Introducing Amazon Bedrock AgentCore Browser Device

At AWS Summit New York Metropolis 2025, Amazon Internet Companies (AWS) introduced the preview of Amazon Bedrock AgentCore browser device, a completely managed, pre-built cloud-based browser. This device permits generative AI brokers to work together seamlessly with web sites. It addresses two elementary limitations: first, basis fashions (FMs) are skilled on massive however static datasets and wish dynamic entry to present info when API entry isn’t available; second, organizations face vital challenges when trying to scale internet automation with AI for enterprise use circumstances.

The event of agentic AI techniques is shifting towards purposes that may execute complicated, multistep duties. For these brokers to be efficient, they require entry to dynamic, real-time information, significantly from web sites and internet purposes that don’t supply APIs or the place API integration can be complicated. Furthermore, as companies search to deploy AI-powered automation throughout their operations, they want options that may reliably scale with out the operational overhead of managing browser farms or fixing complicated concurrency points. The AgentCore Browser Device supplies these capabilities, permitting brokers to carry out duties akin to automating analysis, streamlining operations, and interacting with web-based purposes—all with the scalability, reliability, and safety of the AWS Cloud infrastructure. By offering a completely managed cloud-based browser, AWS addresses the vital want for enterprises to deploy AI automation at scale throughout hundreds of concurrent periods, supporting use circumstances from customer support automation to large-scale information assortment and evaluation, with out the normal complexity and useful resource constraints of self-managed browser automation frameworks.

On this publish, we introduce the newly introduced Amazon Bedrock AgentCore Browser Device. We discover why organizations want cloud-based browser automation and the restrictions it addresses for FMs that require real-time information entry. We speak about key use circumstances and the core capabilities of the AgentCore Browser Device. We stroll via the right way to get began with the device.

Why do you want the cloud-based AgentCore Browser Device?

Conventional browser automation approaches have usually required vital infrastructure administration, safety issues, and growth experience. The introduction of a completely managed, cloud-based browser automation answer addresses a number of vital wants, together with simplified infrastructure administration, enterprise-grade safety, international availability and scaling, and value optimization. Organizations not have to provision, preserve, and scale browser cases to help their automation wants. AWS now handles the complicated infrastructure necessities, so builders can deal with constructing clever agent capabilities quite than managing browser farms. Cloud-based browser automation supplies remoted execution environments with AWS safety controls, lowering the chance of information exfiltration or unauthorized entry which may happen in much less managed environments. With a cloud-based browser, you’ll be able to instantaneously deploy browser cases throughout the worldwide infrastructure of AWS in order that browser automation can scale. By providing browser automation as a managed service, organizations can use a consumption-based pricing mannequin as a substitute of sustaining always-on infrastructure, which might considerably scale back prices for intermittent workloads.

Use circumstances for cloud-based browser automation

Dealing with repetitive internet duties: With the introduction of Amazon Bedrock AgentCore Browser Device, organizations can now implement refined browser automation at scale. Cloud-based browser automation excels at minimizing guide execution of repetitive duties throughout internet interfaces. AI brokers can populate complicated internet varieties throughout a number of techniques, validate entries, and preserve compliance with enterprise guidelines. Brokers can navigate to inner dashboards, extract vital metrics, and compile studies with out human intervention. For organizations managing massive user-generated content material domains, brokers can help human moderators by prescreening content material throughout a number of internet interfaces.

AI powered analysis and intelligence gathering: With cloud-based browser automation, AI brokers turn into highly effective analysis assistants. They mechanically monitor associated web sites for pricing adjustments, new product launches, or content material updates with common monitoring. You need to use AI brokers to collect and analyze client sentiment throughout numerous internet boards, evaluate websites, and social domains to tell product growth. With the AgentCore Browser Device, you’ll be able to create automated techniques that commonly scan trusted info sources to maintain inner information bases present.

