Daily Amazon Negative Review Triage to Linear and Slack

Build me an agent workflow that triages new Amazon negative reviews every morning. It should run on a cron at 8am in my local time zone, Monday through Friday.

Inputs the user configures once: a list of Amazon ASINs to monitor, the Amazon marketplace country (default US), the Linear team that should receive issues, the Slack channel for the digest, and a short paragraph of brand voice guidelines for the drafted replies.

For each ASIN, call Real-Time Amazon Data Get Top Product Reviews. This returns the eight publicly visible top reviews without needing a logged-in Amazon cookie, which is what makes it safe for an unattended cron. Keep a small piece of state (a list of review IDs already seen per ASIN) so the agent only acts on reviews that are new since the last run.

For each new one or two star review, the agent should: (1) classify the root issue into one of product quality, shipping or packaging, sizing or fit, unclear instructions, customer expectation mismatch, or defective unit; (2) draft a polite, specific seller reply in our brand voice that does not violate Amazon's review response policies (no asking for the review to be removed, no offering compensation in public, no personal contact info in the public reply, just empathy plus a clear next step); (3) decide a severity of low, medium, or high based on whether the complaint reads like a one-off, a known issue, or a recurring product defect.

For every medium or high severity review, call Linear Create Issue in the configured team. The issue title should be the ASIN plus a short summary of the complaint. The description should include the full review text, reviewer name and star rating, the chosen issue category, the severity, the drafted seller reply ready to copy into Seller Central, and a link to the product page on Amazon. Set Linear priority to High for high severity and Normal for medium.

At the end of the run, call Slack Send a Message to post a single digest into the configured channel. The digest should include: total reviews triaged, breakdown by issue category, breakdown by severity, and a bulleted list of the newly created Linear issues with their issue keys and titles linked. If there were no new negative reviews, post a short all-clear message instead.

Keep the agent focused and quiet. Do not open Linear issues for low severity reviews. Do not post per-review Slack messages, only the daily digest. Do not attempt to publish the reply to Amazon, it is meant to be human-reviewed.

Additional information

What does this prompt do?

Checks your Amazon product listings each morning for new one and two star reviews since the last run.
Classifies each negative review by root cause (product quality, shipping, sizing, instructions, mismatched expectations, defective unit) and flags low, medium, or high severity.
Drafts a polite, on-brand seller reply for each review that stays inside Amazon's response policies.
Opens a Linear issue for every medium or high severity review with the full context, drafted reply, and a link back to the product.
Posts one Slack digest at the end with counts by category and links to the new Linear issues so the team knows what to handle first.

What do I need to use this?

A RapidAPI account subscribed to the Real-Time Amazon Data API.
A Linear workspace where you can create issues in your support or product team.
A Slack workspace and a channel for the daily digest.
The list of Amazon product IDs (ASINs) you want monitored.

How can I customize it?

Change the schedule (for example, twice a day, or only weekdays) or pick a different time zone.
Adjust the list of product IDs and the marketplace country (US, UK, DE, and others are supported).
Tune what counts as high severity, which Linear team the issues go into, or which Slack channel gets the digest.
Edit the brand voice guidelines so the drafted replies sound like your store.

Frequently asked questions

Does this send the seller reply automatically?

No. The reply is drafted and attached to the Linear issue so a human can review, tweak, and post it from inside Amazon Seller Central. Public review responses are sensitive and should stay human-approved.

How many reviews per product does it check each day?

It pulls the top eight publicly visible reviews per product, which is what Amazon shows without a logged in session. That is enough to catch fresh negative feedback for active listings. If you want deeper history, you can extend the workflow.

Will it create duplicate Linear issues for the same review?

No. The agent tracks which reviews it has already triaged and only opens new Linear issues for reviews it has not seen before.

Can I monitor products across more than one Amazon marketplace?

Yes. Real-Time Amazon Data supports two dozen marketplaces. You can run separate schedules per country or pass a list of regions to the same workflow.

What if a review is borderline, neither a clear defect nor a simple complaint?

The agent marks borderline reviews as low severity, drafts a reply, and skips Linear. You will still see them counted in the Slack digest so nothing slips through.