Introducing Amazon Bedrock AgentCore Browser Software

At AWS Summit New York Metropolis 2025, Amazon Web Services (AWS) introduced the preview of Amazon Bedrock AgentCore browser device, a completely managed, pre-built cloud-based browser. This device allows generative AI brokers to work together seamlessly with web sites. It addresses two elementary limitations: first, foundation models (FMs) are educated on giant however static datasets and want dynamic entry to present data when API entry isn’t available; second, organizations face important challenges when trying to scale internet automation with AI for enterprise use circumstances.

The event of agentic AI techniques is transferring towards purposes that may execute complicated, multistep duties. For these brokers to be efficient, they require entry to dynamic, real-time knowledge, significantly from web sites and internet purposes that don’t provide 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 Software offers these capabilities, permitting brokers to carry out duties corresponding 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 important want for enterprises to deploy AI automation at scale throughout 1000’s of concurrent periods, supporting use circumstances from customer support automation to large-scale knowledge assortment and evaluation, with out the normal complexity and useful resource constraints of self-managed browser automation frameworks.

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

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

Conventional browser automation approaches have sometimes required important infrastructure administration, safety concerns, and improvement experience. The introduction of a completely managed, cloud-based browser automation answer addresses a number of important wants, together with simplified infrastructure administration, enterprise-grade safety, world availability and scaling, and value optimization. Organizations not must provision, preserve, and scale browser cases to help their automation wants. AWS now handles the complicated infrastructure necessities, so builders can give attention to constructing clever agent capabilities fairly than managing browser farms. Cloud-based browser automation offers remoted execution environments with AWS safety controls, decreasing the danger of knowledge exfiltration or unauthorized entry that 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 an alternative 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 Software, organizations can now implement subtle browser automation at scale. Cloud-based browser automation excels at minimizing handbook execution of repetitive duties throughout internet interfaces. AI brokers can populate complicated internet types throughout a number of techniques, validate entries, and preserve compliance with enterprise guidelines. Brokers can navigate to inner dashboards, extract important metrics, and compile reviews with out human intervention. For organizations managing giant 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 change into highly effective analysis assistants. They mechanically observe associated web sites for pricing adjustments, new product launches, or content material updates with common monitoring. You should utilize AI brokers to assemble and analyze client sentiment throughout numerous internet boards, evaluate websites, and social domains to tell product improvement. With the AgentCore Browser Software, you’ll be able to create automated techniques that repeatedly scan trusted data 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 Software 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 providers 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 allows strong testing at scale. You should utilize AgentCore Browser Software to validate person experiences and performance throughout completely different situations, units, and browsers in parallel. Deploy brokers to repeatedly work together with important enterprise purposes and arrange alerts to your groups about efficiency points earlier than clients encounter them. With AgentCore Browser Software, you’ll be able to repeatedly check internet purposes for accessibility compliance, safety vulnerabilities, or regulatory necessities.

Legacy system integration: Many organizations preserve legacy techniques that lack fashionable APIs. Allow fashionable AI capabilities to work together with legacy internet purposes that might be pricey to switch 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 worthwhile organizational knowledge trapped in older internet purposes by way of common, automated harvesting.

Core capabilities

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

Net 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 corresponding to scrolling, hovering, and clicking

Serverless browser infrastructure

• Zero-management browser fleet with automated patching
• Seamless scaling from single session to 1000’s based mostly on demand
• International deployment choices with usage-based pricing
• Optimized efficiency with out infrastructure overhead

Visible understanding

• Full-page screenshots enabling AI comprehension of structure and content material
• Visible aspect identification by look and place
• Content material extraction from graphical components
• 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 Identity and Access Management (IAM) controls for entry administration
• Ephemeral browser periods that reset after every use

Complicated internet utility help

• Full compatibility with fashionable 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 file 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 fairly than being restricted to API-based integrations.

How an AI agent can use AgentCore Browser Software

Amazon Bedrock AgentCore Browser runs in a safe, remoted containerized setting inside AgentCore, insulating internet exercise out of your native system. You may work together with the AgentCore Browser Software utilizing browser actuation libraries, corresponding to Playwright, or use AI agentic frameworks specialised for browser automation, corresponding 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 Software to take pure language directions from the person and convert them to actuations on the browser by following this workflow:

1. The person sends a question corresponding to “seek for sneakers on Amazon”
2. An agentic framework corresponding to Amazon Nova Act or Browser Use passes the question to the large language model (LLM)
3. The LLM causes and generates directions in a structured output format (for instance, JSON encoded)
4. The agentic framework maps these directions into browser actuation instructions (corresponding to Playwright, Puppeteer, or Selenium)
5. The browser actuation instructions are executed on the AgentCore Browser over a safe WebSocket connection
6. The response from the browser and a screenshot are despatched to the agent to motive additional

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

Get began

The Amazon Bedrock AgentCore Browser Software is out there to be used right this moment. 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 Software, you could full the next conditions:

• 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 part within the repository you cloned at: 01-tutorials/05-AgentCore-tools/02-Agent-Core-browser-tool/interactive_tools

You can too visualize the browser reside 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 Software straight with the Playwright library and the Amazon Bedrock AgentCore SDK. This instance initiates a safe browser session, connects to it, and automates an easy workflow wherein it navigates to https://www.amazon.com and searches for a product.

1. To get began with playwright:

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

2. Set up dependencies:

3. 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 preserve 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]
        strive:
            web page.goto("https://amazon.com/")
            console.print(web page.title())
            # Preserve working
            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:

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

pip set up nova-act

6. Writer your Nova Act based mostly 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 most important():
    strive:
        # 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 main points of the bottom priced one on the primary web page")
                    console.print(f"n[bold green]Nova Act End result:[/bold green] {outcome}")
            
            # Preserve working
            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__":
    most important()

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

Pricing and availability

Amazon Bedrock AgentCore provides versatile, consumption-based pricing with no upfront commitments or minimal charges. AgentCore Browser can be utilized independently of the opposite providers. You may strive AgentCore providers at no further cost till September 16, 2025. After this date, AgentCore Browser Software will probably be charged based mostly 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 knowledge switch by way of buyer elastic community interfaces is billed at commonplace Amazon Elastic Compute Cloud (Amazon EC2) charges

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

Conclusion

Amazon Bedrock AgentCore Browser Software marks a transformative development in AI-powered internet automation, providing organizations a completely managed, cloud-based browser answer. AgentCore Browser Software addresses important limitations confronted by generative AI techniques requiring real-time knowledge entry, enabling AI brokers to work together naturally with web sites by way of capabilities corresponding to full navigation management, visible understanding, and seamless integration with frameworks corresponding to Playwright and Amazon Nova Act. By utilizing this device, companies can now implement subtle 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 be taught extra and begin constructing, go to the next sources:

In regards to the authors

Veda Raman is a Senior Specialist Options Architect for generative AI and machine studying at AWS. Veda works with clients to assist them architect environment friendly, safe, and scalable machine studying purposes. Veda makes a speciality of generative AI providers like Amazon Bedrock and Amazon SageMaker.

Rahul Sharma is a Senior Specialist Options Architect at AWS, serving to AWS clients 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 firms construct digital merchandise, powered by knowledge and machine studying. In his free time, Rahul enjoys exploring cuisines, touring, studying books(biographies and humor) and binging on investigative documentaries, in no explicit order.

Kishor Aher is a Principal Product Supervisor at AWS, main the Agentic AI workforce accountable for creating first-party instruments corresponding to Browser Software, 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 repeatedly shares his experience by way of 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 taking part in volleyball.