Amazon Bedrock AgentCore Browser adds OS-level interaction capabilities

Amazon Bedrock AgentCore Browser Enhancements

Amazon Bedrock AgentCore Browser now supports OS-level interaction capabilities, enabling automation of browser workflows that require direct operating system control beyond Chrome DevTools Protocol (CDP) capabilities. This enhancement addresses automation scenarios where CDP alone is insufficient, such as mouse operations, print dialogs, native system alerts, and keyboard shortcuts. The feature serves AI agent developers, test automation engineers, and organizations building LLM-powered web interaction tools.

The new capabilities provide automation through mouse operations (click, move, drag, scroll), keyboard operations (type, press, shortcuts like ctrl+a and ctrl+p), and full desktop screenshots, all at OS-level coordinates extending beyond the browser viewport. Key use cases include automated testing with system dialog handling, document management workflows, complex UI interactions with right-click menus, and vision-based AI agents that require complete browser environment visibility.

What to do

• Explore the new OS-level interaction capabilities in your browser workflows.
• Update your automation scripts to leverage the new mouse and keyboard operations.
• Test the new features in your current projects to enhance automation scenarios.

This feature is available by default on all browser instances in all 14 AWS Regions where Amazon Bedrock AgentCore Browser is available: US East (N. Virginia), US East (Ohio), US West (Oregon), Europe (Frankfurt), Europe (Ireland), Europe (London), Europe (Paris), Europe (Stockholm), Asia Pacific (Mumbai), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Tokyo), Asia Pacific (Seoul), and Canada (Central).

To learn more, visit the AgentCore Browser documentation.

If you need further guidance on AWS, our experts are available at AWS@westloop.io. You may also reach us by submitting the Contact Us form.