- Who
- dotey
- What
- explains the components and practices behind always-on AI agents
- Quote
这期一样一样讲清楚:它怎么醒、两件事同时来会不会打架、记忆为什么要省、要紧的事怎么等你拍板,以及为什么一开始最好让它安静一点。
What happened
Baoyu explains an always-on AI assistant through five components: an inbox that wakes it for incoming tasks, timers for proactive actions, memory files, permissions, and an outbox that controls when it speaks. The post says the assistant spends much of its time idle without calling a model or incurring costs, and previews how the setup handles simultaneous tasks, memory limits, approval for important actions, and quiet operation.
Read next
See the full storyAnthropic Outlines Five Primitives for Always-On Agents24 小时在线的 AI Agent 助理,靠这五样东西
一直在线的 AI 助理,会盯邮件、等回复、到点提醒你。可它大部分时间其实在睡觉,不调用模型,也不花钱。
Anthropic 刚发文拆开讲了这种一直在线的 Agent:
一件事进了收件箱,它才醒过来跑一次;
定时器让它没人叫也能主动;
记忆文件夹让它醒来还记得你;
权限让它拿着你的账号也不乱来;
发件箱决定它什么时候开口。
这期一样一样讲清楚:它怎么醒、两件事同时来会不会打架、记忆为什么要省、要紧的事怎么等你拍板,以及为什么一开始最好让它安静一点。
来源
- Anthropic《Building always-on agents》(2026.11.13),作者 William Hu:claude.com/resources/articles…
The story so far
Anthropic outlined five primitives for building always-on agents: an event inbox, timers, memory, permissions, and an outbox. Together, they coordinate brief runs across sessions, resume work after user input, and manage tool calls made without a person present. The post describes options for implementing the components, including durable databases or object stores for memory and a scheduler or durable execution engine for timers. Dotey separately explained the same five components through an AI assistant, saying it can remain idle much of the time without calling a model or incurring costs.
How the story developed · 2
View full event- 11/14 09:55 (UTC+8)
How Always-On AI Agents Work: Five Components Behind the Assistant This report
- 11/13 16:00 (UTC+8)Building Always-On Agents: Five Primitives for Their ArchitectureClaude Blog