Complicated workflow automation throughout techniques: Many organizations function throughout quite a few internet purposes that lack built-in workflows. Use the AgentCore Browser Device to automate buyer setup throughout a number of software-as-a-service (SaaS) techniques when APIs are unavailable. This helps preserve consistency and reduces error charges. You may monitor provider portals, stock techniques, and logistics companies to keep up visibility throughout complicated provide chains. By automating account creation and permission settings throughout quite a few inner internet purposes, worker onboarding turns into streamlined.

Testing and high quality assurance: Cloud-based browser automation permits strong testing at scale. You need to use AgentCore Browser Device to validate person experiences and performance throughout completely different situations, units, and browsers in parallel. Deploy brokers to constantly work together with vital enterprise purposes and arrange alerts to your groups about efficiency points earlier than prospects encounter them. With AgentCore Browser Device, you’ll be able to commonly check internet purposes for accessibility compliance, safety vulnerabilities, or regulatory necessities.

Legacy system integration: Many organizations preserve legacy techniques that lack trendy APIs. Allow trendy AI capabilities to work together with legacy internet purposes that might be expensive to exchange or modernize. Apply clever automation to techniques that had been by no means designed for programmatic entry. Because of this, you’ll be able to extract invaluable organizational information trapped in older internet purposes via common, automated harvesting.

Core capabilities

The Amazon Bedrock AgentCore Browser Device empowers AI brokers to work together with internet content material the identical means people do, via a completely managed distant browser infrastructure that minimizes conventional complexity whereas delivering enterprise-grade safety and scalability.

Internet interplay capabilities

Full navigation management throughout web sites and multipage workflows
Interplay with JavaScript-heavy purposes and dynamic content material
Kind manipulation, together with textual content fields, dropdown menus, and file uploads
Humanlike interplay patterns akin to scrolling, hovering, and clicking

Serverless browser infrastructure

Zero-management browser fleet with automated patching
Seamless scaling from single session to hundreds primarily based on demand
International deployment choices with usage-based pricing
Optimized efficiency with out infrastructure overhead

Visible understanding

Full-page screenshots enabling AI comprehension of format and content material
Visible aspect identification by look and place
Content material extraction from graphical parts
Decision and gadget emulation capabilities

Human-in-the-loop integration

Actual-time interactive viewing and management for human operators
Session recording for evaluate, coaching, and compliance

Enterprise-grade safety

Full session isolation for every browser occasion
AWS Identification and Entry Administration (IAM) controls for entry administration
Ephemeral browser periods that reset after every use

Complicated internet utility help

Full compatibility with trendy JavaScript frameworks
Authentication dealing with and session persistence
Processing of asynchronous content material and real-time updates
Clever interplay with complicated UI patterns

Audit and compliance

Detailed interplay logging and session recording
Integration with AWS CloudTrail for complete monitoring

Observability

Efficiency metrics on latency and useful resource utilization
Integration with Amazon CloudWatch for unified monitoring
Session document and replay for observability

This complete set of capabilities bridges the elemental hole between AI brokers and the human internet, enabling organizations to construct clever brokers that may perceive and work together with content material designed for people quite than being restricted to API-based integrations.

How an AI agent can use AgentCore Browser Device

Amazon Bedrock AgentCore Browser runs in a safe, remoted containerized surroundings inside AgentCore, insulating internet exercise out of your native system. You may work together with the AgentCore Browser Device utilizing browser actuation libraries, akin to Playwright, or use AI agentic frameworks specialised for browser automation, akin to Amazon Nova Act and Browser Use. You can too combine browser automation as a device in a multi-agentic workflow.

Amazon Nova Act or Browser Use works with the AgentCore Browser Device to take pure language directions from the person and convert them to actuations on the browser by following this workflow:

The person sends a question akin to “seek for footwear on Amazon”
An agentic framework akin to Amazon Nova Act or Browser Use passes the question to the massive language mannequin (LLM)
The LLM causes and generates directions in a structured output format (for instance, JSON encoded)
The agentic framework maps these directions into browser actuation instructions (akin to Playwright, Puppeteer, or Selenium)
The browser actuation instructions are executed on the AgentCore Browser over a safe WebSocket connection
The response from the browser and a screenshot are despatched to the agent to cause additional

This course of repeats till the unique activity is full. The circulation is illustrated within the following diagram.

