AWS bedrock-agentcore documentation change
Summary
Reorganized document structure, moved sections, removed 'Overview' and 'Use cases' sections, rewrote content for clarity, and adjusted security feature descriptions.
Security assessment
The changes primarily restructure content and reword existing security features (isolation, ephemeral sessions, timeouts) without introducing new security documentation or addressing specific vulnerabilities. No evidence of security incident response or vulnerability fixes exists in the diff.
Diff
diff --git a/bedrock-agentcore/latest/devguide/browser-tool.md b/bedrock-agentcore/latest/devguide/browser-tool.md index 40d5a83eb..bdad9e556 100644 --- a//bedrock-agentcore/latest/devguide/browser-tool.md +++ b//bedrock-agentcore/latest/devguide/browser-tool.md @@ -5 +5 @@ -OverviewWhy use remote browsers for agent development?Security FeaturesHow it worksUse cases +How it worksWhy use remote browsers for agent development?Security Features @@ -9 +9 @@ OverviewWhy use remote browsers for agent development?Security FeaturesHow it wo -The Amazon Bedrock AgentCore Browser provides a secure, cloud-based browser that enables AI agents to interact with websites. It includes security features such as session isolation, built-in observability through live viewing, CloudTrail logging, and session replay capabilities. +The Amazon Bedrock AgentCore Browser provides a secure, isolated browser environment for your agents to interact with web applications. It runs in a containerized environment, keeping web activity separate from your system. It includes security features such as session isolation, built-in observability through live viewing, CloudTrail logging, and session replay capabilities. @@ -11,3 +11 @@ The Amazon Bedrock AgentCore Browser provides a secure, cloud-based browser that -## Overview - -The Amazon Bedrock AgentCore Browser provides a secure, isolated browser environment that allows you to interact with web applications while minimizing potential risks to your system. It runs in a containerized environment within AgentCore, and isolates web activity from your local system. +## How it works @@ -17,43 +15 @@ The Amazon Bedrock AgentCore Browser provides a secure, isolated browser environ -## Why use remote browsers for agent development? - -A remote browser runs in a separate environment rather than on the local machine. For agent development, remote browsers allow AI agents to interact with the web as humans do. - -Remote browsers provide the following capabilities for agent development: - - * Web interaction capabilities for navigating websites, filling forms, clicking buttons, and parsing dynamic content - - * Serverless browser infrastructure that automatically scales without infrastructure overhead - - * Visual understanding through screenshots that allow agents to interpret websites as humans do - - * Human intervention with live interactive view capabilities - - * Isolation and security by running web interactions for each session in a separate environment - - * Complex web application navigation for interfaces that require browser capabilities - - * Security through session isolation and audit capabilities - - * Observability with real-time visibility and recorded history of browser interactions - - - - -Remote browsers bridge the gap between AI agents and the human web, allowing agents to interact with websites designed for human users rather than being limited to APIs or static content. - -## Security Features - -The Browser Tool includes several security features to help protect your environment: - - * Isolation: The browser runs in a containerized environment, isolated from your local system - - * Ephemeral sessions: Browser sessions are temporary and reset after each use - - * Session timeouts: Sessions are terminated either by client or when the time to live (ttl) expires - - - - -## How it works - -The Amazon Bedrock AgentCore Browser provides a session-based model for secure web browsing with comprehensive observability features. Here's how the complete workflow operates: +The Amazon Bedrock AgentCore Browser provides session-based web browsing with comprehensive observability. The workflow consists of four key steps: @@ -63 +19 @@ The Amazon Bedrock AgentCore Browser provides a session-based model for secure w -Create a Browser Tool to enable web browsing capabilities. You can choose between the AWS managed Browser (aws.browser.v1) for quick setup, or create a custom browser with advanced features like session recording, custom network settings, and specific IAM execution roles. The Browser Tool allows you to augment your agent runtime to securely interact with web applications, fill forms, navigate websites, and extract information in a fully managed environment. +You start by creating a Browser Tool enabling web browsing capabilities for your agent to interact with web applications, fill forms, navigate websites, and extract information in a fully managed environment. You can choose between the AWS managed Browser (aws.browser.v1) for