- Industry
- Retail
- Department
- Marketing
- Team
- Brand and Insights
- Kind
- Investigator
- Approver
- Customer Service Manager
- Code
- MKT-12
It tracks mentions of the retailer and its private-label brands across news, social, product reviews and forums, detects spikes in volume or negative sentiment against the baseline, and explains which stories, products, stores or delivery problems are driving them. It logs each finding in the communications tracker and opens an alert for the communications owner, drafting a holding statement when a product safety or crisis story is spreading. **The problem it solves:** Why mentions or negative sentiment about the retailer or its brands spiked: which stories, products, stores or service failures drive it, and how far it has spread.
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 social listening tool: mentions, reach and sentiment for the brands and products named over the window and the baseline, with product review ratings from the e-commerce platform..
- 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 communications tracker: it logs the finding and opens an alert for the communications owner. and records what was done.
What it works with
Your knowledge, your systems, your people.
Knows
The brand monitoring guide: monitored brand and private-label names, sentiment baselines, crisis thresholds, the product safety and recall escalation path, and the holding statement templates.
Reads from
the social listening tool: mentions, reach and sentiment for the brands and products named over the window and the baseline, with product review ratings from the e-commerce platform.
Acts in
the communications tracker: it logs the finding and opens an alert for the communications owner.
Hands back
An object with volume_change_percent, negative_change_percent, drivers (a ranked list, each with driver, evidence, reach and confidence), products_flagged (a list, each with sku, rating_before and rating_now), safety_mentions (a list) and holding_statement (text or null).
Asks a person when
A story reaches 250000 people, a mention reports a product safety hazard, or a holding statement is drafted.
Settings
Your limits, set by your managers.
| Setting | Default | What it controls |
|---|---|---|
| Baseline window (days) | 28 | Volume and sentiment are compared with this many days before. |
| Negative spike (%) | 50 | Negative mentions this far above the baseline make a spike. |
| Crisis reach | 250000 | A negative story reaching this many people is treated as a crisis. |
| Product rating drop that is flagged (stars) | 0.5 | A SKU's average review rating falling this much in the window is flagged. |
| Draft a holding statement | On | When on, a crisis or safety story gets a draft holding statement. |
Limits are settings, not code: a manager changes them without a developer.
Rules it always follows
- Compare volume and sentiment with the last 28 days; a rise of 50 percent in negative mentions is a spike.
- Weigh competing drivers for each spike: a product fault or safety claim, a delivery or click-and-collect failure, a store incident, a pricing complaint, a campaign or a news story, and name the evidence for each.
- Any mention of injury, a choking, fire or allergen hazard, or a contaminated product goes to the product safety team at once, because it may start a recall.
- Flag any SKU whose review rating falls 0.5 stars in the window.
- A negative story reaching 250000 people is a crisis; when on is true, draft a holding statement, which is never published without the Customer Service Manager.
See the Brand Monitoring Agent agent on your own work.
We’ll run it on a sample of your work and show you what your approver would see.