Anthropic breaks down the five core components of always-on agents
Understand this story
Anthropic published an article breaking down the architecture of always-on agents: they share the same core loop as other agents, and the difference lies in five peripheral components—the event inbox, timers, memory, permissions, and the outbox. The article explains how each component is implemented one by one, and recommends using evaluations to balance the agent's message-sending frequency. The article states that the latest model has stronger judgment and lower cost for long-horizon tasks: on a long-horizon coding benchmark, Opus 5.5 costs 78% less per resolved task than Opus 5, and 40% less under typical workloads. These cost figures come from Anthropic's own claims.
AI overview based on source reports · Updated 18 hr ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Claude BlogFeaturedBuilding always-on agents
This post explains that always-on agents are stateful and proactive, running on the same core loop as other agents but surrounded by architecture built from five primitives: an event inbox, timers, memory, permissions, and an outbox. It describes how each primitive works, including inbox best practices, follow-up versus scheduled timers, memory types such as user instructions and task progress, credential proxying and deferred tool calls, and outbox delivery pacing. It concludes with how the primitives form a repeating cycle in which each brief run is triggered by an event and can set timers that wake the agent again later.
Activity for this story
- Current comparable activity
- 3
- Peak comparable activity
- 6Nov 14 04:00
- Change in the past 24 hours
- –
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.