Microsoft Copilot brand mentions tracking
Copilot names brands in prose alongside its footnotes, and mention tracking picks up the references its numbered citations leave out.
How it renders
Plain text in the answer body, separate from the footnote list.
Sampling
Mentions are more stable across samples than citations, because the model's underlying association with a category changes more slowly than its choice of sources.
Gotcha
What the API returns
A single collection call against Microsoft Copilot for the brand mentions field, sampled n times and returned as one object per prompt.
{
"engine": "copilot",
"field": "brand_mentions",
"prompt": "best ai visibility tracking tool",
"country": "GB",
"language": "en",
"n": 30,
"mentions": [
{
"brand": "Nostimates",
"alias_matched": "Nostimates",
"count": 2,
"mention_rate": 0.57,
"linked": true
},
{
"brand": "Competitor",
"alias_matched": "Competitor AI",
"count": 1,
"mention_rate": 0.3,
"linked": false
}
]
}Response fields
| Key | Type | Notes |
|---|---|---|
| brand | string | Canonical brand from your configured list. |
| alias_matched | string | The exact surface form found in the answer text. |
| count | integer | Occurrences within a single answer. |
| mention_rate | float | Share of the n samples in which the brand appeared. |
| linked | boolean | Whether the mention was also a citation. |
| context | string | Surrounding sentence, for evidence export. |
What it costs
Included in the base collection. Alias lists are configured per project at no extra cost.
See credit pricing →Microsoft Copilot brand mentions FAQ
- Why are Copilot mention counts low?
- Shorter answers name fewer brands. The rate matters more than the raw count on this surface.
- Does it correlate with Bing?
- Mentions less than citations. The prose is model-generated; the footnotes come from the index.
Complete your Copilot picture with mentions
We'll run your brand list across your Copilot prompt set.
Other Microsoft Copilot data
Across every engine
Compare how brand mentions behaves on every engine we track.
Brand mentions across all engines →