Artificial Intelligence1 min read

Anthropic upgrades Claude Code Projects to run parallel AI workers

By · Published by Everything Blog

In short

Under the redesigned architecture, a central conversational interface manages parallel cloud sessions that execute on dedicated branches and repository copies. These independent threads possess the capability to run testing suites, open pull requests, and deploy subagents to divide work further. The update also adds an artifact library and shared memory to preserve crucial context across extended initiatives. Currently in beta for select premium users, the feature will later expand to broader team tiers and incorporate local execution behind private networks.

Key points

  • The update allows software development workflows to proceed autonomously in the backgroun…: The update allows software development workflows to proceed autonomously in the background even after users step away from their desks.
  • Access is presently limited to a beta group of Claude Pro and Max subscribers before laun…: Access is presently limited to a beta group of Claude Pro and Max subscribers before launching to Team and Enterprise tiers.
  • Anthropic plans to introduce future support for executing worker threads locally alongsid…: Anthropic plans to introduce future support for executing worker threads locally alongside proprietary internal tools.

Sources checked by our analysis pipeline: 1

Projects redesigned: from folder to conversation

A new experience for Claude projects, now available in beta in Claude Code

Managing multiple sessions across a build used to require you to divide the work, juggle handoffs, and stitch the results back together. Now in a Claude Code project, you describe what needs to get done and Claude manages the work.

Claude scopes the request, delegates the work, coordinates parallel threads, reviews the outputs, and assembles the finished result. You can steer progress throughout, even from your phone, and it keeps working after you step away from your computer.

For example, configure a project and set a goal to reduce your app's checkout p75 latency. Then ask Claude to profile each endpoint, test optimizations, and open PRs in parallel threads. Or connect your API, web, and mobile repos and set a goal to retire a deprecated v1 endpoint. Claude creates a thread per repo to migrate the callers, run the tests, open PRs, and then tells you which ones need to merge first.

Starting today, updated projects are available in beta to…

Artificial Intelligence