Anthropic previews Claude Duet, a proactive agent powered by Opus 5.5
Claude Duet lets users delegate tasks to an autonomous agent that can keep working in a virtual machine while they are away.
Anthropic previews Claude Duet, a proactive agent powered by Opus 5.5
This app lets Claude — specifically Opus 5.5 — act as a proactive agent that carries out instructions and continues working while you are away.
It can handle tasks ranging from very simple to long and complex, including meeting planning, dashboard and forecast creation, and software development.
The agent runs on its own virtual machine with a browser and can use any application. When you first use it, it migrates memory, skills and connectors from your Claude account, so there is no lengthy setup.
Access is currently limited to a waitlist.
Why it matters
AnalysisIt marks a move from conversational AI toward persistent, autonomous agents that can operate digital workspaces. For teams, the key questions become oversight, security, permissions and cost.
Discuss in community
Share your questions and insights with developers
Related in Ecosystem
Practical guides, core terminology, and agent skills
Anthropic introduces Claude Duet on Opus 5.5 as rival to Dots and Grok Bot
Anthropic has unveiled Claude Duet, an Opus 5.5-based AI agent with its own VM, browser, and thousands of connectors. It is currently a preview for U.S. Pro and Max subscribers.
Claude Code Projects: How a Single AI Orchestrates a Team of Autonomous Agents
A deep dive into Claude Code Projects: Coordinator and Threads architecture, parallel branches, shared memory via MEMORY.md, and cloud agent management.
Claude’s internal model helped scientists design a protein that could become a scorpion toxin antidote
Anthropic and Citrini Research used Claude to generate and screen candidate proteins that bind scorpion toxins, producing a lab-validated shortlist in about three days.
Computer Use via AI
Anthropic's technology (introduced in Claude 3.5 Sonnet) enables neural networks to control operating systems like a human: taking screenshots, analyzing window coordinates, moving the mouse cursor, clicking buttons, and entering text without using specialized APIs.
Constitutional AI (RLAIF)
A behavior alignment method developed by Anthropic (creators of Claude). Instead of relying on millions of hours of human labor, the model critiques and corrects its own responses based on a clear set of ethical principles ('Constitution').
15 Prompts for Creating Agents in Claude Code
Claude Code can work not only through the main dialogue but also via subagents — separate configurations with their own system prompt, a limited set of tools, and, if necessary, a...