Monitoring competitor costs is important for ecommerce groups to take care of a market edge. Nevertheless, many groups stay trapped in guide monitoring, losing hours day by day checking particular person web sites. This inefficient strategy delays decision-making, raises operational prices, and dangers human errors that end in missed income and misplaced alternatives.
Amazon Nova Act is an open-source browser automation SDK used to construct clever brokers that may navigate web sites and extract information utilizing pure language directions. This publish demonstrates the way to construct an automatic aggressive worth intelligence system that streamlines guide workflows, supporting groups to make data-driven pricing selections with real-time market insights.
The hidden price of guide aggressive worth intelligence
Ecommerce groups want well timed and correct market information to remain aggressive. Conventional workflows are guide and error-prone, involving looking out a number of competitor web sites for sure merchandise, recording pricing and promotional information, and consolidating this information into spreadsheets for evaluation. This course of presents a number of vital challenges:
- Time and useful resource consumption: Guide worth monitoring consumes hours of employees time on daily basis, representing a big operational price that scales poorly as product catalogs develop.
- Information high quality points: Guide information entry introduces inconsistency and human error, doubtlessly resulting in incorrect pricing selections primarily based on flawed info.
- Scalability limitations: As product catalogs develop, guide processes change into more and more unsustainable, creating bottlenecks in aggressive evaluation.
- Delayed insights: Probably the most vital challenge is timing. Competitor pricing can change quickly all through the day, that means selections made on stale information may end up in misplaced income or missed alternatives.
These challenges prolong far past ecommerce. Insurance coverage suppliers routinely evaluation competitor insurance policies, inclusions, exclusions, and premium buildings to take care of market competitiveness. Monetary providers establishments analyze mortgage charges, bank card provides, and charge buildings by time-consuming guide checks. Journey and hospitality companies monitor fluctuating costs for flights, lodging, and packages to regulate their choices dynamically. Whatever the business, the identical struggles exist. Guide analysis is gradual, labor-intensive, and susceptible to human error. In markets the place costs change by the hour, these delays make it nearly unimaginable to remain aggressive.
Automating with Amazon Nova Act
Amazon Nova Act is an AWS service, with an accompanying SDK, designed to assist builders construct brokers that may act inside net browsers. Builders construction their automations by composing smaller, focused instructions in Python, combining pure language directions for browser interactions with programmatic logic corresponding to assessments, breakpoints, assertions, or thread-pooling for parallelization. By way of its device calling functionality, builders can even allow API calls alongside browser actions. This offers groups full management over how their automations run and scale. Nova Act helps agentic commerce eventualities the place automated brokers deal with duties corresponding to aggressive monitoring, content material validation, catalogue updates, and multi-step searching workflows. Aggressive worth intelligence is a powerful match as a result of the SDK is designed to deal with real-world web site habits, together with format modifications and dynamic content material.
Ecommerce websites often change layouts, run short-lived promotions, or rotate banners and elements. These shifts usually break conventional rules-based scripts that depend on mounted component selectors or inflexible navigation paths. Nova Act’s versatile, pure language command-driven strategy helps brokers proceed working whilst pages evolve, offering the resilience wanted for manufacturing aggressive intelligence techniques.
Widespread constructing blocks
Nova Act features a set of constructing blocks that simplify browser automation. This can be utilized by ecommerce firms to gather and file product costs from web sites with out human intervention. The constructing blocks that allow this embrace:
Extracting info from a webpage
With the extraction capabilities in Nova Act, brokers can collect structured information straight from a rendered webpage. You possibly can outline a Pydantic mannequin that represents the schema that they need returned, then ask an act_get() name to reply a query in regards to the present browser web page utilizing that schema. This retains the extracted information strongly typed, validated, and prepared for downstream use.
Nova.act_get(“Seek for ‘iPad Professional 13-inch (M4 chip), 256GB Wi-Fi’.”, schema=ProductData.model_json_schema())
Navigate to a webpage
This step redirects the agent to a selected webpage as a place to begin. A brand new browser session opens at a desired start line, enabling the agent to take actions or extract information.
nova.go_to_url(website_url)
Operating a number of periods in parallel
Worth intelligence workloads usually require checking dozens of competitor pages in a brief interval. A single Nova Act occasion can invoke just one browser at a time, however a number of cases can run concurrently. Every occasion is light-weight, making it sensible to spin up a number of in parallel and distribute work throughout them. This permits a map‑scale back fashion strategy to browser automation the place totally different Nova Act cases deal with separate duties on the identical time. By parallelizing searches or extraction work throughout many cases, organizations can scale back complete execution time and monitor giant product catalogs with minimal latency.
