Building scalable AI agents: Design patterns with Agent Engine on Google Cloud

Explores enterprise-grade AI agent architecture patterns using Google Cloud's Agent Engine and Agent Development Kit (ADK). Covers real-world implementations by system integrators like Deloitte and Quantiphi, demonstrating multi-agent systems with Model Context Protocol (MCP) for data integration and Agent-to-Agent (A2A) protocol for inter-agent communication. Provides a reference architecture for building scalable agentic systems with persistent memory, session management, and observability features deployed on Vertex AI Agent Engine.