Reviews and Community Agent
Moderates product reviews and shopper Q&A and grows the community.
- Industry
- Retail
- Department
- Customer
- Team
- Customer Lifecycle
- Kind
- Assistant
- Approver
- Customer Service Manager
- Code
- CUS-11
It moderates product reviews, shopper questions and answers and the community forum against the review policy, publishing genuine reviews, rejecting fake or abusive ones and answering product questions from the PIM. It routes reviews that mention injuries or defects to product safety and flags incentivised reviews that are not disclosed.
How it works
6 steps, and a person signs off before step 6.
- 01Looks it up
Finds the record the request is about in the e-commerce platform's reviews and Q&A: the items to moderate, the reviewer's history and purchases, and the PIM attributes for the SKUs..
- 02Reads the request
Works out what is being asked and what a complete answer needs.
- 03Checks the facts
Checks figures, dates and rules against the source records, not from memory.
- 04Works it through
Prepares the draft, match, recommendation or reply, with its sources.
- 05Asks a person
Hands the work to Customer Service Manager with its reasoning before anything goes out.
- 06Acts
Once approved, it acts in the e-commerce platform's reviews and Q&A: it publishes, holds or rejects each item, posts answers and routes safety reviews. and records what was done.
What it works with
Your knowledge, your systems, your people.
Knows
The review and community policy: what may be published, the fake and incentivised review rules, the disclosure wording, the moderation reasons, and the product safety signals to escalate.
Reads from
the e-commerce platform's reviews and Q&A: the items to moderate, the reviewer's history and purchases, and the PIM attributes for the SKUs.
Acts in
the e-commerce platform's reviews and Q&A: it publishes, holds or rejects each item, posts answers and routes safety reviews.
Hands back
A list with one entry per item, each with item_id, decision (publish, publish_with_disclosure, hold, reject or route_safety), reason, answer (text or null) and safety_flag (true or false).
Asks a person when
A review reports an injury or a safety defect, alleges a legal breach, or names a member of staff.
Settings
Your limits, set by your managers.
| Setting | Default | What it controls |
|---|---|---|
| Publish only verified-purchase reviews | Off | When on, reviews without a matching purchase are held. |
| Reviews per reviewer a day before it is suspicious | 5 | A reviewer posting more than this in a day is held for fake-review checks. |
| Answer product questions itself | On | When on, it answers shopper questions from the PIM attributes. |
| Words that send a review to product safety | injury, burn, fire, shock, choking, broke and cut, rash | Comma-separated. |
Limits are settings, not code: a manager changes them without a developer.
Rules it always follows
- Never reject a review for being negative; reject only for abuse, personal data, off-topic content, competitor promotion or fakery.
- Hold reviews from reviewers posting more than 5 a day, and when off is true, reviews without a verified purchase.
- An incentivised review is published only with the disclosure label; an undisclosed incentivised review is held.
- A review mentioning any of injury, burn, fire, shock, choking, broke and cut, rash is published only after product safety has seen it, and is routed there at once.
- When on is true, answer questions only from the PIM attributes and say when the answer is not known.
See the Reviews and Community Agent agent on your own work.
We’ll run it on a sample of your work and show you what your approver would see.