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!

Welcome!

"Greetings, World!": Our first agent

In the loop: Running our agent

Running an Agent with the Google ADK

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.

From prompt to action: Exploring tool use

Talking facts: Connecting to a knowledge base

En garde! Building guardrails for our agent

From one to many: Building multi-agent systems

It takes a village: Multi-agent customer support

Wrap-up!

Building a Multi-Agent System

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.

Intermediate Python

Build a customer-support assistant step-by-step with Google’s Agent Development Kit (ADK).

It takes a village: Multi-agent customer support

Building AI Agents with Google ADK

Egzersiz talimatları

Uygulamalı interaktif egzersiz