Amazon Quick's Agent Taxonomy: When, What, Who, and How

Amazon Quick's engineering team cracked the code on building scalable AI agents by identifying four core primitives—triggers, agents, capabilities, and learned context—that stop you from reinventing the wheel every time. This breakdown transforms messy agentic work into a clean framework answering the fundamental questions: When should an agent act, What should it do, Who executes it, and How does it learn.