Anthropic Adds Claude Code Remote Control for Mobile Development
Anthropic’s Claude Code AI development environment was previously used mainly through developers’ local terminals. As agentic coding tasks grow longer, users need to monitor execution, approve permissions and track completion after stepping away from their computers. Remote control addresses that need by extending the existing local environment rather than moving all project files to the cloud.
The latest update allows developers to resume local Claude Code sessions from a phone or browser while retaining access to the local file system and MCP server connections. It also adds mobile push notifications when long-running tasks finish or require approval. As of July 20, 2026, the available information did not specify an official launch date, eligible plans or pricing.
All Coverage
2 original reportsThe Backstory
The history behind this eventAnthropic Overhauls Claude Code Desktop With Side-by-Side Sessions and Integrated Development Tools
Anthropic launched Claude Code in February 2025, allowing developers to use natural language in the terminal to read and write code, run tests and handle tasks spanning multiple files. As AI agents increasingly work on multiple tasks in parallel, centralized progress tracking and fewer terminal switches and code conflicts have become more important. The desktop app has consequently evolved into an integrated development workstation.
Anthropic launched a redesigned Claude Code desktop app on April 14, 2026, adding a multi-session sidebar and drag-and-drop layouts. It integrates a terminal, file editing, diff views and live previews, and offers three display modes. On May 11, it also released an Agent View research preview that lets users centrally monitor and respond to background agents. The feature is available on Pro, Max, Team, Enterprise and API plans.
Anthropic Adds /ultraplan to Claude Code for Visual Implementation Planning
Anthropic's Claude Code is an AI tool that helps developers read, modify and run code, but its implementation plans were previously displayed mainly in the terminal, making them harder to review in full or revise repeatedly. The new feature separates planning from execution, allowing users to confirm the steps and scope of impact before an agent begins implementation. This reduces the risk of miscommunication and unintended changes.
As of July 20, 2026, Anthropic's head of product had announced a new “/ultraplan” command for Claude Code. It allows users to create, edit and preview a complete implementation plan in a web interface, then execute it with one click after approval. The announcement included no pricing details or phased rollout schedule. The core update moves the planning process from the terminal to a visual interface.
Anthropic Launches Claude Dispatch for Remote Control of AI Agents by Phone
Anthropic’s Claude Cowork already allowed AI to work with local files, connected services and knowledge-work tasks with user authorization. Dispatch synchronizes the same work conversation across mobile and desktop devices. The feature means Claude can do more than answer questions: it can continue operating tools while users are away from their computers, advancing the shift from AI assistants toward agents that execute tasks autonomously.
Anthropic released Dispatch as a research preview on March 17, 2026. On March 23, it also enabled Claude Cowork and Claude Code to control the mouse, keyboard, browser and screen. The features are available to Pro subscribers paying $20 a month and Max subscribers paying at least $100 a month, with support for macOS and Windows. The desktop must remain awake with Claude Desktop open, and both devices must stay connected to the internet.
Subscribe to Mark Radar Weekly
Every Friday, the week's strongest signals in your inbox. Unsubscribe anytime.