Reviews · from an X post, Nov 12, 2026 · Added

Review Requests Ad Check by Ratings, Profit and Returns with Claude

Decide which products, if any, should use Amazon's paid Review Requests ad before you spend on it

$18.57

“the product lost $18.57”

Per source From a vendor-affiliated source (see Worth knowing), not independently verified.

Copy-paste prompt

Copy-paste promptPrompt written by us, based on this case
For every product in my catalog, show: total ratings, last 30 days' units, net profit per unit after fees, ad spend and cost of goods, return count and top return reasons, and the main themes of reviews from the last 60 days. Then mark which products qualify for Amazon's Review Requests ad (under 1,000 ratings) and, of those, which are profitable with few complaints. Don't recommend paying for ratings on any product that lost money in the last 30 days.

The source didn't publish its exact prompt. We wrote this starter so you can try the same workflow. Replace anything in [brackets].

See the original X post

What they did

Nhan Dinh, CEO of Seller Labs, checked his own products against Amazon's new Review Requests ad (a US-only beta since late October 2026), which only qualifies products under 1,000 ratings. His best-selling gardening gloves have 1,819 ratings, so they're locked out. His espresso cup set qualifies at 351 ratings, but at $25.99 a sale makes about $2 after fees and cost. He lays out five checks per product and says the slow two (are buyers happy, and is review count really what holds sales back) are one question in Claude with the Seller Labs MCP connected, which pulls profit, returns and recent reviews for every product.

How it went

Over 30 days, two buyers returned a set and the product lost $18.57, so a paid rating could cost more than a sale earns. His call: "My best seller can't use this ad. The one that can, I shouldn't pay for. Not yet."

We only report what the source says. Results are self-reported unless noted.

Worth knowing

Vendor-affiliated: he runs Seller Labs, which makes the MCP, and the post doesn't show the Claude output itself. Amazon hasn't said what Review Requests bills for, and a paid prompt asks every recent buyer, unhappy ones included.

Original source

X postNhan Dinh (Seller Labs) (@NhanTDinh)Published Nov 12, 2026 · x.com https://x.com/NhanTDinh/status/2120887145770414521Open the source

Keep going

Related use cases

ReviewsShows real resultsOlder post · Apr 2026

Review Clustering, Listing Rewrites and PPC Signals with Claude

Use one AI coworker across reviews, listings and search term reports for managed Amazon brands
~70%“reduced time spent on review analysis by ~70%” agency-reported
ToolsClaudeSourceBlog post · Ananth Kuchimanchi (Brandkyte)SharedApr 10, 2026PromptWritten by us
Show promptHide prompt for Review Clustering, Listing Rewrites and PPC Signals with Claude,Written by us
Here are the last [300] reviews for [ASIN] and my current listing: [paste]. Cluster the reviews into themes with counts, list the top complaints and buying triggers with a quote each, and map each one to a gap in my title, bullets or images. Then suggest bullet rewrites that close the top three gaps. Don't invent claims.

Reviews

Return Root Causes and One Listing Fix per ASIN with a Claude Skill

Find why a product gets returned and pick one listing change to test ToolsClaude, Adi (Claude skill)SourceBlog post · Ori FirouzSharedOct 20, 2026PromptWritten by us
Show promptHide prompt for Return Root Causes and One Listing Fix per ASIN with a Claude Skill,Written by us
For my 5 ASINs with the highest return cost, read the FBA customer returns report, the product's reviews and the current listing side by side. For each ASIN give:
- the likely root cause, with return counts, reason-code shares, 2-3 buyer quotes, the gap in the listing, and a confidence level (never 'high' from reason codes alone);
- ONE change to test (title under 75 characters, counted; image brief; size chart; or supplier brief);
- today's return rate as the baseline to check at 30 and 60 days.
Don't change anything and don't contact buyers.

