Anthropic redesigns Claude projects, letting users describe work in one conversation and have Claude manage it across parallel threads, starting in Claude Code
A new experience for Claude projects, now available in beta in Claude Code — https://claude.com/blog/projects- redesigned
It also extends the direction set by Cowork’s minimal-prompt task automation: Claude Code is being positioned less as a single coding chat and more as a place to direct persistent, multi-step work.
First-order effects
Claude Code users can describe a body of work once and have Claude coordinate parallel threads under a single project conversation, reducing the need to manually carry context between sessions.
Anthropic makes Projects a core Claude Code workflow rather than only a container for materials and conversations.
Second-order effects
The desktop session-management interface shifts from being the primary way to organize parallel work to a supporting view beneath a project-level coordinator.
Teams evaluating coding assistants gain a clearer distinction between tools that open multiple chats and tools that retain shared project context while delegating work across them.
Third-order effects
If the model proves reliable, coding-assistant competition will increasingly center on orchestration—persistent context, delegation and review across tasks—rather than the quality of an isolated prompt response.
Projects become a candidate common work surface for Anthropic’s chat, automation and developer products, concentrating more workflow state inside Claude.
The trend: AI coding tools are evolving from session-based assistants into persistent work surfaces that coordinate parallel agent tasks from a single conversational control point.
Projects now run from one conversation, starting in Claude Code. You describe what needs doing, and Claude directs parallel threads that keep working after you close your laptop. In beta today for select Pro and Max users in cloud sessions; coming to all Claude users soon.
Been a minute but really proud of this one! Brought a bunch of what we learned from building Chat/Cowork projects to build something really powerful. In particular, Artifacts inside of Projects are incredible. Excited to see what people think!
Sounds similar to what Cursor announced recently, right? Long-running projects, with context and memories shared across cloud threads as one layer. Very intriguing! Also: I want this for regular Claude/Cowork too.
Super excited to show the world Projects!! We've been building this for the last few months and it has become my new daily driver. A few tips for getting the most out of it 🧵
We've been using projects for a while internally and this is how I do all my work now. Instead of needing to manage and check individuals sessions, you work with one higher level coordinator Claude that directs work for you.
my first biiiiiig launch at anthropic is finally here!! 🫶 projects are a huge labor of love from the claude code team - it's the only way i've been working with claude for the last several months (including using projects...to build projects!!) spam the coordinator with any and a…
Projects brings the architecture of Claude Tag to Claude Code. It has one agent per project that manages memory and spins off subagents for tasks. You can ask it to be proactive, to do things on a schedule, etc. It feels a lot nicer than a bunch of sessions, try it out!
Another day, another improvement to how we work with Claude, that makes it a lot more intuitive, starting with Claude Code: Projects are getting a big upgrade. …