Skip to content
latestai.eulatestai.eu
CD

Claude Duet

by Anthropic

Anthropic's proactive agent app that monitors connected apps, sends briefs and completes tasks on its own virtual machine.

Updated EU status checked Last shown

Claude Duet at a glance

What is Claude Duet?
Claude Duet is an agent from Anthropic. Anthropic's proactive agent app that monitors connected apps, sends briefs and completes tasks on its own virtual machine.
Who makes Claude Duet?
Claude Duet is made by Anthropic.
Does Claude Duet work in the EU?
Not in the EU. Anthropic states the research preview starts "with Pro, Max, and Ultra users in the US" via waitlist; no EU/EEA rollout is announced in the provided material. Last verified 14 Nov 2026.
How much does Claude Duet cost?
Paid. Research preview included in Pro ($20/mo, $17 with annual billing), Max ($100/mo) and Ultra ($200/mo) plans; same usage limits as the rest of Claude. Waitlist access. Licence: Proprietary.
Where was Claude Duet shown?
In 2 creator videos by AI Search, Matt Wolfe. Most recently by AI Search on 25 Oct 2026, at 34:12 in “Cybersecurity chaos, AI for DNA, Kimi K3.1, Claude Duet, Dessa, Fibo 2, Minimax 3.1: AI NEWS”.

Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.

About

Claude Duet is a research-preview app from Anthropic in which Claude acts as a proactive agent. It sends a short morning brief on the most important items across connected apps, checks those accounts every few hours, and messages the user only when something needs attention. Users can also hand it tasks by text or voice in a single ongoing thread, from scheduling meetings to building dashboards, financial or sales forecasts, prototypes and web apps.

It is designed around Claude Opus 5.5 and carries over memory, skills and connected apps from the user's Claude account. It runs on a virtual machine with its own browser, so work continues when the user's laptop or phone is off, and the user is notified when a task finishes or needs review. Anthropic says it checks with the user before acting on their behalf.

Safety measures described by Anthropic include credential handling in which the agent never directly sees passwords or sign-in tokens, an auto mode classifier approving actions, prompt-injection defenses, and a dedicated classifier and system prompt that blocks sharing the strictest tier of sensitive data (such as credit card numbers and government IDs). Health or finance data is shared only on explicit instruction.

It is available as a standalone iOS and Android app and on claude.ai, included in Pro, Max and Ultra plans with the same usage limits as the rest of Claude. Access is by waitlist, starting with US users only.

Key features
  • Daily morning brief across connected apps
  • Proactive monitoring that messages only when attention is needed
  • Runs tasks on its own virtual machine with a browser, even when devices are off
  • Text or voice interaction in one ongoing thread
  • Carries over memory, skills and connectors from the user's Claude account
  • Built-in safeguards: credential isolation, action classifier, sensitive-data classifier
2 moments

As seen on YouTube

Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.

Keep exploring

Similar AI tools

Closest neighbours by meaning, not just by category.