Customise AI agent searching with proxies, profiles, and extensions in Amazon Bedrock AgentCore Browser

AI brokers that browse the online want greater than fundamental web page navigation. Our clients inform us they want brokers that preserve session state throughout interactions, route site visitors by way of company proxy infrastructure, and run with customized browser configurations. AgentCore Browser supplies a safe, remoted browser surroundings in your brokers to work together with net purposes. Till now, in Agent Core Browser, every browser session began from a clean slate with default settings and direct web entry, limiting what brokers might accomplish in real-world enterprise environments.

Immediately, we’re saying three new capabilities that deal with these necessities: proxy configuration, browser profiles, and browser extensions. Collectively, these options provide you with fine-grained management over how your AI brokers work together with the online.

These three capabilities provide you with management over how AgentCore Browser classes hook up with the web, what state they preserve, and the way they behave. Proxy configuration enables you to route browser site visitors by way of your individual proxy servers, offering IP stability and integration with company community infrastructure. Browser profiles persist cookies and native storage throughout classes, so brokers can resume authenticated workflows with out repeating login flows. Browser extensions load Chrome extensions into classes to customise browser conduct in your use case. This publish will stroll by way of every functionality with configuration examples and sensible use instances that will help you get began.

How persistent browser profiles preserve AI Brokers operating easily

Prospects constructing brokers for e-commerce testing, authenticated workflows, and multi-step consumer journeys want browser classes that keep in mind state. With out persistent profiles, brokers are required to re-authenticate and rebuild context initially of each session, including latency and fragility to automated workflows. Browser profiles remedy this by saving and restoring cookies and native storage between classes, so an agent that logged right into a portal yesterday can choose up the place it left off as we speak.

IP stability is one other frequent requirement. Healthcare and monetary portals validate classes primarily based on supply IP deal with, and rotating AWS IP addresses trigger frequent re-authentication cycles that break long-running workflows. Proxy assist enables you to route site visitors by way of servers with secure egress IPs, sustaining session continuity and assembly IP allowlisting necessities. Organizations that route site visitors by way of company proxies want to increase this follow to AI brokers for browser classes. Proxy configuration allows entry to inside webpages and sources that require proxy-based connectivity.

Browser extensions permit customized configurations reminiscent of advert blocking, authentication helpers, or different browser-level customization. When mixed with proxy logging, these capabilities helps present entry management and audit proof that might compliance packages reminiscent of FedRAMP, HITRUST, and PCI.

Characteristic 1: Proxy configuration

Browser now helps routing browser site visitors by way of your individual exterior proxy servers. If you create a browser session with proxy configuration, AgentCore configures the browser to route HTTP and HTTPS site visitors by way of your specified proxy servers.

The way it works

You name StartBrowserSession with a proxyConfiguration specifying your proxy server. If utilizing authentication, AgentCore retrieves proxy credentials from AWS Secrets and techniques Supervisor. The browser session begins along with your proxy configuration utilized, and browser site visitors routes by way of your proxy server primarily based in your area routing guidelines.

Getting began with proxies

Full these conditions earlier than continuing.

import boto3 
import json 
consumer = boto3.consumer('secretsmanager') 
consumer.create_secret( 
    Identify="my-proxy-credentials", 
    SecretString=json.dumps({ 
        'username': '', 
        'password': '' 
    }) 
)

Step 2: Create a browser session with proxy configuration

session_client = boto3.consumer('bedrock-agentcore', region_name="") 
 
response = session_client.start_browser_session( 
    browserIdentifier="aws.browser.v1", 
    title="my-proxy-session", 
    proxyConfiguration={ 
        "proxies": [{ 
            "externalProxy": { 
                "server": "", 
                "port": 8080, 
                "credentials": { 
                    "basicAuth": { 
                        "secretArn": "arn:aws:secretsmanager:::secret:" 
                    } 
                } 
            } 
        }] 
    } 
) 
print(f"Session ID: {response['sessionId']}")

The credentials discipline is non-obligatory for proxies with out authentication.

Area-based routing

Use domainPatterns to route particular domains by way of designated proxies, and bypass.domainPatterns for domains that ought to join instantly:

proxyConfiguration={ 
    "proxies": [ 
        { 
            "externalProxy": { 
                "server": "corp-proxy.example.com", 
                "port": 8080, 
                "domainPatterns": [".company.com", ".internal.corp"] 
            } 
        }, 
        { 
            "externalProxy": { 
                "server": "general-proxy.instance.com", 
                "port": 8080 
            } 
        } 
    ], 
    "bypass": { 
        "domainPatterns": [".amazonaws.com"] 
    } 
}

With this configuration, requests to and inside.corp route by way of the company proxy, requests to amazonaws.com bypass all proxies, and all the pieces else routes by way of the final proxy. These fields are simply an instance. Bypass domains can match bypass.domainPatterns to attach instantly and exterior proxy could be a legitimate proxy’s domainPatterns route by way of that proxy (first match wins primarily based on array order).

Routing priority

When AgentCore Browser processes an outbound request, it walks by way of three tiers of routing guidelines to resolve the place to ship the site visitors. It first checks the bypass listing. If the vacation spot area matches a bypass.domainPatterns entry, the request connects on to the web with out utilizing any proxy. If the area doesn’t match a bypass rule, AgentCore checks every proxy’s domainPatterns so as and routes the request by way of the primary proxy whose sample matches. If no proxy sample matches both, the request falls by way of to the default proxy, which is the proxy entry that has no domainPatterns outlined.

