What Is Claude Duet? Inside Anthropic's Always-On AI Assistant

This story was originally published on HackerNoon at: https://hackernoon.com/what-is-claude-duet-inside-anthropics-always-on-ai-assistant. Claude Duet runs on a cloud VM, checks your apps every few hours and asks before anything irreversible. How it works and when a DIY agent wins. Check more stories related to machine-learning at: https://hackernoon.com/c/machine-learning. You can also check exclusive content about #ai-agents, #anthropic, #artificial-intelligence, #claude-duet, #autonomous-ai-agents, #ai-agent-automation, #ai-agent-development, #ai-workflow-automation, and more. This story was written by: @sebuzdugan. Learn more about this writer by checking @sebuzdugan's about page, and for more stories, please visit hackernoon.com. Anthropic's Claude Duet is a proactive agent: it runs on its own cloud VM with a browser, checks your connected apps every few hours, drafts work on its own and stops at an approval gate before sending, paying, signing or deleting. It ships in Pro and Max at no extra cost but shares their usage limits. A Claude Code plus cron setup still wins if you need custom intervals, niche connectors or full visibility.