Anthropic Claude Code now autonomously fixes CI failures and PR comments

Claude

Mar 28, 2026 · Updated Apr 25, 2026

Anthropic introduced a cloud-based auto-fix feature for Claude Code that monitors GitHub Pull Requests to resolve CI errors and reviewer feedback. This shifts the agent from a local tool to an autonomous background worker, allowing developers to submit code and walk away while the AI handles the iterative review cycle.

Anthropic launched a cloud-based auto-fix capability for Claude Code, enabling the agent to monitor GitHub Pull Requests asynchronously. When a CI check fails or a reviewer leaves a comment, the agent spins up an isolated virtual machine to investigate, run tests, and push fixes directly to the branch.

This update transitions Claude Code from a terminal-bound assistant into an autonomous cloud agent. By offloading the "last mile" of the development cycle—the repetitive back-and-forth of fixing minor errors or addressing feedback—it removes the requirement for developers to remain at their workstations to maintain pull request velocity.

You can trigger auto-fix via the web interface, mobile app, or by using the --remote flag. A new /teleport command pulls these cloud sessions back into your local terminal if manual intervention is required. The feature is in research preview for Pro, Max, Team, and Enterprise users.

View the full update on code.claude.com

Noah Zweben

@noahzwebenMar 26

Thrilled to announce Claude Code auto-fix – in the cloud. Web/Mobile sessions can now automatically follow PRs - fixing CI failures and addressing comments so that your PR is always green. This happens remotely so you can fully walk away and come back to a ready-to-go PR. https://t.co/F41RTeymXJ

4926k

View on X

Every HeadsUpAI update is written based on its original source and reviewed before it's published. Read our editorial standards →

See all AI news & updates from Anthropic →

Keep reading

Anthropic Launches Cloud Agent Command to Automate Pull Request Maintenance

Anthropic released version 2.1.94 of Claude Code, introducing a command that hands off pull request maintenance to a cloud-based agent. This update allows developers to automate the cycle of fixing CI failures and reviewer comments without keeping a local terminal session active.

AnthropicMay 14

Anthropic Updates Claude Code With Goal Command for Autonomous Engineering Workflows

Anthropic released the /goal command for Claude Code, allowing developers to set specific completion conditions that the agent pursues autonomously across multiple turns. This update shifts the developer's role from iterative prompting to high-level supervision, enabling the AI to handle complex migrations without human intervention between steps.

GitHubJun 10

GitHub Copilot Integrates Claude Fable 5 for Autonomous Coding

GitHub Copilot now offers Anthropic's Claude Fable 5, the first model in its Mythos class, for long-horizon, autonomous coding and knowledge-work tasks. This integration provides Copilot users with advanced agentic capabilities, enabling more efficient multi-step code resolution.