Anthropic adds Ultraplan to Claude Code, moving task planning to the cloud
Anthropic has launched Ultraplan, a new feature for Claude Code that offloads programming task planning to the cloud. The feature enables developers to initiate planning jobs from the terminal while the planning executes in the browser, supporting inline comments, emoji reactions, and revision requests on individual plan sections.
Anthropic has added Ultraplan to Claude Code, moving the planning phase of programming tasks from local execution to cloud-based processing.
How Ultraplan Works
Developers initiate a planning job from the terminal. Claude then executes the planning phase on the Claude Code web interface, keeping the local terminal free for concurrent work. Once the plan is generated, it can be executed either in the browser or returned to the terminal for local execution.
Key Features
The web-based planning interface includes capabilities not present in local planning mode:
- Granular feedback: Users can comment on individual plan sections rather than responding to the entire plan at once
- Asynchronous execution: Planning runs in the background in the cloud
- Rich collaboration: The browser interface supports inline comments, emoji reactions, and revision requests
- Dual execution paths: Completed plans can run in the browser or be sent back to the terminal
According to Anthropic documentation, Ultraplan consumes roughly the same token count as the previous local planning mode, meaning it doesn't impose additional computational costs.
Requirements and Limitations
Ultraplan requires:
- Claude Code web account
- GitHub repository integration
- Claude Code version 2.1.91 or later
The feature is not compatible with Amazon Bedrock, Google Cloud Vertex AI, or Microsoft Foundry deployments. It is currently available as a preview for users who have activated Claude Code on the web.
What This Means
Ultraplan shifts developer workflow paradigms by decoupling planning from execution environments. The move to cloud-based planning enables richer collaboration—comments and reactions on specific plan sections address a friction point in multi-developer code review cycles. However, the incompatibility with major cloud platforms limits adoption to those using Anthropic's direct API or Claude Code web platform. The preview status indicates this is an early iteration; broader platform support and feature stability will determine whether this becomes standard practice.
Related Articles
Anthropic adds sandboxed in-app browser to Claude Code desktop app
Anthropic has added an in-app browser to Claude Code's desktop application. The sandboxed browser allows Claude to read, click through, and interact with documentation, designs, and local development servers, with configurable session persistence.
Anthropic launches Claude Reflect analytics dashboard to track AI usage patterns
Anthropic has released Claude Reflect, an analytics dashboard that tracks how users interact with Claude, including conversation topics, usage patterns, and task types. The feature, available in beta for Free, Pro, and Max tier users with memory enabled, includes mindfulness prompts and suggestions for better AI integration.
Anthropic tests feature to prompt Claude users about overuse, adds usage tracking dashboard
Anthropic is testing a beta feature in Claude that tracks usage patterns and periodically prompts users to consider if they're using the chatbot too much. The feature shows usage summaries over periods from one to twelve months and includes quiet hours scheduling.
GitHub reduces Copilot code review costs by switching to Unix-style exploration tools
GitHub reduced costs for Copilot code review by migrating to Unix-style code exploration tools. The company found that more sophisticated tools made reviews worse, leading them to reshape agent workflows around pull request evidence.
Comments
Loading...