from concurrent.futures import ThreadPoolExecutor, as_completed
from nova_act import ActError, NovaAct
# Accumulate the entire record right here.
all_prices = []
# Set max employees to the max variety of energetic browser periods.
with ThreadPoolExecutor(max_workers=10) as executor:
# Get all costs in parallel.
future_to_source = {
executor.submit(
check_source_price, product_name, source_name, source_url, headless
): source_name
for source_name, source_url in sources
}
# Gather the leads to all_books.
for future in as_completed(future_to_source.keys()):
strive:
supply = future_to_source[future]
source_price = future.outcome()
if source_price shouldn’t be None:
all_prices.prolong(source_price.supply)
besides ActError as exc:
print(f”Skipping supply worth resulting from error: {exc}”)
print(f”Discovered {len(all_prices)} supply costs:n{all_books}”)
Captchas
Some web sites current captchas throughout automated searching. For moral causes, we advocate involving a human to unravel captchas somewhat than making an attempt automated options. Nova Act doesn’t remedy captchas on the person’s behalf.
When working Nova Act regionally, your workflow can use an act_get() name to detect whether or not a captcha is current. If one is detected, the workflow can pause and immediate the person to finish it manually, for instance, by calling enter() in a terminal-launched course of. To allow this, run your workflow in headed mode (set headless=False, which is the default) so the person can work together with the browser window straight.
When deploying Nova Act workflows with AgentCore Browser Device (ACBT), you should use its built-in human-in-the-loop (HITL) capabilities. ACBT offers serverless browser infrastructure with stay streaming from the AgentCore AWS Console. When a captcha is encountered, a human operator can take over the browser session in real-time by the UI takeover function, remedy the problem, and return management to the Nova Act workflow.
outcome = nova.act(“Is there a captcha on the display screen?”, schema=BOOL_SCHEMA) if outcome.matches_schema and outcome.parsed_response:
enter(“Please remedy the captcha and hit return when executed”)
…
Dealing with errors
As soon as the Nova Act consumer is began, it might encounter errors throughout an act() name. These points can come up from dynamic layouts, lacking parts, or sudden web page modifications. Nova Act surfaces these conditions as ActErrors in order that builders can catch them, retry operations, apply fallback logic, or log particulars for additional evaluation. This helps worth intelligence brokers keep away from silent failures and proceed working even when web sites behave unpredictably.
Constructing and Monitoring Nova Act workflows
Constructing with AI-powered IDEs
Builders constructing Nova Act automation workflows can speed up experimentation and prototyping through the use of AI-powered growth environments with Nova Act IDE extensions. The extension is on the market for standard IDEs together with Kiro, Visible Studio Code, and Cursor, bringing clever code technology and context-aware help straight into your most well-liked growth setting. The IDE extension for Amazon Nova Act hastens growth by turning pure language prompts into production-ready code. As a substitute of digging by documentation or writing repetitive boilerplate, you may merely describe your automation targets. That is useful for advanced duties like aggressive worth intelligence, the place the extension will help you shortly construction ThreadPoolExecutor logic, design Pydantic schemas, and construct sturdy error dealing with.
Observing workflows within the Nova Act console
The Nova Act AWS console offers visibility into your workflow execution with detailed traces and artifacts out of your AWS setting by way of the AWS Administration Console. It offers a central place to handle and monitor automation workflows in real-time. You possibly can navigate from a high-level view of the workflow runs into the particular particulars of particular person periods, acts, and steps. This visibility lets you debug and analyze efficiency by displaying you precisely how the agent makes selections and executes loops. With direct entry to screenshots, logs, and information saved in Amazon S3, you may troubleshoot points shortly with out switching between totally different instruments. This streamlines the troubleshooting course of and accelerates the iteration cycle from experimentation to manufacturing deployment.
Operating the answer
That will help you get began with automated market analysis, we’ve launched a Python-based pattern mission that handles the heavy lifting of worth monitoring. This answer makes use of Amazon Nova Act to launch a number of browser periods directly, looking for merchandise throughout numerous competitor websites concurrently. As a substitute of going by tabs your self, the script navigates the online to seek out costs and promotions. It then gathers the whole lot right into a clear, structured format so you should use it in your personal pricing fashions. The next sections will describe how one can get began constructing the aggressive worth intelligence agent. After exploring, you may deploy to AWS and monitor your workflows within the AWS Administration Console.
