Taxonomy of agentic primitives in Amazon Quick
TL;DR
As we built Amazon Quick, its agents grew from answering questions to taking actions, and the same primitives kept getting rebuilt under different names. This post shares the taxonomy we converged on — triggers, agents, capabilities, and learned context — found by decomposing agentic work into four plain questions: When, What, Who, and How.
Nauti's Take
For a small team, the taxonomy is most useful as a design check for existing workflows: every agent needs a clear trigger, a bounded capability, and defined context. Before building anything new, map the workflow across the four primitives and verify that triggers and permissions are separated cleanly.
Sources
