Kimi prompt volatility tracking
kimiprompt_volatilityAccount required
Kimi is the most stable Chinese surface we track, because long-document retrieval changes far more slowly than short-form web or social content.
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 makes Kimi cheap to measure but slow to move. Do not promise a client a Kimi shift inside a quarter — document-level retrieval does not turn over that fast.
What the API returns
A single collection call against Kimi for the prompt volatility field, sampled n times and returned as one object per prompt.
{
"engine": "kimi",
"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"
}
}Response fields
| Key | Type | Notes |
|---|---|---|
| jaccard | float | Mean pairwise citation-set overlap across samples. |
| mention_variance | float | Variance in brand presence across samples. |
| recommended_n | integer | Samples needed for a ±10 point interval on this prompt. |
| band | string | stable | moderate | volatile. |
Kimi prompt volatility FAQ
- Why is Kimi stable?
- Its sources are long documents that change rarely, so retrieval is consistent between runs.
- How long until content changes show?
- Longer than on any other engine. Plan reporting cycles accordingly.
Set realistic Kimi expectations with a baseline
We will run a baseline pass so movement later can be proven against it.
Other Kimi data
Across every engine
Compare how prompt volatility behaves on every engine we track.
Prompt volatility across all engines →