quick setup, or create a custom browser with advanced features like session recording, custom network settings, and specific IAM execution roles. @@ -67 +23 @@ Create a Browser Tool to enable web browsing capabilities. You can choose betwee -The Browser Tool uses a session-based model where each session runs in an isolated environment. After creating a Browser Tool, you start a session with a configurable timeout period (default is 15 minutes, extendable up to 8 hours). Sessions automatically terminate after the timeout period, and multiple sessions can be active simultaneously for a single Browser Tool. +Launch isolated sessions with configurable timeouts (default: 15 minutes, maximum: 8 hours). Run multiple sessions simultaneously. @@ -75 +31,2 @@ Once a session is started, you can interact with the browser using WebSocket-bas -All browser sessions provide built-in observability through live viewing capabilities and optional session recording. Live view allows real-time monitoring of browser activity, while session recording (available for custom browsers) captures comprehensive interaction data including DOM changes, user actions, console logs, and network events. Recorded sessions are stored in your Amazon S3 bucket and can be replayed through the AWS Console or accessed programmatically for debugging and analysis. +All browser sessions provide built-in observability which includes Live View for real-time monitoring, Session recording (available for custom browsers), and CloudWatch metrics for real-time performance insights. Session recording captures DOM changes, user actions, console logs, and network events. Recorded sessions are stored in your Amazon S3 bucket and can be replayed through the AWS for detailed analysis capabilities including video playback, timeline navigation, user action tracking, and comprehensive logs for troubleshooting and optimization. + @@ -77 +33,0 @@ All browser sessions provide built-in observability through live viewing capabil - 5. ###### Assess performance using observability @@ -79 +34,0 @@ All browser sessions provide built-in observability through live viewing capabil -Monitor key metrics for each tool in CloudWatch to get real-time performance insights. Session recordings provide detailed analysis capabilities including video playback, timeline navigation, user action tracking, and comprehensive logs for troubleshooting and optimization. @@ -80,0 +36,3 @@ Monitor key metrics for each tool in CloudWatch to get real-time performance ins +## Why use remote browsers for agent development? + +A remote browser runs in a separate environment rather than on the local machine. For agent development, remote browsers allow AI agents to interact with the web as humans do. Key capabilities include: @@ -81,0 +40 @@ Monitor key metrics for each tool in CloudWatch to get real-time performance ins + * Navigate websites, fill forms, click buttons, parse dynamic content @@ -82,0 +42 @@ Monitor key metrics for each tool in CloudWatch to get real-time performance ins + * Serverless infrastructure that scales automatically @@ -84 +44 @@ Monitor key metrics for each tool in CloudWatch to get real-time performance ins -## Use cases + * Visual understanding through screenshots @@ -86 +46 @@ Monitor key metrics for each tool in CloudWatch to get real-time performance ins -The AgentCore Browser can be used for a wide range of use cases, enabling AI agents to interact with web applications just as humans do. This section describes common use cases. + * Human intervention with live interactive view @@ -88 +48 @@ The AgentCore Browser can be used for a wide range of use cases, enabling AI age -With the AgentCore Browser, you can: + * Session isolation for security @@ -90 +50 @@ With the AgentCore Browser, you can: - * Test web applications in a secure environment + * Complex web application navigation @@ -92 +52 @@ With the AgentCore Browser, you can: - * Access online resources and services + * Comprehensive audit capabilities @@ -94 +53,0 @@ With the AgentCore Browser, you can: - * Perform web-based tasks and workflows @@ -96 +54,0 @@ With the AgentCore Browser, you can: - * Interact with web interfaces @@ -98 +55,0 @@ With the AgentCore Browser, you can: - * Capture screenshots and record browser sessions @@ -100 +57 @@ With the AgentCore Browser, you can: - * Build AI agents that can navigate the web +## Security Features @@ -102 +59 @@ With the AgentCore Browser, you can: - * Automate form submissions and data entry +The Browser Tool includes several security features to help protect your environment: @@ -104 +61 @@ With the AgentCore Browser, you can: - * Extract information from websites + * Isolation: Containerized environment separate from your system @@ -106 +63 @@ With the AgentCore Browser, you can: - * Perform e-commerce transactions + * Ephemeral sessions: Temporary sessions that reset after each use @@ -108 +65 @@ With the AgentCore Browser, you can: - * Monitor website changes and updates + * Automatic termination when time-to-live expires