Deploy Multi-Agent Systems with Agent Development Kit 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.
Course Overview
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.
What You Will Learn
- 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.
- Evaluate agents within the Agent Development Kit.
Target Audience
- Machine learning engineers and Gen AI engineers
Detailed Syllabus
- Basics of building an agent in the Agent Development Kit.
- Explain how the Agent Development Kit compares to other tools such as the Google Gen AI SDK or LangChain.
- Describe the parameters used to build an agent in Agent Development Kit.
- Enhance agents with tools and cover the growing breadth of available tools.
- Discuss the importance of structured docstrings and typing when writing tool functions for agents.
- Demonstrate the ability to provide tools to an agent.
- List common and useful tools available for the Agent Development Kit agents, including LangChain tools.
- Lab, Get started with Agent Development Kit (ADK)
- Lab, Empower ADK agents with tools
- Manage communication and task-sharing between agents through parent-child relationships and flows to enable coordinated responses to queries.
- Describe the directory structure and naming conventions encouraged by the Agent Development Kit.
- Demonstrate the ability to create multiple agents and relate them to one another with parent-child relationships.
- Describe the different flow options and when you might use them.
- Get responses that have passed through multiple agents.
- Control content at different points with callbacks.
- Lab, Build multi-agent systems with ADK
- Deploying agent apps to Agent Engine and querying responses.
- Describe the benefits of deploying agents, especially multi-agent systems, to Agent Engine over self-hosting, such as in Vertex AI online predictions.
- Demonstrate deploying to Agent Engine.
- Demonstrate querying a deployed agent app.
- Lab, Deploy ADK agents to Agent Engine
- Evaluate agents within the Agent Development Kit.
- Use the web interface to view evaluations.
Request In-Company Training
Private cohort scheduled for your engineering team with customized hands-on labs and enterprise pricing.
- Flexible dates and times for your team
- Hands-on labs in official Google Cloud environment
- Official certificates of completion issued
Accelerate Your Cloud Transformation
Talk directly with our curriculum advisors to design a custom training track for your team.