Introduction to Agents with ADK

Introduction

Welcome to DevCore Inc.! We are a fast-moving tech company where innovation thrives. Our developers have the freedom to spin up Cloud resources on demand, fostering rapid prototyping and experimentation. However, this freedom has a downside: zombie resources. Developers frequently create servers for tests but forget to stop or delete them afterwards.

This results in hundreds of idle resources running 24/7, costing the company tens of thousands of dollars every month for zero value. The manual cleanup process is tedious, error-prone, and can’t keep up. We need an automated, intelligent system to solve this problem.

Our objective is to build a Cloud Janitor an AI-powered agentic solution that can automatically identify, verify, and safely terminate unused cloud resources.

Overview of Agents and Tools

In this hack, we’ll use the Agent Development Kit (ADK) framework to develop this solution step-by-step, starting with a single agent and progressively building a collaborative, multi-agent system.

Learning Objectives

This hack will help you explore the following tasks:

  • Using LLM Agents to analyze unstructured data
  • Augmenting Agents with Tools to expand their capabilities
  • Using multiple agents for collaboration
  • A bit of prompt engineering
  • Model Context Protocol (MCP) as the abstraction layer for 3rd party tools
  • Agent2Agent (A2A) Protocol for using 3rd party remote agents

Challenges

Prerequisites

  • Basic knowledge of GCP
  • Basic knowledge of Python
  • Access to a GCP environment

 Note
In principle you could do the challenges in any environment, but we recommend Cloud Shell as it comes with most of the required tooling.

Contributors

  • Murat Eken