Get began

The Amazon Bedrock AgentCore Browser Device is on the market to be used as we speak. For a group of open supply examples, go to the amazon-bedrock-agentcore-samples repository on GitHub.

Stipulations

To make use of the Amazon Bedrock AgentCore Brower Device, it’s essential to full the next stipulations:

Python 3.10+
Confirm your IAM person or position has the permissions to make use of AgentCore Browser:

git clone https://github.com/awslabs/amazon-bedrock-agentcore-samples.git
pip set up bedrock-agentcore

For browser visualization in your native machine, you want the BrowserViewerServer element within the repository you cloned at: 01-tutorials/05-AgentCore-tools/02-Agent-Core-browser-tool/interactive_tools

You can too visualize the browser stay on the Amazon Bedrock AgentCore console at https://us-east-1.console.aws.amazon.com/bedrock-agentcore/builtInTools

The next Python code demonstrates the right way to use the AgentCore Browser Device immediately with the Playwright library and the Amazon Bedrock AgentCore SDK. This instance initiates a safe browser session, connects to it, and automates a simple workflow through which it navigates to https://www.amazon.com and searches for a product.

To get began with playwright:

cd 01-tutorials/05-AgentCore-tools/02-Agent-Core-browser-tool

Set up dependencies:

Writer your playwright-based script:

from playwright.sync_api import sync_playwright, Playwright, BrowserType
from bedrock_agentcore.instruments.browser_client import browser_session
from browser_viewer import BrowserViewerServer
import time
from wealthy.console import Console
console = Console()
def run(playwright: Playwright):
    # Create the browser session and hold it alive
    with browser_session('us-west-2') as consumer:
        ws_url, headers = consumer.generate_ws_headers()
        # Begin viewer server
        viewer = BrowserViewerServer(consumer, port=8005)
        viewer_url = viewer.begin(open_browser=True)
        # Join utilizing headers
        chromium: BrowserType = playwright.chromium
        browser = chromium.connect_over_cdp(
            ws_url,
            headers=headers
        )
        context = browser.contexts[0]
        web page = context.pages[0]
        attempt:
            web page.goto("https://amazon.com/")
            console.print(web page.title())
            # Preserve operating
            whereas True:
                time.sleep(120)
        besides KeyboardInterrupt:
            console.print("nn[yellow]Shutting down...[/yellow]")
            if 'consumer' in locals():
                consumer.cease()
                console.print("✅ Browser session terminated")
        besides Exception as e:
            console.print(f"n[red]Error: {e}[/red]")
            import traceback
            traceback.print_exc()
with sync_playwright() as playwright:
    run(playwright)

Alternatively, you’ll be able to construct a browser agent utilizing Amazon Nova Act to automate internet interactions:

Join Nova Act at https://nova.amazon.com/act and generate an API key.
In the identical Python digital surroundings:

pip set up nova-act

Writer your Nova Act primarily based script:

import time
from bedrock_agentcore.instruments.browser_client import browser_session
from nova_act import NovaAct
from wealthy.console import Console
from browser_viewer import BrowserViewerServer
 
NOVA_ACT_API_KEY = "YOUR_NOVA_ACT_API_KEY"
console = Console() 
 
def foremost():
    attempt:
        # Step 1: Create browser session
        with browser_session('us-west-2') as consumer:
            print("r   ✅ Browser prepared!                    ")
            ws_url, headers = consumer.generate_ws_headers()
 
            # Step 2: Begin viewer server
            console.print("n[cyan]Step 3: Beginning viewer server...[/cyan]")
            viewer = BrowserViewerServer(consumer, port=8005)
            viewer_url = viewer.begin(open_browser=True)
 
