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
METR report: Anthropic's unreleased Model 4 scores 178.6 on AECI, ahead of Opus 5.5
METR's new report discloses three unreleased Anthropic models, Model 2, Model 3 and Model 4. Model 4 scores 178.6 on Anthropic's AECI index, about 3.9 points above Opus 5.5. Anthropic co-founder Sam McCandlish confirmed the report's main findings but said much information was removed.
METR Report: Anthropic's AI Development Pace May Have Doubled Due to Internal AI Use
A new report from AI research nonprofit METR says AI use within Anthropic may have doubled the company's pace of AI development. The rate at which Anthropic's models are improving as of October is roughly twice the rate between March 2024 and October 2025, according to The Information.
Anthropic launches Personal Finance in Claude with read-only Plaid access for US Pro, Max and Ultra users
Anthropic announced Personal Finance in Claude, a feature that connects bank and credit card accounts through Plaid with read-only access. Conversations in the Personal Finance hub are not used to train Anthropic's models. It is available only to Pro, Max and Ultra subscribers in the US.
Anthropic Reports Bacterial and Phage Proteins Assemble Into Vault Particles in E. coli, With Claude Aiding a 3.2 Å Map
Anthropic reported on November 4, 2026 that prokaryotic and bacteriophage relatives of the major vault protein can assemble into vault particles when produced in E. coli. Claude helped the team map one bacteriophage-derived shell at a nominal resolution of 3.2 angstroms.
Comments
Loading...