Anthropic introduces the security, privacy, and credential-isolation design of the Claude Duet agent
Claude Duet Safety, Privacy, and Security
AI BriefingAnthropic published an overview of the security and privacy design of the Claude Duet agent, currently in research preview. Important actions such as sending messages, making payments, and deleting items require user confirmation on an approval card. A classifier independent of the model checks whether an action matches the user's intent. Passwords, cookies, and login tokens do not pass through the model, and payments use one-time virtual cards. Sensitive information is divided into two levels: never share and share only with consent, with an independent classifier checking it before transmission.
Source: Claude: Blog · claude.com
Event follow-up3
View all event coverage- Claude Duet sends invitations to all US Pro, Max, and Ultra subscribers on the waiting listAdo Kukic · 3 days ago
- Anthropic introduces the security, privacy, and credential-isolation design of the Claude Duet agentClaude:Blog · 24 days ago
- Anthropic launches the Claude Duet research preview, with Claude taking over daily work as a proactive agent.Claude:Blog · 26 days ago