Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

Anthropic publishes a guide to architecting always-on AI agents

AI summary

Anthropic’s “Building always-on agents” guide presents a design architecture rather than a product launch. It divides persistent, proactive agents into five primitives: an event inbox, timers, memory, permissions, and an outbox, with each run loading memory, acting within defined permissions, updating its state, and delivering a message. The guide also says recent models have made the pattern more practical, citing an unverified vendor claim that Opus 5.5 costs 78% less per solved task than Opus 5 on one long-horizon coding benchmark.

In-depth insight

The guide gives developers a concrete implementation model for building stateful agents that operate across multiple sessions and wake in response to events or schedules.

Over the past few months, we’ve seen a resurgence of always-on agents.

Always-on agents are stateful and proactive, meaning they manage context across sessions and take actions without direct supervision. Underneath, they run on the same core loop as other agents. The difference is the surrounding architecture, which is built from primitives that control when the agents wake up, what carries over between runs, and how their work reaches the user.

The resurgence is largely due to recent model advancements, which have made always-on agents more practical to run. First, the latest models have better judgment: they’re more reliable at understanding user intent and knowing when to check in. Second, intelligence is becoming cheaper, with long-horizon tasks benefiting the most. For example, on one long-horizon coding benchmark, Opus 5.5 cost 78% less per solved task than Opus 5, compared with 40% less on typical workloads.

Customers have started to ask us how to integrate this type of experience into their own products. Some companies want to make their existing agents more proactive, while others are looking to build them from the ground up.

#Anthropic#Claude#Claude Code#Messages API#Opus 5.5#Opus 5

Original · 11 min readRead the original
Group chat

No comments yet. Start the conversation.