# Measuring AI visibility by sampling prompts

> AI visibility is a share of runs, so one run measures nothing. A 2025 study found results stabilise at about 30 runs, with 60 or more for low-visibility brands. Measure in the product customers use, since one 2026 test found DeepSeek recommended a brand in 69% of API runs but 1% of app runs. Separate category and brand-name prompts, and date every figure.

- URL: https://geo.casa/measurement/ai-visibility-measurement/
- Guide · Observed in practice
- Reviewed: 2026-10-27

Search platforms report some AI data: Google counts impressions in AI features, and Bing counts citations. See [Generative AI performance report: AI Overviews and AI Mode in Search Console](https://geo.casa/measurement/search-console-ai-features/) and [Bing AI Performance report](https://geo.casa/measurement/bing-ai-performance/). Other assistants, such as Doubao, DeepSeek or ChatGPT's app, publish nothing. The only way to know whether they mention you is to ask them many times and count. This entry covers how to do that so the numbers mean something.

## Visibility is a proportion

The same prompt to the same model returns different brands from run to run. So "are we recommended?" has no yes/no answer. The measurable quantity is **the share of runs that mention you**, and a share estimated from a few runs is mostly noise.

Basic statistics sets the floor. For a proportion *p* measured over *N* independent runs, the standard error is √(p(1−p)/N). (This calculation is ours, not taken from either source.)

| Runs per prompt (N) | Standard error at 20% visibility | at 50% | 95% range at 50% |
|---|---|---|---|
| 5 | ±18 pts | ±22 pts | ±44 pts |
| 10 | ±13 pts | ±16 pts | ±31 pts |
| 30 | ±7 pts | ±9 pts | ±18 pts |
| 60 | ±5 pts | ±6 pts | ±13 pts |
| 100 | ±4 pts | ±5 pts | ±10 pts |

Runs are not fully independent in practice (same account, same hour, cached retrieval), so real error is usually larger than this.

> **Observed in practice:**
> In September 2025, Miaozhen Marketing Science Institute asked three models (DeepSeek, Doubao, Yuanbao) 2,025 times in all. It used one typical question per product category, five categories, and 135 runs per model. It concluded that results reach basic stability only at 30 or more runs. High-visibility brands (over 80%) were more stable than mid (50%) or long-tail (20%) ones. Low-visibility brands need 60 runs or more.
>
> Sources: [中国商务广告协会AI营销应用工作委员会 · 秒针营销科学院: 2025年中国GEO行业发展报告](https://g4-img-all.oss-cn-beijing.aliyuncs.com/video/50108560/01503a0d1eaeb4429ee3c0014738e9ea.pdf)

The study's reported spreads at 30 runs (±6–8%) are close to the standard errors above. Its figures at 100 runs (±2%) are smaller than sampling theory allows (±4–5 points). Treat that row with caution, because the report doesn't say how the spread was computed.

## Test where your customers ask

> **Observed in practice:**
> A 2026 study of Pilates studios in Hefei ran the same questions through vendor APIs and through consumer apps on phones. Doubao gave similar results in both. Qwen recommended the brand in 78% of API runs but 53% of app runs. DeepSeek and Yuanbao were reversed: DeepSeek 69% by API against 1% in the app, and Yuanbao 3% by API against 99% in the app.
>
> Sources: [腾讯新闻（报道合肥图灵象普拉提行业GEO白皮书）: 行业首份GEO白皮书：AI正在重写'附近哪家好'的答案](https://news.qq.com/rain/a/20260909A0EGBH00)

The API and the consumer app can run different models, retrieval settings, system prompts and location handling. So the API is not a cheap proxy for what people see. Measure in the product your customers use, logged out or with a fresh account. Ask from the city your customers ask from. If you also run the API for scale, keep the two sets of numbers apart.

A brand's visibility on one platform says little about another, and being mentioned is not the same as being mentioned first.

> **Observed in practice:**
> In Xsignal's infant formula monitoring (DeepSeek, Doubao, Yuanbao, Kimi; 1–26 June 2025), Friso Prestige had the highest mention rate on DeepSeek (60.6%) and Yuanbao (64.7%). It ranked 5th on Doubao and 13th on Kimi. On Yuanbao, Aptamil's total mention rate was 38.44% against Friso Prestige's 60.55%. Yet Aptamil was named first far more often (28.39% against 5.78%). The report does not disclose the number of prompts or repeats. (Brand names and quotes translated from Chinese.)
>
> Sources: [Xsignal（奇异因子）: AI搜索时代：从GEO到AIBE的品牌新蓝图（GEO白皮书 2026）](https://repository.ceibs.cn/ws/portalfiles/portal/65520358/_AI_GEO_AIBE_GEO_2026_.pdf)

Report each platform separately, and record the position of the first mention as well as whether the brand appeared at all.

## Choose prompts that reflect demand

> **Observed in practice:**
> In the same study, the studio appeared in only 34% of answers to niche pre-purchase questions, such as who is good at postnatal recovery. Broad category questions returned it 77% of the time.
>
> Sources: [腾讯新闻（报道合肥图灵象普拉提行业GEO白皮书）: 行业首份GEO白皮书：AI正在重写'附近哪家好'的答案](https://news.qq.com/rain/a/20260909A0EGBH00)

A prompt that contains your brand name nearly always returns your brand. That proves little, because new customers ask category questions ("best Pilates studio near me for back pain"). Build the prompt set from real customer questions. Group prompts by intent and report each group separately. Brand-name prompts are still useful for checking that what assistants *say* about you is accurate.

## A minimal protocol

1. **Fix the prompt set** before you start, and keep it unchanged between rounds so results compare. Version it when you must change it.
2. **Record the environment** for every run: product (app or API), model or mode, account state, location, date.
3. **Run each prompt at least 30 times** per environment per round. Use more runs for prompts where you are rarely mentioned.
4. **Report proportions with their range**, for example "41% ± 9 pts, n = 30, Doubao app, Shanghai, 2026-10". Never show a single screenshot as a result.
5. **Expect movement between rounds.** Models and retrieval change, so a change smaller than the sampling error is not a result. Treat any claim of a "stable #1" position in AI answers with suspicion.
6. **Keep the raw answers.** Counting rules change, and you will want to recount.

Third-party GEO tools do this sampling for you. They observe answers from the outside, like you would. None of them sees inside Google's systems ([Claim: GEO tools can see your rankings inside Google's AI](https://geo.casa/measurement/third-party-ai-tools/)).

## Sources

- [中国商务广告协会AI营销应用工作委员会 · 秒针营销科学院: 2025年中国GEO行业发展报告](https://g4-img-all.oss-cn-beijing.aliyuncs.com/video/50108560/01503a0d1eaeb4429ee3c0014738e9ea.pdf)
- [腾讯新闻（报道合肥图灵象普拉提行业GEO白皮书）: 行业首份GEO白皮书：AI正在重写'附近哪家好'的答案](https://news.qq.com/rain/a/20260909A0EGBH00)
- [Xsignal（奇异因子）: AI搜索时代：从GEO到AIBE的品牌新蓝图（GEO白皮书 2026）](https://repository.ceibs.cn/ws/portalfiles/portal/65520358/_AI_GEO_AIBE_GEO_2026_.pdf)