{"id":1392,"kind":"story","title":"The 5 components for building an always-on AI agent, a Claude official article summarized as slides","url":"https://speakerdeck.com/minorun365/jouji-kadou-ejento-no-tsukurikata","host":"speakerdeck.com","by":"startupxo","score":0,"comments":0,"time":"2026-11-15T00:45:00.226Z","origin":"curated","language":{"source":"ko","reading":"en","translated":true},"summary":["An always-on agent is an AI that carries context across changing conversations and starts work on its own without a person watching. Its core task loop is the same as a regular agent's; the surrounding machinery is different.","In practice it sleeps most of the time. When a notification arrives it wakes up, works, leaves a record, and goes back to sleep. The article explains that it does not use tokens (the unit of AI usage) while asleep.","The surrounding components are an event inbox, a timer, memory, permissions, and an outbox. The inbox gathers requests in one place, preventing conflicts between requests that arrive at the same time and loss of requests if work is interrupted.","Permissions are named as the riskiest part. The approach introduced is that an external proxy injects credentials, a classifier blocks dangerous actions, and important decisions proceed only after user confirmation.","This is an experimental slide deck made by a Japanese presenter, Minorun, who put the URL of the official Claude blog into their own Claude Code. The Opus 5.5 cost reduction figure is also a claim from the original article."],"discussion":"https://startupxo.com/en/1392/","markdown":"https://startupxo.com/en/1392.md","api":"https://startupxo.com/api/v1/item.json?id=1392&lang=en","text":null,"edited":null,"sources":[{"site":"rss","name":"はてなブックマーク テクノロジー","url":"https://speakerdeck.com/minorun365/jouji-kadou-ejento-no-tsukurikata","score":null,"comments":null,"observed_at":"2026-11-15T06:28:46Z"}],"thread":[]}