// AI news · 2026-11-07 · AWS Machine Learning Blog
Amazon classifies agentic primitives for Quick
Amazon introduces a taxonomy of agentic primitives for Quick, decomposing work into When, What, Who, and How.
Published 2026-11-07 01:34 (Beijing time)Source AWS Machine Learning BlogAuto-summarised, fact-checked against source
01Summary
Triggers initiate tasks with instructions; agents are persistent, learning entities with instructions, capabilities, and learned context. Capabilities include tools, skills, and sub-agents, updated dynamically. Learned context accumulates usage patterns, enabling improved performance over time.
Summarised from the original article by an open-source model, then checked automatically: every number and English name must appear in the source. The original article is authoritative.
02Key points
- Triggers initiate tasks with instructions: user input, delegation, scheduling, or event-driven.
- Agents are persistent, learning entities with instructions, capabilities, and learned context.
- Capabilities include tools, skills, and sub-agents, dynamically updated.
- Learned context accumulates usage patterns to improve future performance.
03Source
Taxonomy of agentic primitives in Amazon Quick
AWS Machine Learning Blog · published 2026-11-07 01:34 Beijing time
05Related news
- Same source · Govern AI Agent Access with Okta and AgentCore2026-11-07 · AWS Machine Learning Blog
- Same source · Deep Insight Implements Four-Layer Context Engineering2026-11-05 · AWS Machine Learning Blog
- Same topic · Google Launches Storage-Optimized Z4M Instances for AI/ML Workloads2026-11-07 · Google Cloud
- Same topic · Meta launches 'spaces' in Muse AI2026-11-07 · The Verge
- Same day · Midterm Blue Wave May Reshape AI Industry2026-11-07 · TechCrunch AI
From AIMap AI news: collected from 1,100+ official and media sources. Summaries only restate the original article; follow the link for the full story. All stories of 2026-11-07 · Archive by date · All AI news · Today