Anthropic launches Claude Duet, a proactive AI agent for professionals
Anthropic has launched Claude Duet, a proactive AI agent designed for professionals and small business owners. Powered by its Opus 5.5 model, Duet operates on a dedicated cloud virtual machine to manage tasks across connected apps. Currently in research preview for US-based Pro and Max subscribers, the tool sends daily briefings and alerts only when attention is required. It positions itself as a direct competitor to Meta’s Muse and OpenAI’s Dots, aiming to streamline complex administrative workflows.
Key points
- Anthropic, the developer of the Claude AI models, announced Claude Duet on October 21, 2026, as a proactive agent for professionals and small business owners.
- The agent is powered by Anthropic's Opus 5.5 model and operates on a dedicated cloud virtual machine with a browser, allowing it to work in the background without requiring an active local session.
- Claude Duet is available as a research preview to US-based Pro and Max plan subscribers via a waitlist, with access included in existing usage limits and no additional cost.
- The tool sends a morning brief on important items from connected apps and alerts users only when specific attention is needed, handling tasks ranging from scheduling to building web apps.
- Safety features include a dedicated classifier to prevent data leaks and mandatory user approval for sensitive actions like sending payments or deleting files before execution.
- The launch positions Claude Duet as a direct competitor to Meta’s Muse and OpenAI’s Dots, with plans to expand availability to Team and Enterprise plans in the future.
Anthropic has introduced Claude Duet, a new proactive AI agent designed to assist professionals and small business owners in managing their digital workflows. Announced on October 21, 2026, the tool is currently available as a research preview to US-based subscribers of the company’s Pro and Max plans. Access is being rolled out via a waitlist, and the agent is included in existing subscription usage limits without additional fees.
Built around Anthropic’s Opus 5.5 model, Claude Duet operates on a dedicated cloud virtual machine equipped with a browser. This architecture allows the agent to perform tasks in the background, even when the user is not actively interacting with the application. The agent integrates with existing Claude accounts to leverage user memory, skills, and connected apps, eliminating the need for extensive setup. It provides a daily morning brief summarizing important items and monitors connected applications throughout the day, sending alerts only when specific attention is required.
The agent is capable of handling a wide range of tasks, from simple administrative duties like scheduling meetings to complex projects such as building dashboards, creating financial forecasts, and prototyping web applications. To ensure safety and user control, Claude Duet includes a dedicated classifier to guard against sensitive data leaks and requires explicit user approval before executing high-impact actions like sending payments or deleting files. All interactions occur within a single ongoing thread, allowing users to review and steer the agent’s work easily.
The launch positions Claude Duet as a direct competitor to Meta’s Muse and OpenAI’s Dots, both of which have recently gained popularity as proactive AI assistants. While currently limited to individual US subscribers, Anthropic plans to expand availability to Team and Enterprise plans in the future. The tool aims to help users prioritize their time by automating routine tasks and providing judgment-based alerts, allowing them to focus on more ambitious projects.
Sources
The WireByte editorial team synthesises technology news from multiple primary sources, verifies the facts, and links every source. Articles are produced with AI assistance and reviewed under our editorial policy.
