From Foundations to Deployment: A Full-Stack Guide to Multi-Agent Systems

Hands-On Training

Duration: 1 hour

This session explores how to design, build, and deploy multi-agent systems (MAS) using Google's Agent Development Kit (ADK) and the Agent-to-Agent Protocol (A2A).

We'll begin with foundational concepts of MAS, including how agents coordinate, communicate, and collaborate using different architectural patterns—sequential, parallel, loop, and hierarchical routing. Then, we'll dive into practical implementation strategies using ADK, showcasing how to compose workflows, build memory-aware agents, and define custom tools. Finally, we’ll unpack the Agent-to-Agent (A2A) protocol, a powerful standard that enables agents to discover, invoke, and collaborate with external agents securely using a standardized metadata format and JSON-RPC.

This session is ideal for AI developers, ML engineers, and technical architects building intelligent applications. Attendees will leave with a clear understanding of how to construct agentic workflows and leverage multi-agent orchestration to solve real-world problems—from research assistance to developer tooling.

Hands-On Training

Duration: 1 hour

This session explores how to design, build, and deploy multi-agent systems (MAS) using Google's Agent Development Kit (ADK) and the Agent-to-Agent Protocol (A2A).

We'll begin with foundational concepts of MAS, including how agents coordinate, communicate, and collaborate using different architectural patterns—sequential, parallel, loop, and hierarchical routing. Then, we'll dive into practical implementation strategies using ADK, showcasing how to compose workflows, build memory-aware agents, and define custom tools. Finally, we’ll unpack the Agent-to-Agent (A2A) protocol, a powerful standard that enables agents to discover, invoke, and collaborate with external agents securely using a standardized metadata format and JSON-RPC.

This session is ideal for AI developers, ML engineers, and technical architects building intelligent applications. Attendees will leave with a clear understanding of how to construct agentic workflows and leverage multi-agent orchestration to solve real-world problems—from research assistance to developer tooling.

Hands-On Training

Duration: 1 hour

Move beyond theory and learn to build, test, and deploy production-grade AI agents in this intensive 1-hour training. We will explore Google's complete agentic stack, guiding you through the modern workflow for creating and scaling agentic systems.

Using the open-source Agent Development Kit (ADK), you'll learn to construct a capable agent, grounding it with relevant information via the Model Context Protocol (MCP). Next, you’ll learn how to take that agent from your local machine to a global scale by deploying it on the managed Vertex AI Agent Engine. Once managed by the engine, we'll unlock collaborative agents, showing how to enable communication between agents using the Agent2Agent (A2A) protocol. You'll leave this session understanding the full lifecycle: building locally, deploying for production, and then enabling multi-agent collaboration.

Annie Wang

Developer Relations Engineer at Google Cloud

Annie Wang is a Developer Relations Engineer at Google Cloud, where she helps developers build with AI on Google Cloud. With 6 years of experience as a software engineer and a passion for making complex topics accessible, Annie bridges engineering and education through technical talks, hands-on workshops, and community events.

Ivan Nardini

Ivan Nardini is a Developer Relations Engineer on Google’s Cloud team, focusing on Artificial Intelligence and Machine Learning. He enables developers to build innovative AI and ML applications using their preferred libraries, models, and tools on Vertex AI, through code samples, online content, and events. Ivan has a master degree in Economics and Social Sciences from Università Bocconi and he attended a specialized training in Data Science from Barcelona Graduate School of Economics.