The problem
Simply opening an Amazon product page may give your agent only a few visible reviews. More feedback can require opening other pages or changing how reviews are displayed. The agent needs a tool that can collect the written reviews before it can explain what customers like or dislike.
How NativePort helps
NativePort connects to Amazon through a review-collection tool on Apify and brings back the available customer feedback. Your agent can use those reviews to explain what buyers like, identify recurring complaints, and show examples. Share the product link with your agent and ask what customers are saying.
Let your agent build it
You don’t need to write this code yourself. Copy the prompt and paste it into your agent. It will follow NativePort’s setup guide, help you use an existing account or create one, read this page, and ask what you’d like to do next.
View prompt
Help me use NativePort for this use case. 1. Read https://nativeport.ai/SKILL.md and follow its instructions to learn how to use NativePort. Save or update the skill if your environment supports it. 2. Check whether I already have a working NativePort connection or account. Reuse it if available. Otherwise, help me sign in or create an account by following the skill's setup instructions. Guide me through any steps that require me to use a browser, then help connect my agent. Keep credentials private. 3. Follow the skill to learn how to find the right tools, check their prices and instructions, and use them through NativePort. 4. Read this entire use-case page, including the instructions for agents inside the accordion: https://nativeport.ai/use-cases/extract-amazon-reviews/ Once setup is complete and you have read the page, briefly explain what you can help me do and ask me what I would like to do next. Wait for my answer before implementing the example or running paid tools.
Instructions for the agents - You don't need to read this
Technical implementation
Use Python 3 with requests installed (python -m pip install requests). Set NATIVEPORT_API_KEY in your environment to your NativePort key. Run the snippets on your server, where your key stays private.
Set AMAZON_PRODUCT_URL to a public Amazon product URL. This example requests up to ten recent reviews in one run using the Actor’s documented inputs.
import json
import os
import requests
BASE = "https://api.nativeport.ai"
HEADERS = {"Authorization": f"Bearer {os.environ['NATIVEPORT_API_KEY']}"}
TERMINAL = {"SUCCEEDED", "FAILED", "TIMED-OUT", "ABORTED"}
def call(method, path, **kwargs):
response = requests.request(method, BASE + path, headers=HEADERS, timeout=90, **kwargs)
response.raise_for_status()
return response.json()
run = call(
"POST",
"/apify/v2/acts/junglee~amazon-reviews-scraper/runs",
params={"waitForFinish": 60},
json={"productUrls": [{"url": os.environ["AMAZON_PRODUCT_URL"]}],
"maxReviews": 10, "sort": "recent",
"includeGdprSensitive": False},
)["data"]
while run["status"] not in TERMINAL:
run = call("GET", f"/apify/v2/actor-runs/{run['id']}", params={"waitForFinish": 60})["data"]
reviews = call("GET", f"/apify/v2/datasets/{run['defaultDatasetId']}/items")
if not isinstance(reviews, list):
raise RuntimeError("Expected a dataset of review records")
print(json.dumps(reviews, indent=2, ensure_ascii=False))The limit is a requested maximum; the collector may return fewer reviews. Availability varies by product and marketplace, and the sample does not represent every buyer. Keep review dates and product identifiers with the text before passing it to your agent. A larger collection runs the same way; page its dataset with limit and offset (see the Apify reference).
Tool costs
| Tool used in the example | Price per call |
|---|---|
| Apify — Amazon Reviews Scraper, one bounded run | Priced from Apify's reported cost for the request or run (usage-based) |
Prices in USD. Usage-based tools have no fixed per-call price. View pricing.
Keep exploring
Build a larger history of customer reviews
Let your agent collect and page through available reviews beyond a small initial sample.
View guide
Collect large datasets and retrieve them when ready
Let your agent start a bounded collection job and return for its results without starting over.
View guide
Compare prices and availability across countries
Let your agent inspect how the same product page appears to visitors in different countries.
View guide
Explore all use cases
Find the next tool your agent needs, from web access to voice and document processing.
All use cases