Introducing OS Level Actions in Amazon Bedrock AgentCore Browser
Amazon AWS AI Blog / 5/6/2026
📰 NewsDeveloper Stack & InfrastructureTools & Practical UsageModels & Research
Key Points
- Amazon Bedrock AgentCore Browser introduces “OS Level Actions,” enabling agents to control the operating system directly via the InvokeBrowser API.
- This expands agent capabilities from interacting only with the browser’s web layer to operating on native UI elements that are visible on the screen.
- The approach combines full-desktop screenshots with OS-level mouse and keyboard control, allowing agents to observe, reason about, and act within the same session.
- The post explains how OS Level Actions function, lists the supported OS actions, and provides guidance to get started.
We’re announcing OS Level Actions for AgentCore Browser. This new capability unblocks these scenarios by exposing direct OS control through the InvokeBrowser API, so agents can interact with content visible on the screen, not only what's accessible through the browser's web layer. By combining full-desktop screenshots with mouse and keyboard control at the OS level, agents can observe native UI, reason about it, and act on it within the same session. This post walks through how OS Level Actions work, what actions are supported, and how to get started.
Related Articles
Black Hat USA
AI Business
Transform Your Blurry Photos into HD Masterpieces, Instantly!
Dev.to
6 New Moats for AI Agent Infrastructure — Trust Score, Deployment, SLA, Identity, Compliance-as-Code
Dev.to
Google Home’s Gemini AI can handle more complicated requests
The Verge
Exit Code 2: How Claude Hooks Turn Agentic Rules Into Runtime Barriers
Dev.to