The aggressive worth intelligence agent is on the market as an AWS Samples answer within the Amazon Nova Samples GitHub repository as a part of the Worth Comparability use case.
1. Conditions
Your growth setting should embrace: Python: 3.10 or later and the Nova Act SDK.
2. Get Nova Act API key:
Navigate to https://nova.amazon.com/act and generate an API key. When utilizing the Nova Act Playground or selecting Nova Act developer instruments with API key authentication, entry and use are topic to the nova.amazon.com Phrases of Use.
3. Clone the repo, set the API key, and set up the dependencies:
To get began, clone the repository, set your API key so the appliance can authenticate, and set up the required Python dependencies. This prepares your setting so you may run the mission regionally with out points. An API Key could be generated on Nova Act.
# Clone the repo
https://github.com/aws-samples/amazon-nova-samples.git
cd nova-act/usecases/price_comparison
# Create and activate a digital setting (non-compulsory however advisable)
python3 -m venv .venv
supply .venv/bin/activate
# Home windows:
.venvScriptsactivate
# Set up Python dependencies
pip set up -r necessities.txt
# Set the Nova Act API Key export NOVA_ACT_API_KEY=”your_api_key”
4. Operating the script
As soon as your setting is ready up, you may run the agent to carry out aggressive worth intelligence. The script takes a product title (non-compulsory) and an inventory of competitor web sites (non-compulsory), launches concurrent Nova Act browser periods, searches every web site, extracts worth and promotional particulars, and returns a structured, aggregated outcome.
The earlier instance makes use of the script’s default competitor record, which incorporates main retailers corresponding to Amazon, Goal, Finest Purchase, and Costco. You possibly can override these defaults by supplying your personal record of competitor URLs when working the script.
python -m important.py
–product_name “iPad Professional 13-inch, 256GB Wi-Fi”
–product_sku “MVX23LL/A”
–headless
The agent launches a number of Nova Act browser periods in parallel, one per competitor web site. Every session hundreds the retailer’s web site, checks whether or not a captcha is current, and pauses for person enter if one must be solved. As soon as clear, the agent searches for the product, opinions the returned outcomes, clicks probably the most related itemizing, and extracts the worth and promotional info. Operating these flows concurrently permits the agent to finish a multi-site comparability effectively.
For instance, when focusing on Amazon, the agent opens a contemporary browser session, navigates to amazon.com, and performs a site-specific seek for the product. It inspects the returned outcomes, identifies the product itemizing that almost all carefully matches the question, and extracts key particulars corresponding to worth, promotions, availability, and related metadata. This course of is mirrored within the following terminal output that displays every reasoning step (costs on this instance are illustrative and never consultant of actual market costs):
583c> act(“Is there a captcha on the display screen?, format output with jsonschema: {“kind”: “boolean”}”)
583c> …
583c> assume(“I’m on the Amazon homepage. My process is to return whether or not there’s a captcha on the display screen. I can look across the web page to try to discover a captcha. I do not see something that appears like a captcha. I additionally do not see something that looks as if it might require a captcha to be displayed. I ought to return false to point that there isn’t any captcha on the web page.”);
…
583c> act(“Seek for ‘iPad Professional 13-inch (M4 chip), 256GB Wi-Fi’.”)
