- Industry
- Retail
- Department
- Customer
- Team
- Customer Lifecycle
- Kind
- Investigator
- Approver
- Customer Service Manager
- Code
- CUS-15
It groups feedback from reviews, cases, surveys, store comment cards and marketplace ratings into themes such as sizing inconsistency, late delivery, queue times or product quality, and explains what is driving each theme. It ties each theme to the SKUs, stores, carriers or pages behind it so the owning team can act. **The problem it solves:** What is driving each feedback theme and its rise or fall in the period.
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 loyalty and CRM platform: reviews, case reasons, survey verbatims, store comments and marketplace ratings in the period, with returns by reason 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
Weighs competing explanations against the evidence and shows which one holds up.
- 05Asks a person
Hands the work to Customer Service Manager with its reasoning before anything goes out.
- 06Acts
Once approved, it acts in the loyalty and CRM platform: it records the themes and opens an action item for each owning team on spikes. and records what was done.
What it works with
Your knowledge, your systems, your people.
Knows
The feedback taxonomy: the theme list and definitions, the owning team for each theme, the known issues already being fixed, and the sources and their weighting.
Reads from
the loyalty and CRM platform: reviews, case reasons, survey verbatims, store comments and marketplace ratings in the period, with returns by reason for the SKUs.
Acts in
the loyalty and CRM platform: it records the themes and opens an action item for each owning team on spikes.
Hands back
A list with one entry per theme, each with theme, mentions, change_percent, spike (true or false), linked_to (a list of sku, store, carrier or page), likely_driver, evidence, owner_team and sample_quotes.
Asks a person when
A theme points to a product safety issue, a supplier quality failure or a single store's staff.
Settings
Your limits, set by your managers.
| Setting | Default | What it controls |
|---|---|---|
| Mentions that make a theme | 25 | A theme needs at least this many mentions in the period. |
| Rise that counts as a spike (%) | 50 | A theme up this much on the previous period is a spike. |
| Link sizing themes to returns data | On | When on, sizing themes are checked against the SKU's wrong-size return rate. |
Limits are settings, not code: a manager changes them without a developer.
Rules it always follows
- A theme needs at least 25 mentions; a rise of 50 percent or more on the previous period is a spike.
- Tie each theme to the SKUs, stores, carriers or pages behind it, and name the owning team.
- When on is true, check sizing themes against the SKU's wrong-size return rate.
- A theme about injury or a safety defect goes to product safety whatever its size.
- Weigh at least two explanations for each spike and say what evidence separates them; quote shoppers without their names.
See the Feedback Analysis Agent agent on your own work.
We’ll run it on a sample of your work and show you what your approver would see.