Nostimates

Microsoft Copilot prompt volatility tracking

copilotprompt_volatilityAnonymous

Copilot is comparatively stable because it leans on a fixed index rather than a fan-out process, so volatility scores here run lower than on the Google surfaces.

How it renders

Derived across the sample set.

Sampling

Volatility is what tells you the right n for every other field. We recommend using it to allocate credits: sample noisy prompts deeply, stable prompts lightly.

Gotcha

Stability driven by index dependence means Copilot movement usually reflects a Bing index change, not an AI behaviour change. Diagnose accordingly.

What the API returns

A single collection call against Microsoft Copilot for the prompt volatility field, sampled n times and returned as one object per prompt.

{
  "engine": "copilot",
  "field": "prompt_volatility",
  "prompt": "best ai visibility tracking tool",
  "country": "GB",
  "language": "en",
  "n": 30,
  "volatility": {
    "jaccard": 0.42,
    "mention_variance": 0.11,
    "recommended_n": 75,
    "band": "moderate"
  }
}
GET /v1/collect?engine=copilot&field=prompt_volatility

Response fields

KeyTypeNotes
jaccardfloatMean pairwise citation-set overlap across samples.
mention_variancefloatVariance in brand presence across samples.
recommended_nintegerSamples needed for a ±10 point interval on this prompt.
bandstringstable | moderate | volatile.

What it costs

Derived from samples you already pay for. No separate charge.

See credit pricing →

Microsoft Copilot prompt volatility FAQ

Why is Copilot stable?
Its citations come from Bing's index, which moves more slowly than a generative retrieval process.
What does a Copilot swing mean?
Usually a Bing index change. Check organic before blaming the model.

Separate index movement from model movement

We'll set up Copilot volatility tracking alongside your other engines.

No newsletter. One reply from a human.

Across every engine

Compare how prompt volatility behaves on every engine we track.

Prompt volatility across all engines →