What Is Claude Duet?
Claude Duet is Anthropic’s new personal AI agent, launched as part of a research preview. It is designed to work proactively on your behalf, bringing tasks to your attention and completing them even when you step away.
Anthropic describes Claude Duet this way: it comes to you with what needs your attention, completes tasks you ask of it, keeps working even when you step away, and checks with you before it acts on your behalf.
For now, access is limited. You need to join a waitlist that is only open to Claude subscribers in the US to try the new tool.
How Claude Duet Works
Each day, Claude Duet generates a short briefing with a list of action items drawn from your connected apps. You can also hand it tasks of all shapes, from simple administrative work like scheduling meetings to more complex projects such as building dashboards with dozens of tools, creating financial or sales forecasts, prototyping, and building web apps.
According to Anthropic, Claude Duet will only message you when something requires your attention.
The agent runs on Opus 5.5, one of the models Anthropic offers through Claude. Anthropic is also releasing standalone Android and iOS apps for people to use Claude Duet. You do not need to keep a Claude session open at all times. The agent runs on its own virtual machine, where it can complete tasks in the background.
Pricing and Availability
One of the most notable details about Claude Duet is its pricing. Anthropic says subscribers of its $20 per month Pro plan will get access once the agent rolls out in general availability. That sets Claude Duet apart from rival agents that are currently only available to higher-tier subscribers.
Claude Duet shares usage with all your other Claude tools, including Code. That could be a recipe for the new agent to blow through your rate limits, but Anthropic at least appears to be thinking ahead.
Claude Duet checks your connected accounts every few hours, because checking nonstop would use up your plan’s limits much faster. Anthropic says it is continuing to test its judgment about when to message you and will keep tuning it based on what testers report. Users will also be able to set how frequently Claude Duet messages them and in relation to what topics.
Security and Privacy Protections
On the security side, Anthropic says Claude Duet incorporates a new classifier and system prompt designed to prevent it from leaking sensitive information. According to Anthropic, Claude Duet will never directly see your passwords or sign-in tokens. Information that might relate to your health or personal finances is only let through if you explicitly tell Claude Duet to share it.
Anthropic said it would have more information about Claude Duet’s safety protections to share in the coming days.
What Claude Duet Means for Users
How much you get out of Claude Duet will depend on how much you trust Anthropic. Context is everything to AI models, and for some people, sharing their entire digital life with an AI agent is simply too much to ask.
The appeal is clear, though. A proactive agent that checks your apps, surfaces what matters, and handles tasks in the background could save real time. The trade-off is the level of access you are willing to grant.
Claude Duet marks Anthropic’s entry into the personal agent space, and it does so with a notably accessible price point for Pro subscribers. With standalone apps, background task execution, and a focus on only interrupting you when necessary, it is built to fit into daily life rather than demand constant attention. The waitlist is open now for US Claude subscribers.
