Answer text tracking across AI answer engines
Answer text is the raw output of an AI engine, captured per sample. Nostimates stores every answer behind every metric, which is what lets a team show the actual sentence rather than only the percentage.
How it differs by engine
The answer body itself, before any of our parsing runs.
Google AI Overviews answer text
The summary block itself, captured before parsing.
google_ai_overviews
Google AI Mode answer text
The full multi-section answer body, captured before parsing.
google_ai_mode
ChatGPT answer text
The answer body, captured before parsing.
chatgpt
Perplexity answer text
The answer body with citation markers preserved in the stored markup.
perplexity
Microsoft Copilot answer text
The answer body captured before parsing.
copilot
Gemini app answer text
The answer body, captured before parsing.
gemini
DeepSeek answer text
The answer body, stored unmodified.
deepseek
Qwen answer text
The answer body, stored unmodified.
qwen
Doubao answer text
The answer body, stored unmodified.
doubao
Kimi answer text
The full answer body, stored unmodified.
kimi
Baidu ERNIE answer text
The SERP AI answer block, captured before parsing.
baidu_ernie
Naver answer text
The answer body, stored unmodified.
naver
Sampling
What the API returns
{
"engine": "google_ai_overviews",
"field": "answer_text",
"prompt": "best ai visibility tracking tool",
"country": "GB",
"language": "en",
"n": 30,
"samples": [
{
"sample_index": 1,
"tokens": 214,
"text": "Several APIs return AI answer data…",
"captured_at": "2026-08-03T09:14:22Z"
}
]
}Response fields
| Key | Type | Notes |
|---|---|---|
| text | string | Verbatim answer, markup stripped. |
| html | string | Original markup, for citation position reconstruction. |
| tokens | integer | Approximate length, useful for drift detection. |
| captured_at | timestamp | UTC collection time for this sample. |
| sample_index | integer | Which of the n samples this is. |
Answer text FAQ
- What is answer text tracking?
- Answer text is the raw output of an AI engine, captured per sample. Nostimates stores every answer behind every metric, which is what lets a team show the actual sentence rather than only the percentage.
- How is answer text sampled?
- Every sample is stored, not just the modal one. Divergence between samples is the raw material for the volatility metrics.
- What does answer text cost?
- Included. Evidence retention defaults to 90 days and is configurable.
Get answer text on your prompt set
Track it in the dashboard or pull it in through the API. Send us the prompts, the brands and the markets, and we'll come back with a per-engine coverage plan and the credit arithmetic behind it.