Anthropic Upgrades Claude Code Projects to Run Parallel AI Workers Hands-Free
What happened
Anthropic has upgraded Claude Code Projects so the coordinator can proactively answer questions and post status updates in chat, reducing the need for developers to monitor thread lists. Threads can now be shared as read‑only links with signed‑in Claude users, while threads that accessed local computers remain unshareable to protect private data. New slash commands (/btw and /fork) allow branching and side threads, and the threads panel now shows recent, pinned, and updated threads with artifact thumbnails for easier navigation. The public beta is available to Pro and Max subscribers on web, desktop, and mobile, with a limit of 200 new threads per day per account. Each worker consumes the subscriber’s Claude Code allowance, and projects default to Opus models with low effort for the coordinator and high effort for workers.
Why it matters
This makes managing multiple AI workers in a project smoother, saving developers time and reducing manual oversight. It also introduces privacy safeguards for local data when sharing thread links.
Reality check
An automated, sceptical read of the sourceIncremental. The changes improve workflow and privacy but do not introduce fundamentally new AI capabilities.
Is this a big deal?
Get stories like this every morning
The day's AI news in plain English, in your inbox at 8:30 IST. Free.
More from Anthropic
Claude designed FPGA scaler board for 6th-gen consolesAnthropic · 13 Nov 2026I asked Claude Fable 5.2 to turn my site into a 90s Silicon Graphics workstationAnthropic · 13 Nov 2026Anthropic is endorsing SB 53Anthropic · 13 Nov 2026Understanding and addressing AI harmsAnthropic · 13 Nov 2026Anthropic update on independent evaluatorsAnthropic · 13 Nov 2026This page was collected from alphasignal.ai and summarised automatically by AIPulsee's pipeline. See how it runs.