Use these documents to help inform the creation of a Google Cloud agentic AI architecture and deployment:
- Choose a design pattern for your agentic AI system: Guidance to build a distinct framework for organizing a system's components, integrating the model, and orchestrating a single agent or multiple agents to accomplish a workflow.
- Multi-agent AI system in Google Cloud: An example reference architecture to help you design robust multi-agent AI systems in Google Cloud.
- Develop an Agent Development Kit agent: An example of how to use the Agent Platform SDK for Python to develop an Agent Development Kit (ADK) agent, define the model, add tools, and manage sessions and memories.
- Multi-tool agent - Agent Development Kit: Guidance to install Agent Development Kit (ADK) and then set up an agent with multiple tools.
- Multi-agent private networking patterns in Google Cloud: Information about how to design private networking infrastructure that supports a publicly accessible, multi-agent, Gemini Enterprise app with private connections between agents, subagents, and tools.
- Choose your agentic AI architecture components: Guidance for how to evaluate the characteristics of an application and workload in order to choose appropriate products, services, and tools that best suits your needs.
- Use automatic registration: Information about how to enable discovery for agents on supported runtimes.
- Build and deploy an AI agent to Cloud Run using the Agent Development Kit (ADK): An example of how to build and deploy an AI agent to Cloud Run using ADK for Python.
- AI and ML perspective: Security: An overview of principles and recommendations to help ensure that AI and ML deployments meet security and compliance requirements.
- AI and ML perspective: Reliability: An overview of the principles and recommendations to design and operate reliable AI and ML systems on Google Cloud. It describes how to integrate advanced reliability practices and observability into your architectural blueprints.
- AI and ML perspective: Operational excellence: An overview of the principles and recommendations to build and operate robust AI and ML systems on Google Cloud. These recommendations help you set up foundational elements like observability, automation, and scalability.
- AI and ML perspective: Cost optimization: An overview of principles and recommendations to optimize the cost of AI systems throughout the ML lifecycle.
- AI and ML perspective: Performance optimization: An overview of the principles and recommendations to help you optimize the performance of AI and ML workloads on Google Cloud. These recommendations help you make decisions about factors like the model architecture, parameters, and training strategy.
- Well-Architected Framework: Sustainability pillar: Provides recommendations to design, build, and manage workloads in Google Cloud that are energy-efficient and carbon-aware.
- Gemini Enterprise Agent Platform Language support: Details the supported languages for Gemini Enterprise Agent Platform.
- Agent Gateway overview: An overview of Agent Gateway, which is the networking component of the Gemini Enterprise Agent Platform ecosystem.
- agents-cli overview: Information and FAQ for the Agents CLI and skills for building agents on Gemini Enterprise Agent Platform.
- agents-cli development guide: The full development workflow for Agents CLI, from defining what to build to monitoring it in production.