Reviews

Competitor Review Mining with Claude

Classify competitor reviews into patterns and turn them into tested ad angles ToolsClaudeSourceX post · wetracked.ioSharedAug 28, 2026PromptSeller's own prompt
Show promptHide prompt for Competitor Review Mining with Claude,Seller's own prompt
You are a senior ecommerce customer-research and creative strategist.

I am giving you public Amazon reviews from competing products.

Analyze only the supplied reviews. Do not invent facts, product capabilities, customer quotes, frequencies, or conclusions.

First, classify each review as:
1. Product defect
2. Expectation gap
3. Setup or usability friction
4. Missing feature
5. Wrong customer or use case
6. Shipping, seller, or delivery noise
7. Isolated complaint with insufficient evidence

Then create a table showing:
• Complaint pattern
• Number of reviews mentioning it
• Situation in which it happens
• Consequence for the customer
• Outcome the customer wanted
• Objection our advertising must answer
• Proof required before making the claim
• Review IDs supporting the pattern

Do not treat one-star reviewers as representative of the entire market. Identify repeated patterns separately from isolated complaints.

Next, compare the negative reviews with any positive reviews I provide. Find where customers disagree and explain what product type, expectation, or use case may cause the difference.

Finally, create 12 original ad experiments for my product.

For every experiment, provide:
• Hook
• Body copy
• Visual concept
• Customer problem
• Promise
• Proof needed
• Awareness stage
• Hypothesis being tested
• Result we should measure

Do not copy review wording, use a reviewer as a testimonial, attack a named competitor, or claim our product solves a problem unless my product information supports it.

ReviewsShows real resultsOlder post · May 2025

Review Analysis for Listing Conversion with Claude

Find what buyers love in reviews and rebuild listing images around it
19.6%“a client's conversion rate rose 19.6%, from 25.86% to 30.93%” self-reported
ToolsClaude, Data DiveSourceYouTube video · George Schwartz (Extension Ecom)SharedMay 9, 2025PromptSeller's own prompt
Show promptHide prompt for Review Analysis for Listing Conversion with Claude,Seller's own prompt
please analyze the attached reviews and write the top five reasons why people love this product based on the order of frequency these reasons appear within the reviews

PPC & AdsShows real results

Replacing a PPC Agency with Claude and the Seller Labs MCP

Take Amazon ads back in-house from a $15,000/month agency
$75,000 a month“he was saving about $75,000 a month” vendor-affiliated
ToolsClaude, Seller Labs MCPSourceX post · Nhan Dinh (Seller Labs)SharedOct 19, 2026PromptWritten by us
Show promptHide prompt for Replacing a PPC Agency with Claude and the Seller Labs MCP,Written by us
You have read access to my Amazon Ads and sales data. Don't change anything without my approval.
1. List my current campaigns and the products each one covers. Flag any campaign that mixes different product formats.
2. Propose a structure with one campaign per product format, each with its own keyword list pulled from search terms that already convert for that format.
3. For every change you want to make (new campaign, bid, budget, negative), tell me what and why, and wait for my yes.
4. Each week, report spend, CPC, sales and units by product format against the week before.

PPC & AdsShows real results

Negative Keyword Cleanup with Claude and the Seller Labs MCP

Audit an ad account and add negatives for search terms that waste money
83 negative keywords“the AI added 83 negative keywords across the campaigns” vendor-affiliated
ToolsClaude, Seller Labs MCPSourceX post · Nhan Dinh (Seller Labs)SharedOct 16, 2026PromptWritten by us
Show promptHide prompt for Negative Keyword Cleanup with Claude and the Seller Labs MCP,Written by us
Audit my Sponsored Products search terms for the last 60 days. List every search term with spend and zero orders, grouped by campaign, with clicks and spend.
Before you change anything, write out the full change list: campaign, the negative you'd add, match type, and why. Flag any term that converts in other campaigns, since blocking it everywhere could cut sales. Wait for my OK.