AgentsThe story, in brief

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

Anthropic's Claude Code now splits coding tasks across parallel autonomous threads—each opening PRs and running tests independently. Beta rolling to Pro and Max.

Paper-cut illustration of a coral software window opening into a three-dimensional drafting space.
New tools for building and creating with AI.AI illustration by KeyNews
The KeyNews take

Why it matters

Anthropic is moving Claude Code from assisted coding toward genuine autonomous multi-threaded agents. The parallel coordinator + shared memory architecture is a significant step toward agentic software engineering at scale—practitioners deploying Claude in CI/CD will watch this closely.

The key facts

5 to know
  1. Claude Code Projects rebuilt with coordinator splitting tasks across parallel cloud threads

  2. Each thread independently opens pull requests and runs tests

  3. Threads share common memory for coordination

  4. Beta available to select Pro and Max subscribers

  5. Marks shift from assisted coding toward autonomous agent workflows

Go to the source

The Decoderthe-decoder.com

Publisher excerpt: Anthropic has rebuilt Projects in Claude Code. A coordinator now splits tasks across parallel cloud threads that independently open pull requests and run tests. All threads share a common memory. The beta is available to select Pro and Max subscribers.
Read original report
Back to today's editionMore agents news

Keep reading

Related stories

More from Agents