Edited by Paul Derrington, Chief Editor
TL;DR
Anthropic opened a research preview of Claude Duet on October 21: a standalone app where Claude works as a proactive agent instead of waiting for a prompt. It sends a morning brief on what needs your attention across your connected apps, checks them every few hours, takes on tasks you hand it by message, and asks before it sends a message, makes a payment, signs a document, or deletes anything. The preview is waitlisted for US Pro and Max subscribers, runs on Opus 5.5, and its background work counts against the same plan limits as chat.
What Duet is
Claude Duet is a separate app for iOS and Android, also available on the web at claude.ai. You message it the way you would message a person, by text or voice, in one ongoing thread. It carries over the memory, skills, and connected apps from your existing Claude account, and Anthropic says it works with more than 6,000 connectors and plugins in the Claude Marketplace, including Gmail, Slack, QuickBooks, and Shopify.
The difference from ordinary chat is who starts. Each morning Duet sends a short brief on the most important items across your connected apps. Through the day it checks those apps every few hours and messages you only when something needs your attention. Anthropic says it does not check nonstop because that would burn through plan limits much faster.
What it can do
Duet runs on its own computer in the cloud, with its own browser, so tasks keep going after you close the app or put your phone down. Anthropic's examples run from scheduling meetings to building dashboards, financial and sales forecasts, prototypes, and web apps. For people running a small business, its examples are concrete: finding unpaid invoices and drafting the reminders, preparing payroll for review, and getting contracts ready to send.
It can also make purchases through Stripe's Link wallet and Shopify's Shop Pay. Every one of those consequential steps sits behind the approval gate described below, and MacRumors calls Duet Anthropic's answer to Meta's Muse agent and OpenAI's Dots agent, both already proactive agents.
The guardrails
Duet is designed to ask before it acts on your behalf. Anthropic's product page says it waits for your approval before sensitive operations like sending messages or paying, and the same gate covers signing a document or deleting anything. Approvals, logins, and safety checks run inside your own cloud computer, and Anthropic says Duet does not see your passwords or logins when it works in connected accounts.
Anthropic's announcement adds two harder lines: trading securities and moving money between accounts are off-limits even with approval, and a dedicated classifier is built to refuse requests that would share credit card numbers or government identification. Health and personal finance details go out only when the user has explicitly told Duet to send them.
The catch
This is a research preview, with the limits that implies. Access is by waitlist, US only, and only for Pro and Max subscribers; Team and Enterprise plans are not included yet. It costs nothing extra, but it shares your plan's existing usage limits, and Anthropic warns background checks count toward them, so heavy users may hit their caps sooner than with chat alone.
Anthropic is also plain about the judgment problem: Duet may misread a thread or miscalibrate what is urgent, and it can miss something that arrives between checks. An agent that messages you first lives or dies on whether it interrupts at the right moments. That part is unproven, and the preview is how Anthropic intends to find out.