Build Multi-Agent Systems Using Google's Agentic Stack
This 4-hour Cloud Interactive course is an interactive, instructor-led session for building multi-agent systems with Google’s agentic stack.
In Build Multi-Agent Systems Using Google’s Agentic Stack you will build and deploy a realistic multi-agent system on Google Cloud, with an agent integrated into Gemini Enterprise, to solve a customer engagement use case. The course brings together the Agent Development Kit, Model Context Protocol, the Agent2Agent (A2A) protocol, Agent Engine, Cloud Run and Gemini Enterprise.
Across three hands-on labs you will create agents with the Agent Development Kit, give them remote tools through MCP, and add guardrails for sensitive data with Model Armor and Sensitive Data Protection templates. You will enable observability with Cloud Trace and Cloud Logging, connect agents using A2A, deploy to Cloud Run and Agent Engine, and finally expose the agent to users through Gemini Enterprise.
The course is aimed at application developers, DevOps engineers, ML engineers and anyone deploying agentic applications on Google Cloud. It is an advanced course: you should have completed Deploy Multi-Agent Systems with Agent Development Kit and Agent Engine or have equivalent knowledge, and be familiar with the business domains and processes being addressed.