            # Step 3: Use Nova Act to work together with the browser with NovaAct
            with NovaAct(
                    cdp_endpoint_url=ws_url,
                    cdp_headers=headers,
                    preview={"playwright_actuation": True},
                    nova_act_api_key=NOVA_ACT_API_KEY,
                    starting_page="https://www.amazon.com",
                ) as nova_act:
                    outcome = nova_act.act("Seek for espresso maker and get the small print of the bottom priced one on the primary web page")
                    console.print(f"n[bold green]Nova Act Outcome:[/bold green] {outcome}")
            
            # Preserve operating
            whereas True:
                time.sleep(1)
             
    besides KeyboardInterrupt:
        console.print("nn[yellow]Shutting down...[/yellow]")
        if 'consumer' in locals():
            consumer.cease()
            print("✅ Browser session terminated")
    besides Exception as e:
        print(f"n[red]Error: {e}[/red]")
        import traceback
        traceback.print_exc()
 
if __name__ == "__main__":
    foremost()

Alternatively, you’ll be able to run the tutorial notebooks within the Amazon Bedrock AgentCore GitHub repository.

Pricing and availability

Amazon Bedrock AgentCore gives versatile, consumption-based pricing with no upfront commitments or minimal charges. AgentCore Browser can be utilized independently of the opposite companies. You may attempt AgentCore companies at no extra cost till September 16, 2025. After this date, AgentCore Browser Device shall be charged primarily based on consumption. Billing is calculated per second, utilizing the best watermark of CPU and reminiscence utilization for that second, with a 1-second minimal. 128 MB minimal reminiscence billing applies. Community information switch via buyer elastic community interfaces is billed at normal Amazon Elastic Compute Cloud (Amazon EC2) charges

For extra details about pricing, go to Amazon Bedrock AgentCore (Preview) Pricing.

Conclusion

Amazon Bedrock AgentCore Browser Device marks a transformative development in AI-powered internet automation, providing organizations a completely managed, cloud-based browser answer. AgentCore Browser Device addresses vital limitations confronted by generative AI techniques requiring real-time information entry, enabling AI brokers to work together naturally with web sites via capabilities akin to full navigation management, visible understanding, and seamless integration with frameworks akin to Playwright and Amazon Nova Act. By utilizing this device, companies can now implement refined automation at scale throughout numerous use circumstances—from streamlining repetitive internet duties and conducting AI-enhanced analysis to automating complicated workflows and integrating with legacy techniques—all whereas benefiting from the dependable cloud infrastructure of AWS that adapts to organizational wants with out the operational overhead of managing browser farms.

Sources

To study extra and begin constructing, go to the next sources:

Concerning the authors

Veda Raman is a Senior Specialist Options Architect for generative AI and machine studying at AWS. Veda works with prospects to assist them architect environment friendly, safe, and scalable machine studying purposes. Veda focuses on generative AI companies like Amazon Bedrock and Amazon SageMaker.

Rahul Sharma is a Senior Specialist Options Architect at AWS, serving to AWS prospects construct and deploy, scalable Agentic AI options. Previous to becoming a member of AWS, Rahul spent greater than decade in technical consulting, engineering, and structure, serving to corporations construct digital merchandise, powered by information and machine studying. In his free time, Rahul enjoys exploring cuisines, touring, studying books(biographies and humor) and binging on investigative documentaries, in no specific order.

Kishor Aher is a Principal Product Supervisor at AWS, main the Agentic AI staff answerable for creating first-party instruments akin to Browser Device, and Code Interpreter. As a founding member of Amazon Bedrock, he spearheaded the imaginative and prescient and profitable launch of the service, driving key options together with Converse API, Managed Mannequin Customization, and Mannequin Analysis capabilities. Kishor commonly shares his experience via talking engagements at AWS occasions, together with re:Invent and AWS Summits. Outdoors of labor, he pursues his ardour for aviation as a common aviation pilot and enjoys enjoying volleyball.