# Always-on agents on Claude Managed Agents: what Anthropic's docs cover and what Source: https://farcaster.xyz/kazani/0xf36b0bf5 Kiwi News: https://news.kiwistand.com/stories/Always-on-agents-on-Claude-Managed-Agents-what-Anthropics-docs-cover-and-what?index=0x6afdd2db8644facf4724cb41c745d861f6a9ef8a2c2f75b9c7fe63310831fe352a74e80d Submitted by 0xkazani.eth on 2026-11-18 UTC, 1 upvote, 0 comments ## Summary Anthropic published a guide to always-on agents on 13 Nov, written by William Hu. Its central point is that an always-on agent is not really always on: it wakes when an event arrives, does a short run, saves what it learned, and goes back to sleep. Hu breaks the design into five parts: an event inbox, timers, memory, permissions, and an outbox. ## Article Always-on agents on Claude Managed Agents: what Anthropic's docs cover, and what's still on you On 13 Nov, Anthropic published a guide to always-on agents by William Hu. An always-on agent isn't really always on. When an event arrives, it wakes and does a short run. Afterward, it saves what it learned and goes back to sleep. Hu breaks the design into five parts: **_an event inbox, timers, memory, permissions, and an outbox._**