it and install the Python dependencies from the requirements.txt. Configure the agent to use user credentials for local development through Agent Platform (formerly known as Vertex AI).

Once everything is set up, run adk web and make sure that the agent responds back.

Success Criteria

  • The Git repository has been cloned to Cloud Shell.
  • You get no errors when you greet the agent from the adk web UI.
  • No code was modified.

Tips

  • The utility adk web is part of ADK CLI that gets installed when you install the dependencies in your virtual environment.
  • Newer versions of the adk web feature require you to set the --allow_origins to "*" to prevent CORS errors.

Learning Resources

Next Challenge