Anthropic launches cloud-based code routines for automated bug fixes and PR reviews
Anthropic has released routines for Claude Code, allowing automated bug fixes, code reviews, and deployment monitoring to run on cloud infrastructure without requiring users' local machines. The feature is available in research preview with daily limits of 5-25 runs depending on subscription tier.
Anthropic launches cloud-based code routines for automated bug fixes and PR reviews
Anthropic has released "routines" for Claude Code, automated workflows that can fix bugs, review pull requests, and respond to GitHub events on the company's cloud infrastructure without requiring a user's local machine to be running.
How routines work
Routines are configured once and execute on three types of triggers: scheduled intervals, API calls, or GitHub events. According to Anthropic, typical use cases include nightly bug triage, automated code reviews based on team-specific checklists, porting code changes between programming languages, and checking deployments for errors.
The feature integrates with existing repository connections and external services including Slack and Asana. Users configure routines by assigning a name, describing the task, selecting a trigger type, and connecting relevant services.
Availability and limits
Routines are available as a research preview for Pro, Max, Team, and Enterprise subscription plans. Daily execution limits range from 5 to 25 runs depending on the plan tier, though Anthropic has not disclosed specific pricing or which plans receive which limits.
Anthropic states that support for webhook sources beyond GitHub is planned for future releases.
Recent Claude Code updates
The routines feature follows several desktop updates to Claude Code. Anthropic recently added capabilities for starting development servers, displaying web applications, and autonomous error fixing. The company also shipped the /loop command, which enables local scheduled background tasks.
Routines effectively move this automation capability from local execution to cloud-based infrastructure.
What this means
By shifting code automation to cloud infrastructure, Anthropic removes the requirement for developers to keep local machines running for scheduled tasks. This positions Claude Code as infrastructure for continuous integration workflows rather than just a local development tool. The integration with GitHub events and external services like Slack suggests Anthropic is targeting team-based development workflows where automated code maintenance can run independently of individual developer availability. The research preview designation and daily execution limits indicate Anthropic is still evaluating resource costs and usage patterns before wider release.
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...