The agent pulls every new review across your listings and marketplaces, with the rating, text, and variant bought.
2
Cluster the complaints
Reviews are grouped by cause — sizing runs small, arrived broken, instructions confusing — not by keyword, by meaning.
3
Separate listing problems from product problems
"Smaller than expected" with a correct size chart is a listing fix; the same complaint with a wrong chart is a product fix. Different owners, different lists.
4
Draft the fixes
For listing causes, it drafts the bullet or image caption that answers the complaint before the next buyer asks.
5
Weekly digest
One email: top complaint clusters, trend vs last month, drafted fixes awaiting your approval.
What it needs
Inputs & tools
ReviewsFreshCrawl
Your catalogListing IDs
CadenceWeekly
OutputDigest + draft fixes
ApprovalHuman approves edits
Your time≈ 20 min/week
The classic find: a third of a product's 2★ reviews say "stopped working in a week" — all for one variant. That's not a quality crisis, it's one bad batch, and the agent surfaces it in week one instead of month three.
Run this agent yourself
⚡
1 · Get a FreshCrawl subscription
The agent runs on live marketplace data. FreshCrawl plans start free (1,000 credits), paid plans from $29/mo — every plan includes MCP access and an API key. freshcrawl.io →
🔗
2 · Link the MCP to your LLM
In Claude or ChatGPT, add a custom FreshCrawl MCP connector — server crawl.onewally.com/mcp — and paste your FreshCrawl API key. Your LLM can now pull live offers, Buy Box history, and sales estimates itself.
📋
3 · Paste the prompt
Copy the prompt below into your LLM and name your store. The agent runs against the live data it can now reach — no code, no exports.
Copy the prompt
Starter prompt
Step 3 · Paste this into your LLM
# Review Miner
Use the FreshCrawl MCP connected to this chat for all live marketplace data.
MY STORE (fill in once):
- Store name: [your store name]
- Seller ID or storefront URL: [paste it — the agent uses it to find your catalog]
- Marketplace: [Walmart US / Amazon US]
First, use the FreshCrawl MCP to look up my store, pull my catalog,
and work only on my listings. If you can't identify my store from
what I gave you, ask me for my storefront URL before anything else.
RUN SCHEDULE (set this where you run the prompt):
- Run this prompt: weekly, Mondays at 6:30 AM.
- If your LLM app supports scheduled/recurring tasks, set it there; otherwise re-paste the prompt on that cadence.
Pull all my 1–3 star reviews from the last 7 days across every
listing. Cluster them by root cause (meaning, not keywords). Split
each cluster into "listing problem" vs "product problem". For
listing problems, draft the bullet or caption that would have
prevented the complaint. Return: ranked clusters with counts, one
example review each, and the drafted fixes.
EXECUTION — READ CAREFULLY:
Analysis and drafts only. You never edit my listings or reply to reviews — I publish what I approve.
The prompt gets you the shape. The reliable version runs on live data through the MCP — that's steps 1 and 2 above.
Rewrites titles, bullets, and keywords from what converts in your category.
Questions sellers ask
Does it reply to reviews?
No. It mines reviews for fixes and drafts listing changes. Public replies stay human — your voice in public is not an automation.
What if I sell on several marketplaces?
It merges them — the same complaint on Amazon and Walmart counts once, with both sources noted, so a pattern can't hide by splitting across channels.
How accurate is the clustering?
It groups by meaning using the review text and the variant purchased; borderline reviews are quoted verbatim in the digest so you can judge.
Run this on your store.
Every agent here runs on live FreshCrawl data through the MCP. Start free, connect your LLM, paste the prompt — or get the free Buy Box Loss Report and see the data first.