{"version":1,"type":"story","url":"https://digestai.news/story/amazon-quick-defines-four-agentic-primitives-based-on-when-what-who-an","json":"https://digestai.news/story/amazon-quick-defines-four-agentic-primitives-based-on-when-what-who-an.json","markdown":"https://digestai.news/story/amazon-quick-defines-four-agentic-primitives-based-on-when-what-who-an.md","slug":"amazon-quick-defines-four-agentic-primitives-based-on-when-what-who-an","headline":"Amazon Quick defines four agentic primitives based on When, What, Who, and How","summary":"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.\n\nTriggers 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.\n\nThe 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.","keyPoints":["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"],"whyItMatters":"A common taxonomy lets developers design, share, and audit AI agents more consistently, reducing confusion and accelerating building of reliable, scalable agentic applications.","category":{"slug":"agents","name":"Agents & Tools","url":"https://digestai.news/category/agents"},"entities":{"companies":["Amazon"],"models":[],"people":[]},"firstPublishedAt":"2026-11-06T17:34:45Z","updatedAt":"2026-11-06T17:34:45Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"AWS Machine Learning Blog","title":"Taxonomy of agentic primitives in Amazon Quick","url":"https://aws.amazon.com/blogs/machine-learning/taxonomy-of-agentic-primitives-in-amazon-quick","publishedAt":"2026-11-06T17:34:45Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Amazon Quick defines four agentic primitives based on When, What, Who, and How\", 6 November 2026, https://digestai.news/story/amazon-quick-defines-four-agentic-primitives-based-on-when-what-who-an","publisher":"Digest AI","title":"Amazon Quick defines four agentic primitives based on When, What, Who, and How","datePublished":"2026-11-06T17:34:45Z","url":"https://digestai.news/story/amazon-quick-defines-four-agentic-primitives-based-on-when-what-who-an"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}