Claude Code revamps projects so you can work and pay in parallel

Claude Code customers have a new reason to give Anthropic more of their money.

The tool now allows you to launch multiple sessions related to a single project, burning through more resources and cash at once.

Appropriately enough, the feature is called projects and can be accessed from the Claude.ai sidebar.

It's not the old version of projects, capitalized in some reference material, which allowed for the creation of self-contained workspaces with separate chat histories and knowledge bases.

The new implementation is technically in beta, though that term hardly means anything anymore amid the constant code iteration.

Anthropic describes projects as a way to let Claude manage multiple related tasks.

"Claude scopes the request, delegates the work, coordinates parallel threads, reviews the outputs, and assembles the finished result," the company explains in a blog post.

"You can steer progress throughout, even from your phone, and it keeps working after you step away from your computer." It's the sort of capability that might be useful if you are prompting the model to begin a large coding project and you want to get several essential components like authorization, databases, caching, and containers up and running at the same time.

Essentially, a project spins up each task as its own Claude Code cloud session thread that works on its own git branch and its own copy of the relevant repo.

A coordinator directs the threads; if they touch the same code, overlaps surface as merge conflicts like those in other pull requests.

And each thread may get broken down into distinct tasks handled by subagents within that session.

Claude Code now offers five different ways to run multiple tasks at the same time.

Subagents work within a session, though each with its own context.

Agent View provides a single screen interface for overseeing several independent tasks.