Anthropic keeps pushing Claude Code toward autonomous coding with new parallel agent workflows
decoder ·
Anthropic has rebuilt the Projects feature in Claude Code to support more autonomous coding workflows. Users describe a goal, and a coordinator divides the work among parallel threads, each running in its own cloud session. Progress can be monitored in the main chat or within individual threads, including on mobile, while threads can open pull requests and run tests. Claude also builds shared memory across threads, and a library stores uploaded files and results. The beta is available to selected Pro and Max subscribers using cloud sessions, with Team and Enterprise access planned later and local execution expected soon. The update follows Anthropic’s decision to make autopilot mode the default in Claude Code; the article says the company claims it outperformed human developers on safety tasks and argues that more autonomous agents could increase token consumption and shift control over that usage from users to Anthropic.
decoder