- Course overview
- Course details
- Prerequisites
Course overview
About this course
In this course, you will use your knowledge of developing agents using Agent Development Kit to productionize agents using Google's Agentic Stack on Google Cloud. After reviewing the agentic stack and different deployment targets, you will build an agent using session, memory and example services available within Google Cloud. You will integrate external tools using Model Context Protocol (MCP) and communicate with other agents using Agent2Agent (A2A) protocol. Finally, you will design applications with human-agent interaction in mind.
Audience
• Generative AI developers
• AI engineers
• Agentic system architects
Course details
Module 1: Reviewing Google’s Agentic Ecosystem
• Agentic stack overview
• Models and the “brain” of the agent
• The Agent Development Kit (ADK)
• Open source libraries and protocols
• Deployment targets
Module 2: Managing Context with Session, Memory, and Examples
• Sessions: Current conversation context
• Memory: Cross-session context
• Example Store: Example database
• Activities Lab: Building an ADK Agent with Session, Memory, and Example Services
Module 3: Leveraging Model Context Protocol (MCP)
• MCP Fundamentals
• Using MCP with ADK
• Activities Lab: Use Model Context Protocol (MCP) Tools with ADK Agents
Module 4: Building Agent2Agent (A2A) Multi-Agent Solutions
• A2A Fundamentals
• Leveraging A2A in ADK
• Lab: Connect to Remote Agents with ADK and the A2A SDK
Module 5: Designing Human-Agent Interactions
• Communicating with agents
• Access control
• Building client experiences
• Lab: Implementing End-User Interfaces for Agents on Google Cloud
Prerequisites
- Completion of "Deploy Multi-Agent Systems with Agent Development Kit and Agent Engine" or equivalent knowledge
- Python
- Prompt engineering
- Agent Development Kit
Enquiry
Course : Build Production-Ready Agents on Google Cloud
Enquiry
request for : Build Production-Ready Agents on Google Cloud
