Anthropic has opened a waitlist for Claude Duet, a new app in which Claude works as a proactive agent instead of waiting for a prompt. The research preview, announced on 21 October, starts with Pro and Max subscribers in the US.

Claude Duet is aimed at professionals and small business owners who have more to track than they can manage. It runs as a standalone app on iOS and Android and on claude.ai, is included in Pro and Max plans, and shares usage limits with the rest of Claude. Anthropic says it is built around Claude Opus 5.5.

How Claude Duet works as an AI agent

Each morning, the app sends a short brief on the most important items across a user’s connected apps. During the day it messages only when something needs attention. It checks accounts every few hours rather than continuously, because constant checking would use up plan limits much faster.

Users can also hand it tasks, from scheduling meetings to building dashboards, sales or financial forecasts, prototypes and web apps. Claude Duet runs on a virtual machine with its own browser, so it keeps working when the user’s laptop or phone is off, and it sends a notification when a task is done or needs review. Memory, skills and connected apps carry over from the user’s Claude account.

Connectors and payments

Claude Duet can draw on more than 6,000 connectors and plugins in the Claude Marketplace. Anthropic’s examples include:

• Gmail and Slack: finding missed messages and helping to reply
• Intuit QuickBooks and Stripe: checking unpaid invoices and drafting reminders
• Gusto: preparing and running payroll, with hours, bonuses and reimbursements filled in
• HubSpot: drafting follow-up emails from contact and deal history
• Docusign: preparing agreements and sending them for review and signature
• Canva: turning a product launch into a social campaign
• Shopify: setting up, designing and managing a store

For purchases, Claude Duet can use Link, Stripe’s digital wallet, which pays with a virtual card so the real card number is not shared. It can also check out at online stores through Shop Pay. Signing in with logins saved in 1Password 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 the user what it is about to do and waits for approval. Trading securities and moving money between accounts are off-limits even with approval.

Anthropic has also added a dedicated classifier and safety system prompt that check each message for leaks of sensitive information. They are designed to reject requests to share the strictest tier, including credit card numbers and government identification. Health and personal finance details go out only when the user explicitly tells Claude Duet to send them. Credentials are handled using the design behind Claude Managed Agents, so the app never directly sees passwords or sign-in tokens. Red teams and an external firm penetration tested the product, and it is covered by Anthropic’s bug bounty programme.

Early testers and current limits

Anthropic staff have been using the app internally. Karan Ahuja, who leads the Claude Duet team, uses it to schedule user interviews, prototype and ship code. Boris Cherny, who leads Claude Code, talks through his to-do list with it on walks.

Small business owners also got early access. Amin Ebrahimi, who owns Shahs of Kabob in South Florida with about 110 employees, has used it for accounting, customer support and marketing. He said: “I don’t need to open up 100 tabs.”

Anthropic describes the release as an early version that may misread a thread or misjudge what is urgent. Personal errands such as booking tickets are weaker, since the product was built around work, and users cannot yet see its browser. Background checks and larger jobs, such as building a financial model or a deck, count towards plan limits. The announcement does not say when Claude Duet will reach markets outside the US.