This document in the Architecture Center provides links to architecture guides that you can use to build and deploy agentic AI applications in Google Cloud.
| Architecture guide | Description |
|---|---|
| Choose a design pattern for your agentic AI system |
A design guide to help you choose a design pattern for your agentic AI system. |
| Choose your agentic AI architecture components |
A design guide to help you choose architectural components for your agentic AI applications in Google Cloud. |
| Multi-agent private networking patterns in Google Cloud |
A design guide to help you design private networking infrastructure that supports a publicly accessible, multi-agent, Gemini Enterprise application with private connections between agents, subagents, and tools. |
| Multi-agent AI system |
A reference architecture to help you design a robust multi-agent AI system in Google Cloud. |
| Multi-tenant agentic AI system |
A reference architecture to help you design a robust multi-tenant agentic AI system in Google Cloud. |
| Single-agent AI system using ADK and Cloud Run |
A reference architecture to help you design a single-agent AI system by using Agent Development Kit (ADK) and Cloud Run with Gemini and Model Context Protocol (MCP). |
| Administer interactive learning |
A high-level architecture to design a single-agent AI system that assesses a user's knowledge on a specific topic and generates a personalized learning experience. |
| Automate data science workflows |
A high-level architecture to design a multi-agent AI system that automates complex data analytics and machine learning tasks. |
| Build a borderless open data lakehouse |
A high-level architecture to build a borderless open data lakehouse that establishes a highly governed, secure pipeline from raw borderless silos to AI and agentic driven actions. |
| Build a trusted agentic system with Google Maps Platform |
A high-level architecture to build trustworthy and effective AI agents by grounding them in real-world maps and calendar data. |
| Classify multimodal data |
A high-level architecture to design a multi-agent AI system that analyzes disparate multimodal data and produces a high-confidence classification. |
| Guide technical workflows with bidirectional multimodal streaming |
A high-level architecture to build and deploy a multi-agent AI system that provides technical guidance and automated safety monitoring through a continuous, bidirectional stream of multimodal data. |
| Implement agentic analytics workflows for distributed data |
A high-level architecture for implementing cross-cloud analytics workflows that use AI agents. |
| Multimodal GraphRAG resource orchestration |
A high-level architecture to build and deploy a multi-agent AI system that consolidates fragmented multimodal data into a searchable knowledge graph. |
| Orchestrate access to disparate enterprise systems |
A high-level architecture to design an agentic AI system that orchestrates interactions with disparate enterprise systems. |
| Orchestrate security operations workflows |
A high-level architecture to build a multi-agent AI system that orchestrates complex investigation and triage processes in a security operations center (SOC). |