Claude Duet research preview for Pro and Max plans
By Steven Van ·
Anthropic's proactive agent app is on a waitlist for US Pro and Max subscribers, on iOS, Android and claude.ai, sharing the usage limits of the rest of Claude.
Claude Duet, a new app where Claude works as a proactive agent, is now in research preview for Claude Pro and Max subscribers in the US. Access is by waitlist, and Anthropic says it will email people as soon as the app is ready for them.
What it does
Claude Duet is available as a standalone app on iOS and Android, and on claude.ai. It is built around Claude Opus 5.5 and aimed at professionals and small business owners. It sends a short morning brief on the most important items across connected apps, then messages again during the day only when something needs attention. Tasks can be handed over in one ongoing thread by typing or voice, from scheduling meetings to building dashboards, forecasts, prototypes and web apps.
How it works
- Memory, skills and connected apps carry over from your Claude account.
- Claude Duet runs on a virtual machine with its own browser, so work continues when your laptop or phone is off. A notification arrives when a task is done or needs review.
- It checks connected accounts every few hours, not continuously, to avoid using up plan limits faster. You can say what you want to hear about and how often.
- It can use the 6,000+ connectors and plugins in the Claude Marketplace, including Gmail, Slack, QuickBooks, Stripe, Gusto, Docusign, HubSpot, Canva and Shopify.
- For purchases, it can pay through Link, Stripe's digital wallet, using a virtual card, or check out with Shop Pay. Sign-in with saved 1Password logins is listed as coming soon.
Approvals and safeguards
Claude Duet reads, drafts and prepares work on its own. Before it sends a message, makes a payment, signs a document or deletes anything, it shows what it is about to do and waits for approval. Trading securities and moving money between accounts are off-limits even with approval. Any connected app can be disconnected.
Anthropic says Claude Duet never directly sees passwords or sign-in tokens, and that actions are approved by its auto mode classifier. A new classifier and safety system prompt are meant to reject requests to share the strictest tier of information, such as credit card numbers and government identification. Health or personal finance details are sent only when explicitly instructed. The app was red-teamed and penetration tested by an external firm, and is covered by Anthropic's public bug bounty program.
Limits of the preview
Claude Duet uses the same usage limits as the rest of Claude, and background checks count toward them. Larger tasks such as financial models or decks need more model turns and background work. Anthropic says it can misread a thread or miscalibrate urgency, that personal errands such as booking tickets are weaker, and that it cannot yet show its browser. For now it lives in its own app, separate from the main Claude app.
