Nostimates

Microsoft Copilot brand mentions tracking

copilotbrand_mentionsAnonymous

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

Copilot's answers are shorter than AI Mode's, so mention counts per answer are low. Small absolute numbers here are normal, not a parsing fault.

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
    }
  ]
}
GET /v1/collect?engine=copilot&field=brand_mentions

Response fields

KeyTypeNotes
brandstringCanonical brand from your configured list.
alias_matchedstringThe exact surface form found in the answer text.
countintegerOccurrences within a single answer.
mention_ratefloatShare of the n samples in which the brand appeared.
linkedbooleanWhether the mention was also a citation.
contextstringSurrounding 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.

No newsletter. One reply from a human.

Across every engine

Compare how brand mentions behaves on every engine we track.

Brand mentions across all engines →