E-commerce & Dropshipping · n8n

Product Review Summarizer: 500 competitor reviews distilled into what buyers actually want

An n8n workflow that scrapes the reviews of any Amazon or AliExpress product with an Apify actor, has Claude cluster them into top praises, top complaints, and unmet wishes, and writes a one-page product-improvement brief to Google Sheets — market research that used to take a weekend, done in minutes.

difficulty Intermediatesetup 40 minresult A buyer-voice brief per product: what to advertise, what to fix, what to bundle
  1. 1

    Trigger with a product URL

    Add an n8n Form Trigger with two fields: product URL and review count (default 300). You run this on demand per product you're researching — it's an analysis tool, not a scheduled job.

  2. 2

    Scrape reviews via Apify

    An HTTP Request node calls Apify's run-sync-get-dataset-items endpoint for the review actor matching your marketplace. Pass the product URL and max results. The response is a clean JSON array of review texts, ratings, and dates — no HTML parsing on your side.

  3. 3

    Distill with Claude

    A Code node concatenates review texts (capped to fit the context window, newest first), then an HTTP Request to Claude asks for the five-section brief in structured JSON. One long prompt beats many small ones here — clustering needs to see all reviews at once.

  4. 4

    Write the brief to Sheets

    A Google Sheets node appends one row per product: URL, date, and the five sections in separate columns. Over time this sheet becomes your niche's voice-of-customer database — searchable, comparable, yours.

Frequently asked questions

Which review sources work?

Anything Apify has a maintained actor for: Amazon, AliExpress, Etsy, Walmart, Trustpilot. You paste the actor ID and product URL into the trigger form. The Claude analysis step is source-agnostic — it just reads review text.

How much does a run cost?

Apify's review actors typically cost $0.30–$1 per 500 reviews on the free-tier credits, and one Claude summarization call on that batch is a few cents. Call it under $1.50 per product analyzed — versus hours of reading.

What exactly does the brief contain?

Five sections: top 5 praises with frequency estimates, top 5 complaints, feature wishes buyers mention, recurring quality-control issues, and three ad angles pulled from the reviewers' own wording. The last one is the sleeper hit — copy written in customer language converts.

Related recipes

TikTok Trend Product Radar: spot winning dropshipping products twice a week, automatically

An n8n workflow that scrapes trending TikTok product videos twice a week, has Claude score each product for saturation and audience fit, then logs everything to Google Sheets and pings your Telegram with the top 5.

Intermediate · 45 min setup

Low-Stock Alert: never oversell again — a ping before inventory hits zero

An n8n workflow that checks your Shopify inventory levels twice a day, flags every variant below its reorder threshold, and sends one consolidated Telegram message listing exactly what to reorder — instead of you discovering stockouts from angry customer emails.

Beginner · 20 min setup

Competitor Price Watch: know within the hour when a rival changes a price

An n8n workflow that checks a list of competitor product pages on a schedule, extracts the current price with Claude (so layout changes don't break it), compares against the last known price in Google Sheets, and pings your Telegram the moment something moves.

Intermediate · 45 min setup
About this recipe. Recipes on FlowRecipesHub are written for business owners, not developers, and are tested before publishing — how recipes get made. Some ingredient links are affiliate links that cost you nothing — full disclosure.