Anthropic launches Claude Duet, an always-on agent that asks approval for risky steps
AIAnthropic has released Claude Duet as a research preview, a standalone app that runs Claude as a proactive agent working on tasks while the user is away. It asks approval before sending messages, making payments, signing documents, or deleting anything, and it cannot trade securities or move money between accounts.
Loading source posts…
This story is featured in top picks: “Anthropic launches Claude Duet, a proactive agent research preview”
Source details
The Decoder · Maximilian Schreiner · the-decoder.comPublished
Original title: Anthropic takes on Grok Bot, Meta's Muse, and OpenAI's Dots with its always-on agent "Claude Duet"