- Industry
- Procure AI
- Department
- Marketing
- Team
- Brand and Insights
- Kind
- Investigator
- Approver
- Marketing Lead
- Code
- MKT-12
It tracks mentions of our brand and services across trade press, professional social, review sites and procurement forums, detects spikes in volume or negative sentiment against the baseline, and explains which stories drive them, such as a supplier complaining publicly about a reverse auction we ran or a client's payment delays blamed on us. It logs each finding in the communications tracker. **The problem it solves:** Why brand mentions or negative sentiment spiked: which items, from which sources, about which engagement or event, and whether it is a one-off or a growing story.
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 with source, reach, sentiment and text for the period and baseline..
- 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 Marketing Lead with its reasoning before anything goes out.
- 06Acts
Once approved, it acts in the communications tracker: it logs each finding and escalation. and records what was done.
What it works with
Your knowledge, your systems, your people.
Knows
The brand monitoring setup, monitored sources, baseline sentiment, the crisis playbook, the rules for discussing client engagements and sourcing events in public, and holding statements.
Reads from
the social listening tool: mentions with source, reach, sentiment and text for the period and baseline.
Acts in
the communications tracker: it logs each finding and escalation.
Hands back
An object with period, volume_change_percent, negative_change_percent, drivers (a list with item, source, reach, sentiment and theme), escalate (true or false) and holding_statement (or null).
Asks a person when
The spike is escalated (reach above 50000, or payments, sanctions, bribery, a data breach or an executive is involved) or a holding statement is drafted.
Settings
Your limits, set by your managers.
| Setting | Default | What it controls |
|---|---|---|
| Baseline (days) | 30 | The window sentiment is compared with. |
| Negative spike (%) | 50 | A rise this large in negative mentions is a spike. |
| Reach that escalates | 50000 | A negative item with this reach escalates; trade audiences are small. |
| Sources | trade press, professional social, review sites, procurement forums | Where mentions are tracked. |
| Draft a holding statement | On | When on, a holding statement is drafted on escalation. |
Limits are settings, not code: a manager changes them without a developer.
Rules it always follows
- Compare with the 30-day baseline across trade press, professional social, review sites, procurement forums.
- A rise of 50 percent in negative mentions is a spike; explain it by the items driving it.
- Escalate a negative item with reach above 50000, or any that involves a client's payments to suppliers, a sanctions or bribery allegation, a data breach or an executive.
- Never confirm a client relationship or comment on a sourcing event in a holding statement.
- Draft a holding statement only when on is true.
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.