ZeroHour
The Decoderpublished ()ingested Matthias Bastian

Anthropic keeps pushing Claude Code toward autonomous coding with new parallel agent workflows

infoAI industryimportance 55
AI summary · glm-5.3-flash

Anthropic rebuilt Claude Code's Projects feature to split goals across parallel cloud agent threads that can open pull requests and run tests.

Anthropic's updated Claude Code Projects feature uses a coordinator that splits a user's goal into parallel threads, each running as its own cloud session, with shared memory and a library of uploaded files and results. Threads can open pull requests and run tests, and progress is trackable in the main chat or per thread, including on mobile. The beta is open to select Pro and Max subscribers, with Team and Enterprise access and local execution to follow. The update follows Anthropic making autopilot mode the default in Claude Code.

  • Coordinator splits goals into parallel cloud agent threads
  • Threads can open pull requests and run tests independently
  • Shared memory and file library built across threads
  • Beta limited to select Pro and Max subscribers
  • Commentary links autonomy to increased token consumption
VendorsAnthropic
ProductsClaude Code
OrganizationsAnthropic
Full article215 words · extracted from the-decoder.com · click to collapse

Sep 17, 2026

Anthropic has rebuilt the Projects feature in Claude Code. Users now describe a goal and a coordinator splits the work across parallel "threads," each running as its own cloud session. Progress is trackable in the main chat or per thread, including on mobile. Each thread can open pull requests and run tests. Claude builds a shared memory across threads over time, and a library collects all uploaded files and results.

The beta is open to select Pro and Max subscribers using cloud sessions in Claude Code. Team and Enterprise access comes later, and local execution is coming soon. The waitlist is here.

The update is another step toward code automation. Anthropic recently made autopilot mode the default in Claude Code, claiming it outperformed human developers on safety tasks. It's also great for the IPO pitch: more autonomous agents likely mean more burned tokens, and control over how many tokens get burned shifts from users to the company selling them, like letting gas companies control the throttle in your car.

AI News Without the Hype – Curated by Humans

Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.

Subscribe now

Text extracted automatically; images, tables and formatting may be missing. Original: https://the-decoder.com/anthropic-keeps-pushing-claude-code-toward-autonomous-coding-with-new-parallel-agent-workflows/