Claude Duet: Anthropic's agent app that flags what matters and asks before it acts
What is it?
Claude Duet is a separate app where Claude reaches out first. Every morning it sends a short brief on what matters across your connected apps (Gmail, Slack, QuickBooks and others). Tasks you hand it keep running on its own virtual machine and browser, so your laptop can be off. It runs on Opus 5.5 and pulls in the memory, skills and connectors from your existing Claude account. It's on iOS, Android and claude.ai.
Why does it matter?
Before it sends a message, pays, signs or deletes anything, it shows you exactly what it will do and waits for approval. Trading securities and moving money between accounts are off-limits even if you approve. Credentials follow the Managed Agents design, so it never sees your passwords, and a dedicated classifier blocks card numbers and government IDs from leaking. If you're building an assistant-style agent, the safeguards are worth reading as a reference design. Note that its background checks, which run every few hours, count against your plan's usage limits.
Maturity
WaitlistResearch preview, open only through a waitlist for US Pro and Max subscribers. Anthropic says it can still misjudge what's urgent.
How to track it
- Rollout: watch claude.com for the waitlist expanding beyond the US or to Team and Enterprise plans.
- Safety design: read the detailed safety write-up Anthropic says it will publish in the coming days.
- Usage: see how much of the Pro and Max limits the background checks eat, from early user reports.