Anthropic launches Claude Duet, a proactive agent app
Anthropic has launched Claude Duet, a proactive agent app, opening it to US Pro and Max subscribers via a waitlist. Duet checks connected accounts every few hours, runs on a cloud virtual machine with a separate browser, uses Claude Opus 5.5, and users currently cannot watch the browser operations in progress. Based on Opus 5.5's API pricing, a check that reads 40K tokens and writes 1.5K tokens costs about $0.19; six checks a day comes to about $34 a month, higher than Pro's $20 monthly price. Before sending messages, making payments, signing documents, or deleting content, Duet shows the specific action and waits for approval; securities trading and transfers between accounts remain prohibited even with approval.
Why read this
SelectedAI score 76
The original article lists Duet's check frequency, approval process, and cost estimates, so readers can judge the cost and safety boundaries of proactive agents.
Topics
Body
Anthropic rolls out Claude Duet, a proactive agent application that takes on Meta’s Muse and OpenAI’s Dots
> Claude Duet checks connected accounts every few hours instead of continuously because constant checking would use up Pro and Max limits much faster, and those background checks draw on the same allowance as regular Claude chats.
> Duet runs Claude Opus 5.5 on a cloud virtual machine with its own browser, but users can’t yet watch that browser, so they see results and approval prompts rather than each step.
> at Opus 5.5’s API list price a hypothetical check reading 40K tokens and writing 1.5K tokens would cost about $0.19. 6 such checks a day would come to about $34 a month at API rates, more than Pro’s $20 monthly price
> Purchases need 2 separate approvals, with Duet confirming the item and Stripe’s Link wallet approving the spend, before Duet pays with a virtual card that keeps your real card number private.
> Before Duet sends a message, makes a payment, signs a document or deletes anything, it shows exactly what it will do and waits for approval, yet trading securities and moving money between accounts stay blocked even with approval.
> A new classifier and safety system prompt reject requests to share credit card numbers and government IDs, while health or personal-finance details go out only when the user explicitly tells Duet to send them.
> Credential handling follows the Claude Managed Agents design, so Duet never directly sees passwords or sign-in tokens, and the auto mode classifier used in Claude Code screens its actions.