Deploy Multi-Agent Systems with Agent Development Kit (ADK) and Agent Engine
Deploy Multi-Agent Systems with Agent Development Kit (ADK) and Agent Engine
In this course, you’ll learn to use the Google Agent Development Kit to build complex, multi-agent systems. You will build agents equipped with tools, and connect them with parent-child relationships and flows to define how they interact. You’ll run your agents locally and deploy them to Vertex AI Agent Engine to run as a managed agentic flow, with infrastructure decisions and resource scaling handled by Agent Engine.
Please note these labs are based off a pre-released version of this product. There may be some lag on these labs as we provide maintenance updates.
Informações sobre o curso
Objetivos
- Build an agent with tools using the Google Agent Development Kit.
- Establish interaction patterns between multiple agents with parent-child relationships and flows.
- Utilize features such as session memory, artifact storage, and callbacks.
- Deploy a multi-agent app to Agent Engine.
- Query an agent app running on Agent Engine.
Pré-requisitos
A good understanding of python, gen AI prompt engineering, and gen AI tool use.
Público-alvo
Machine learning engineers and Gen AI engineers
Idiomas disponíveis
English
O que eu faço quando terminar o curso?
Ao final do curso, você pode navegar pelo conteúdo complementar do programa de aprendizado ou conferir nosso catálogo.
Quais selos eu posso ganhar?
Ao terminar um curso, você receberá um selo de conclusão. Os selos são exibidos no seu perfil e podem ser compartilhados nas suas redes sociais.
Tem interesse em participar desse curso com um dos nossos parceiros?
Confira o conteúdo do Google Cloud no Coursera e no Pluralsight.
Prefere aprender com um instrutor?