Check the brand new proxy characteristic with this code instance.

Characteristic 2: Browser profiles

Browser profiles allow you to persist and reuse session information throughout a number of browser classes, together with cookies and native storage. An agent that authenticates with an internet portal in a single session can restore that state in a later session with out logging in once more. That is helpful for authenticated workflows the place re-login provides latency, e-commerce testing the place procuring carts and type information must survive between classes, and multi-step consumer journeys that span a number of browser invocations.

The profile lifecycle has 4 phases. You begin by calling create_browser_profile() to create a named profile. On the finish of a session, you name save_browser_session_profile() to seize the present cookies and native storage into that profile. If you begin a brand new session, you cross the profile identifier within the profileConfiguration parameter of start_browser_session(), which restores the saved state into the brand new browser. If you now not want the profile, you name delete_browser_profile() to scrub it up.

The next instance exhibits an agent that provides gadgets to a procuring cart in a single session and verifies they persist in a subsequent session.

Full these conditions earlier than continuing.

import boto3 

control_client = boto3.consumer('bedrock-agentcore-control', region_name="") # substitute by your area 

session_client = boto3.consumer('bedrock-agentcore', region_name="") # substitute by your area  
 
# Create a browser profile 
profile = control_client.create_browser_profile(title="ecommerce_profile") 
profile_id = profile['profileId'] 
 
# Session 1: Add gadgets to cart 
session1 = session_client.start_browser_session( 
    browserIdentifier=”aws.browser.v1”, 
    title="shopping-session-1" 
) 
# ... agent navigates and provides gadgets to cart ... 
 
# Save session state to profile 
session_client.save_browser_session_profile( 
    sessionId=session1['sessionId'], 
    browserIdentifier=”aws.browser.v1”, 
    profileIdentifier=profile_id 
) 
session_client.stop_browser_session(sessionId=session1['sessionId'], browserIdentifier="aws.browser.v1") 
 
# Session 2: Resume with saved profile 
session2 = session_client.start_browser_session( 
    browserIdentifier=”aws.browser.v1”, 
    title="shopping-session-2", 
    profileConfiguration={"profileIdentifier": profile_id} 
) 
# Cart gadgets from Session 1 are actually accessible

Check the brand new profile characteristic with this code instance.

Characteristic 3: Browser extensions

Browser extensions allow you to load Chrome extensions into AgentCore Browser classes to customise how the browser behaves. You bundle extensions as ZIP information, add them to Amazon Easy Storage Service (Amazon S3), and reference them when beginning a browser session. This supplies entry to performance accessible by way of the Chrome extension API, from proxy routing and advert blocking to authentication helpers and content material modification. For instance, you’ll be able to inject authentication tokens for inside purposes, take away advertisements, and observe scripts that intervene with agent navigation, or modify web page content material to enhance how brokers work together with a web site.

Your extension ought to observe the usual Chromium extension format and cling to Chromium extension pointers.

Full these conditions earlier than continuing.

Add the extension to Amazon S3:

# Add extension to S3 

import boto3 
s3 = boto3.consumer('s3') 
s3.upload_file( 
    'my-extension.zip', 
    'amzn-s3-demo-bucket-extensions', 
    'extensions/my-extension.zip' 
)

Then, begin a session with the extension, pointing to the Amazon S3 bucket the place you’ve uploaded the zip file:

import boto3 
area = "" # substitute by your area 
consumer = boto3.consumer('bedrock-agentcore', region_name=area) 

response = consumer.start_browser_session( 
    browserIdentifier="aws.browser.v1", 
    title="my-session-with-extensions", 
    sessionTimeoutSeconds=1800, 
    viewPort={ 
        'peak': 1080, 
        'width': 1920 
    }, 
    extensions=[ 
        { 
            "location": { 
                "s3": { 
                    "bucket": "amzn-s3-demo-bucket-extensions", 
                    "prefix": "extensions/my-extension.zip" 
                } 
            } 
        }, 
        { 
            "location": { 
                "s3": { 
                    "bucket": "amzn-s3-demo-bucket-extensions", 
                    "prefix": "extensions/another-extension.zip", 
                    "versionId": "abc123"  # Optional - for versioned S3 buckets 
                } 
            } 
        } 
    ] 
) 
 
print(f"Session ID: {response['sessionId']}") 
print(f"Standing: {response['status']}") 
print(f"Automation Stream: {response['streams']['automationStream']['streamEndpoint']}")

Check the brand new extensions characteristic with this code instance.

Conclusion

Proxy configuration, browser profiles, and browser extensions give AgentCore Browser the proxy routing, session persistence, and extensibility controls that clients must deploy AI brokers that browse the online in manufacturing. You may route site visitors by way of your company proxy infrastructure, preserve session continuity throughout interactions, and customise browser conduct with extensions, all whereas preserving credentials safe in AWS Secrets and techniques Supervisor. Prospects can carry e-commerce context and data amongst classes, create your individual extension and check it in a safe surroundings earlier than launch, and, additionally, have browser connecting into your community by way of proxies.

To get began, see the tutorials within the Amazon Bedrock AgentCore samples repository and the Amazon Bedrock AgentCore Browser documentation. For extra details about pricing, go to Amazon Bedrock AgentCore Pricing.