• AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.

Anyone running Claude Code inherits a new default trust boundary and should understand what the agent will now execute without asking.

• postWe shipped four updates to Claude Managed Agents this week. First, you can now s
• postNext, you can now control where inference runs for Claude Managed Agents. Set mo
• postNew in Claude Code: your sessions can now message each other. Instead of having
• postLastly, you can now give a Claude Managed Agent an advisor: a stronger model it

• postStarting August 14, auto mode will be the default permission mode in Claude CodeClaudeDevs
• articleAuto mode is now the default in Claude Code for Pro, Max, and Team plansSimon Willison
• postautomode is much safer than any other permission system out there, especially retrq212

Sign in to comment.

Loading comments…