583c> …
583c> assume(“I’m on the amazon homepage. My process is to seek for ‘iPad Professional 13-inch (M4 chip), 256GB Wi-Fi’. I see an empty search area. I have to kind ‘iPad Professional 13-inch (M4 chip), 256GB Wi-Fi’ into the search area.”);
583c> …
583c> assume(“I see that the search area is populated with ‘iPad Professional 13-inch (M4 chip), 256GB Wi-Fi’, however the search has not been initiated. Due to this fact, my final motion was not right. I see a search button to the suitable of the search area which can be utilized to finish the search. I’ll click on on the search button to finish the search.”);
…
583c> assume(“I’m now on the search outcomes web page for ‘iPad Professional 13-inch (M4 chip), 256GB Wi-Fi’. My process is full, and I have to return.”);
…
583c> assume(“I’m on the Amazon search outcomes web page for “iPad Professional 13-inch (M4 chip), 256GB Wi-Fi”. My process is to evaluation all the outcomes and discover probably the most related one, then extract the worth and any promotion particulars. I have to return the data within the specified JSON format. I see an inventory of merchandise, however the first few are sponsored. I ought to scroll down the web page to seek out probably the most related, non-sponsored product.”);
583c> …
583c> assume(“The web page has scrolled down and I see extra merchandise. My prior motion of scrolling down was profitable. I see the primary non-sponsored product, which is the “Apple iPad Professional 13-Inch (M4): Constructed for Apple Intelligence, Extremely Retina XDR Show, 256GB, 12MP Entrance/Again Digicam, LiDAR Scanner, Wi-Fi 6E, Face ID, All-Day Battery Life — House Black”. I ought to click on on the product to navigate to its web page and discover the worth and promotion particulars.”);
583c> …
583c> assume(“I’m now on the product web page for the “Apple iPad Professional (M4) 13-inch (M4 chip), 256GB Wi-Fi”. My prior motion of clicking on the product was profitable. I see the worth of the product is $1,039.99 and there’s a promotion for 19% off. I ought to return the worth and promotion particulars within the specified JSON format.”);
4. Reviewing the output
After the agent finishes looking out all competitor websites, it returns a consolidated desk that lists every retailer, the matched product, the extracted worth, the promotion particulars, and extra metadata. From this desk, you may evaluate outcomes throughout a number of sources in a single view. For instance, the output may look as follows (costs on this instance are illustrative and never consultant of actual market costs):
| Supply | Product Title | Product SKU | Worth | Promotion Particulars |
|——–|————–|——-|——-|——————-|
| Amazon | Apple iPad Professional (M4) 13-inch (M4 chip), 256GB Wi-Fi | MVX23LL/A | $1,039.99 | 19% off |
| Finest Purchase | Apple – 13-inch iPad Professional M4 chip Constructed for Apple Intelligence Wi-Fi 256GB with OLED – Silver | MVX23LL/A | $1239.00 | Save $50 |
| Costco | iPad Professional 13-inch (M4 chip), 256GB Wi-Fi | MVX23LL/A | $1039.99 | $200 OFF; financial savings is legitimate 11/12/25 by 11/22/25. Whereas provides final. Restrict 2 per member. |
| Goal | Apple iPad Professional (M4) WiFi with Commonplace glass | MVX23LL/A | $999.00 | Sale ends Wednesday |
The agent writes the extracted outcomes to a CSV file to later combine with pricing instruments, dashboards, or inner APIs.
Conclusion
Amazon Nova Act transforms browser automation from a posh technical process right into a easy pure language interface, so retailers can automate guide workflows, scale back operational prices, and acquire real-time market insights. By considerably lowering the time spent on guide information assortment, groups can shift their focus to strategic pricing selections. The answer scales effectively as monitoring wants develop, with out requiring proportional will increase in assets. Nova Act allows builders to construct versatile, sturdy brokers that ship well timed insights, decrease operational effort, and assist data-driven pricing selections throughout industries.
We welcome suggestions and would love to listen to how you employ Nova Act in your personal automation workflows. Share your ideas within the feedback part or open a dialogue within the GitHub repository. Go to the Nova Act to study extra or discover extra examples on the Amazon Nova Samples GitHub Repository.
Concerning the authors
Nishant Dhiman
Nishant Dhiman is a Senior Options Architect at AWS primarily based in Sydney. He comes with an in depth background in Serverless, Generative AI, Safety and Cellular platform choices. He’s a voracious reader and a passionate technologist. He likes to work together with prospects and believes in giving again to group by studying and sharing. Outdoors of labor, he likes to maintain himself engaged with podcasts, calligraphy and music.
Nicholas Moore
Nicholas Moore is a Options Architect at AWS, serving to companies of all sizes – from agile startups to Fortune International 500 enterprises – flip concepts into actuality. He focuses on cloud options with a give attention to synthetic intelligence, analytics, and fashionable utility growth. Nicholas is acknowledged for his contributions to the technical group by architectural patterns and thought management, in addition to his dedication to utilizing expertise for good by volunteer work.
Aman Sharma
Aman Sharma is an Enterprise Options Architect at AWS, the place he companions with enterprise retail and provide chain prospects throughout ANZ to drive transformative outcomes. With over 21 years of expertise in consulting, architecting, migration, modernization and answer design, he’s enthusiastic about democratizing AI and ML, serving to prospects craft purposeful information and ML options. Outdoors of labor, he enjoys exploring nature, music and wildlife images.
