Skip to main content
HomePython

Course

Building AI Agents with Google ADK

IntermediateSkill Level
4.8+
387 reviews
Updated 03/2026
Build a customer-support assistant step-by-step with Google’s Agent Development Kit (ADK).
Start Course for Free
PythonArtificial Intelligence1 hr4 videos9 Exercises700 XP5,456Statement of Accomplishment

Create Your Free Account

or

By continuing, you accept our Terms of Use, our Privacy Policy and that your data is stored in the USA.

Loved by learners at thousands of companies

Group

Training 2 or more people?

Try DataCamp for Business

Course Description

Build a customer-support assistant step-by-step with Google’s Agent Development Kit: start from a one-line greeting bot, then add tools for FAQ look-ups, policy guardrails for safety, and multi-agent delegation for complex queries. Throughout the course, you’ll wire up Gemini, call external APIs, and orchestrate specialist sub-agents, focusing on hands-on agent design.The videos contain live transcripts you can reveal by clicking "Show transcript" at the bottom left of the videos. The course glossary can be found on the right in the resources section. To obtain CPE credits you need to complete the course and reach a score of 70% on the qualified assessment. You can navigate to the assessment by clicking on the CPE credits callout on the right.

Feels like what you want to learn?

Start Course for Free

What you'll learn

  • Assess the application of guardrails and content-safety settings to ensure agents refuse unsafe or off-topic requests
  • Define the procedure for configuring an AI support agent to access external data through FunctionTool integrations
  • Differentiate single-agent workflows from coordinated multi-agent systems within Google ADK for customer support scenarios
  • Evaluate agent outputs to verify correct tool usage, delegation, and compliance with specified instructions in multi-step customer interactions
  • Identify the required environment setup steps and core classes in Google ADK needed to instantiate and run an LlmAgent

Prerequisites

Intermediate Python
1

Running an Agent with the Google ADK

Get ready to experience running your own AI agent! In this chapter, you’ll install and configure Google ADK, set up your credentials, and run your very first Gemini-powered agent. Watch as it greets you in real time!
Start Chapter
2

Building a Multi-Agent System

Get ready to give your agents real-world superpowers! Explore how tools can extend an agent’s capabilities beyond chatting, like answering FAQs using a structured knowledge base. Then, build your own customer support multi-agent system and see it in action.
Start Chapter
Building AI Agents with Google ADK
Course
Complete

Earn Statement of Accomplishment

Add this credential to your LinkedIn profile, resume, or CV
Share it on social media and in your performance reviewEnroll Now

Don’t just take our word for it

*4.8
from 387 reviews
85%
13%
2%
0%
0%
  • Mohamed
    4 days ago

  • Antonino
    5 days ago

    A short intro to Google's ADKs! Fantastic combination of videos and notebooks!

  • Gary
    6 days ago

  • Amir
    last week

    simple and easy to follow

  • Sean
    last week

    solid quick overview - adk is surprisingly simple to work with

  • Kim Chuan
    2 weeks ago

Mohamed

"A short intro to Google's ADKs! Fantastic combination of videos and notebooks!"

Antonino

"simple and easy to follow"

Amir

FAQs

What is Google ADK, and do I need prior experience with it?

Google ADK is Google's Agent Development Kit for building AI agents. No prior ADK experience is needed, but you should know basic Python from Introduction to Python and Intermediate Python.

What kind of AI agent will I build in this course?

You will build a customer-support assistant step by step, starting from a simple greeting bot and adding FAQ lookups, policy guardrails, and multi-agent delegation for complex queries.

Which AI model powers the agents in this course?

The agents are powered by Google Gemini. You will learn to configure credentials, wire up Gemini, and run your agent in real time within the ADK framework.

Does the course cover multi-agent systems?

Yes. The second chapter teaches you to build a multi-agent system where specialist sub-agents handle different tasks, such as answering FAQs from a structured knowledge base.

How long does this course take to finish?

It has 2 chapters and 11 exercises with a median completion time of about 1 hour, making it a quick hands-on introduction to agent development.

    Join over 19 million learners and start Building AI Agents with Google ADK today!

    Create Your Free Account

    or

    By continuing, you accept our Terms of Use, our Privacy Policy and that your data is stored in the USA.

    Grow your data skills with DataCamp for Mobile

    Make progress on the go with our mobile courses and daily 5-minute coding challenges.