Doubao prompt volatility tracking
doubaoprompt_volatilityAccount required
Doubao is volatile because its sources are: short-video content turns over far faster than reference content, so the citation set moves week to week even when nothing about your brand changes.
How it renders
Derived across the sample set and across runs over time.
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
Doubao volatility is mostly source churn, not model behaviour. Reporting it as instability misses that the underlying content genuinely changed.
What the API returns
A single collection call against Doubao for the prompt volatility field, sampled n times and returned as one object per prompt.
{
"engine": "doubao",
"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. |
Doubao prompt volatility FAQ
- Why does Doubao move so much?
- Its corpora refresh constantly. A week-old Doubao reading is materially staler than a week-old AI Overview reading.
- How often should I re-run?
- More often than the Western engines. We will recommend a cadence for your category.
Set a Doubao cadence that matches its churn
We will run a volatility pass and recommend how often to collect.
Across every engine
Compare how prompt volatility behaves on every engine we track.
Prompt volatility across all engines →