Deploy multi-agent systems with Agent Development Kit and Agent Runtime
This 1-day course is an advanced, hands-on introduction to building and deploying multi-agent systems with the Google Agent Development Kit and Agent Runtime.
In the Deploy Multi-Agent Systems with Agent Development Kit and Agent Runtime course you will learn to use the Agent Development Kit to build complex, multi-agent systems. You will start with the basics and see how the kit compares with tools such as the Google Gen AI SDK or LangChain, then equip agents with tools and connect several agents through parent-child relationships and flows that define how they interact. You will also use features such as session memory, artifact storage and callbacks.
You will run your agents locally and then deploy them to Agent Runtime, which runs them as a managed agentic flow and takes care of infrastructure decisions and scaling. Finally you will query the deployed agent app and evaluate agents within the Agent Development Kit. The day includes four hands-on labs.
The course is aimed at machine learning engineers and gen AI engineers. You should know Python, gen AI prompt engineering and gen AI tool use. Testing and evaluation of models is not covered.