Agent design patterns
Reusable architectures for arranging one or many agents, and how to choose between them.
Agents
Agent guardrails
Sandboxing, permissions and input handling that bound what an agent can do.
Agent loop
The core of every AI agent: a model choosing actions in a loop until the task is done.
Context engineering
Deciding what goes into an agent’s finite context window, and when.
Model Context Protocol (MCP)
Open standard for exposing tools, resources and prompts to any compatible agent.
Source: Choose a design pattern for your agentic AI system (Google Cloud)
Google Cloud Architecture Center guide to 12 agent design patterns and how to choose between them.
Source: The Anatomy of a Modern AI Agent
Blog post mapping an AI agent as a loop plus tools, context, delegation, verification and guardrails.
Subagents
Delegating focused sub-tasks to agents with fresh context windows.
The Anatomy of a Modern AI Agent
Strip away the hype and an AI agent is a loop, some tools, and a lot of careful context management. Here’s how the pieces fit together and where the real engineering lives.
Tools
Functions an agent can call to act on the world; their design is interface design for a model.