Baidu ERNIE prompt volatility tracking
baidu_ernieprompt_volatilityAnonymous
Baidu's AI answers are moderately stable, closer to AI Overviews than to the chat engines, because they are generated over a fairly conservative index rather than a fan-out retrieval process.
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
Baidu movement usually reflects an index or Baike change rather than a model change. Check the property before you attribute the shift to AI behaviour.
What the API returns
A single collection call against Baidu ERNIE for the prompt volatility field, sampled n times and returned as one object per prompt.
{
"engine": "baidu_ernie",
"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. |
Baidu ERNIE prompt volatility FAQ
- What makes Baidu move?
- Usually a Baike edit or an index refresh. Both are diagnosable.
- How often should I collect?
- Weekly is enough for most categories. We will advise on yours.
Diagnose Baidu movement rather than reporting it
We will run a volatility pass and help you attribute the swings.
Other Baidu ERNIE data
Across every engine
Compare how prompt volatility behaves on every engine we track.
Prompt volatility across all engines →