Claude Code Announces Major Next-Gen Upgrade: You Chat, and the Backend Gets the Job Done
Claude Code's next major upgrade will make its sub-agents run in the background by default, transforming the tool from a conversational interface into a multi-threaded workflow engine. Users can chat with Claude while sub-agents handle tasks like code refactoring, running tests, and opening PRs in parallel. Creator Boris Cherny, who hasn't written a line of code in eight months and sometimes manages thousands of AI agents, states that users are no longer just prompters; "another Claude writes the prompts."
This evolution builds on recent features like Routines for scheduled tasks and Dynamic Workflows for complex, multi-agent jobs. The change signifies a shift where engineers focus on strategy and decision-making rather than writing code. Anthropic's internal data suggests Claude Code triples engineering output, creating a bottleneck for product managers who can't generate enough work. Spotify's case study reveals that 73% of its pull requests are AI-assisted, with executives using the tool to build prototypes directly from natural language descriptions. The core takeaway: the scarcest resource is no longer the ability to write code, but the ability to decide what code to write.
marsbit06/30 09:33
