Cloud Hero: Building AI Agents with ADK & Gemini

This game utilizes the Agent Development Kit (ADK) to build and orchestrate multi-agent systems using specialized agents for modular coordination. You will equip these agents with Agent Search, Google Search, and custom function tools to extend their capabilities. The process includes implementing a reasoning layer that communicates with remote MCP servers and deploying these agentic applications to Cloud Run and Gemini Enterprise Agent Platform. To ensure output quality, you will evaluate agent performance using the Agent Platform Generative AI Evaluation Service. Finally, you will develop a root agent architecture to manage sub-agents, handle session states, and retrieve values for complex instructions.

The achievement of training objectives is evaluated at multiple levels to ensure quality:

• Continuous Knowledge Assessment : Verification of knowledge throughout the training via participatory methods (quizzes, practical exercises, case studies) under instructor supervision.
• Progress Measurement : Comparative self-assessment system including an initial diagnostic to determine the starting level, followed by a final evaluation to validate skills development.
• Quality Evaluation : End-of-session satisfaction questionnaire to measure the relevance and effectiveness of the training as perceived by participants.