AWS takes aim at runaway AI agent behavior with Strands Box

What happened

Amazon Web Services (AWS) has introduced an open-source sandbox for AI agents (AI that carries out multi-step tasks rather than answering one question) that allows developers to restrict their actions based on previous behavior, seeking to address security risks as enterprises give autonomous systems greater access to applications and data. Released in developer preview on October 7 under the Apache 2.0 license, it currently provides support for Macs with Apple silicon processors running macOS 15 or later. Amazon Web Services is a cloud computing company based in Seattle.

The tool, called Strands Box, combines operating system-level isolation with policies that govern what agents can do. Strands Box operates with Dogwood, an open-source policy language developed by AWS, and its accompanying evaluation engine to determine whether an agent should be permitted to perform an action.

The engine can factor in an agent’s recorded activity across different tools, allowing a file read through a shell command, for example, to trigger restrictions on subsequent network requests. “Consider an agent investigating a production incident,” AWS said in a post.

Key facts

• Amazon Web Services (AWS) has — introduced: an open-source sandbox for AI agents that allows developers to restrict their actions based on previous behavior, seeking to address security risks as enterprises give autonomous systems greater access to applications and data
• Released in developer preview on October 7 under the Apache 2.0 license, it currently — support: Macs with Apple silicon processors running macOS 15 or later
• Strands Box — uses: Dogwood, an open-source policy language developed by AWS, and its accompanying evaluation engine to determine whether an agent should be permitted to perform an action