Amazon Quick defines four agentic primitives based on When, What, Who, and How
Amazon Quick introduces a taxonomy that breaks down agentic work into four plain questions: When, What, Who, and How. The framework groups the building blocks into triggers that start work, agents that own the execution, capabilities that describe how the work is performed, and learned context that carries lessons forward.
Key points
- Amazon Quick’s taxonomy uses four questions – When, What, Who, How – to classify agentic work
- Primitives include triggers, agents, capabilities (tools, skills, workflows), and learned context
- The shared vocabulary lets the same request be handled as a trigger, a skill, or a workflow depending on confidence needs
Triggers can be human‑initiated, agent‑delegated, scheduled, or event‑driven, each combining the activation moment and the task description. Agents are persistent, learning actors defined by instructions, capabilities (tools, skills, workflows), and accumulated memory. Capabilities span tools (atomic operations), skills (structured guidance), and workflows (deterministic coordination). The taxonomy aims to give builders a shared vocabulary so that requests like “monitor my Slack channel and send me a daily digest” can be satisfied via different combinations of these primitives, matching the user’s confidence requirements.
The post notes that this shared language makes the system easier to reason about for developers, keeps most of the framework invisible to end users, and sets the stage for future posts on the agentic operating system, background learning, and proactive feeds.
Taxonomy of agentic primitives in Amazon Quick
AWS Machine Learning Blog · 6 November 2026
Loading the full article…
This text was published by AWS Machine Learning Blog and written by Thomas Delteil. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Agents & Tools
All →- Perplexity launches Teammates agents for Perplexity Max users · 3 src
- Zapier Sidekick automates deal reports, Slack channels and more for users · 1 src
- Zapier’s Sidekick shifts AI approvals from tools to protected resources · 1 src
- OpenAI, Meta and xAI launch AI agents for long-term task delegation · 8 src
- Study finds AI agents waste 18% of tokens on unnecessary tasks · 1 src
Comments
via GitHub Discussions