Anthropic opens a research preview of Claude Duet, a proactive agent app built around Opus 5.5

Anthropic opened a research preview of Claude Duet on October 21, a new app in which Claude works as a proactive agent: it brings you what needs your attention, completes tasks you hand it, keeps working when you step away, and checks with you before it acts on your behalf. Access is by waitlist, starting with US Pro and Max subscribers.

WHAT ANTHROPIC SAYS IT DOES

Per Anthropic's announcement, read directly, Duet is designed around Claude Opus 5.5. It sends a short morning brief on the most important items across your connected apps, checks those accounts every few hours, and messages you only when something needs you. It runs in a virtual machine with its own browser, so your laptop or phone does not need to be on, and it carries over your Claude memory, skills and connected apps. It is a standalone app on iOS and Android, and on claude.ai.

THE PRICE

No separate fee during the preview. Duet is included in Pro and Max and draws on the same usage limits as the rest of Claude. Anthropic says Duet checks accounts every few hours rather than nonstop because constant checking would use up a plan's limits much faster.

THE GUARDRAILS

Before Duet sends a message, makes a payment, signs a document or deletes anything, it shows the action and waits for approval. Some actions are off-limits even with approval, such as trading securities or moving money between accounts. Anthropic says a new classifier refuses to share the strictest tier of information, such as credit card numbers and government IDs, and that Duet never directly sees passwords or sign-in tokens.

WHAT WE DO NOT KNOW

When access widens beyond US Pro and Max, and how quickly Duet draws down usage limits in practice. Anthropic says it will share more about Duet's safety design in the coming days. On X, @LuminaBench and @kimmonismus compared it with the always-on agents other labs already offer.