Course
digicode: AFDSMA
Deploy multi-agent systems with Agent Developer Kit and Agent Engine
Learn to use the Google Agent Development Kit to build complex, multi-agent systems.
Duration
1 day
Price
850.–
exkl. 8.1% MWST
Course facts
- Building an agent with tools using the Google Agent Development Kit
- Establishing interaction patterns between multiple agents with parent-child relationships and flows
- Utilizing features such as session memory, artifact storage, and callbacks
- Deploying a multi-agent app to Agent Engine
- Querying an agent app running on Agent Engine
- Evaluating agents within the Agent Development Kit
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.
1 Get started with the Agent Development Kit
- 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.
2 Empower Agent Development Kit agents with tools
- 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
3 Build multi-agent systems with Agent Development Kit
- 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
4 Deploy Agent Development Kit agents to Agent Engine
- 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
5 Evaluate agent systems
- Evaluate agents within the Agent Development Kit.
- Use the web interface to view evaluations
- Machine learning engineers
- Gen AI engineers
Python, gen AI prompt engineering, gen AI tool use
Products:
- Agent Development Kit
- Vertex AI Agent Engine