Customize AI agent browsing with proxies, profiles, and extensions in Amazon Bedrock AgentCore Browser

2026-02-13 · Source: Artificial Intelligence · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Cloud Computing & IT Infrastructure, Software Development & Engineering · Depth: Intermediate, medium

Summary

AWS has announced three new capabilities for AgentCore Browser: proxy configuration, browser profiles, and browser extensions. These features enhance AI agents' ability to interact with web applications by providing fine-grained control over internet connectivity, session state, and browser behavior. Proxy configuration allows routing browser traffic through corporate proxy servers, ensuring IP stability and access to internal resources. Browser profiles enable persistence of cookies and local storage across sessions, facilitating authenticated workflows and multi-step user journeys without repeated logins. Browser extensions support loading custom Chrome extensions to modify browser behavior, such as ad blocking or authentication assistance. These additions address enterprise requirements for secure, stateful, and customizable web browsing for AI agents.

Key takeaway

For AI Engineers developing web-browsing agents for enterprise environments, these new AgentCore Browser features are crucial. You can now ensure your agents comply with corporate network policies via proxy configuration, maintain session continuity for complex workflows using browser profiles, and customize agent behavior with browser extensions. This significantly reduces development overhead for authenticated or multi-step web interactions, improving agent reliability and performance.

Key insights

AgentCore Browser now offers proxy, profiles, and extensions for robust enterprise AI agent web interaction.

Principles

• Session state persistence improves agent workflow efficiency.
• IP stability is critical for enterprise web application access.
• Browser extensibility enables custom agent behaviors.

Method

Configure proxy settings via `StartBrowserSession` with `proxyConfiguration`, manage session state using `create_browser_profile`, `save_browser_session_profile`, and `start_browser_session` with `profileConfiguration`, and load extensions by uploading ZIPs to S3 and referencing them in `start_browser_session`.

In practice

• Route agent traffic through corporate proxies for compliance.
• Persist login sessions for e-commerce testing agents.
• Load custom Chrome extensions for ad blocking or auth helpers.

Topics

• AWS AgentCore Browser
• AI Agents
• Proxy Configuration
• Browser Profiles
• Browser Extensions

Code references

• awslabs/amazon-bedrock-agentcore-samples

Best for: AI Engineer, Machine Learning Engineer, MLOps Engineer

Related on AIssential

• Control where your AI agents can browse with Chrome enterprise policies on Amazon Bedrock AgentCore — Amazon Bedrock AgentCore now offers granular control over AI agent browsing via Chrome policies and custom root CAs.
• Introducing OS Level Actions in Amazon Bedrock AgentCore Browser — OS Level Actions in AgentCore Browser enable AI agents to interact with native OS UI elements.
• Semantic search across MCP tools with Amazon Bedrock AgentCore Gateway — Amazon Bedrock AgentCore Gateway enables scalable LLM agents through built-in semantic search for tool selection.
• Build and Run Your Own AI Agent in the Cloud — AgentCore provides managed AWS services for deploying and operating framework-agnostic AI agents, complementing agent frameworks like Strands.
• AWS Bedrock Agents: The Beginner’s Guide — AWS Bedrock Agents provide a managed platform for building and deploying AI agents with integrated orchestration and security.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Artificial Intelligence.