AI Visibility (GEO)
How AIEO.ee measures your brand across AI answer engines.
GEO (Generative Engine Optimization) is the practice of getting your brand mentioned and cited by AI answer engines. AIEO.ee measures this when you start a run.
Core metrics
| Metric | What it answers |
|---|---|
| Mention rate | In what share of AI answers does your brand appear at all? |
| Citation rate | In what share of answers is your domain cited as a source? |
| Share of voice (SOV) | Of all brand mentions across your prompts, what share is yours vs competitors? |
| Citation breakdown | Which domains do engines cite — and why is it not you? |
Engines
AIEO.ee tracks six engines, each with real retrieval behind it. Five run on paid accounts today; Doubao is coming soon, once its search price is verified:
- ChatGPT, Gemini, Perplexity are read from the real consumer product through scraping vendors (DataForSEO, Bright Data). The answer is the one a user of that product sees.
- Qwen, DeepSeek, Doubao use each vendor's official API with web search on (Alibaba Bailian, DeepSeek, Volcengine Ark). This approximates the consumer app; the run says who ran the search.
Your prompt is sent as written, with no system prompt. Citations come only from the sources the engine returned. Each run is labeled Real product UI or Official API · web search; runs recorded under the old method are labeled Legacy sampled data and left out of current metrics. See data sources for vendors and timing.
The engine list is defined once in code (packages/core/src/engines.ts) and
rendered from that single source on the marketing site and in the product.
Prompts & scheduling
You track prompts — the questions your customers ask AI. Each prompt has a
category and an engine list, and runs when you start it. Every
prompt × engine attempt is billed at its actual cost and sent to the vendor
at most once; a failed attempt is never retried automatically.
Scraped engines finish asynchronously, and DeepSeek runs only between 22:00
and 08:00 Beijing time.
GEO tracking calls paid third-party APIs, so it needs an active subscription.
Competitor benchmarks
SOV is computed against the competitor brands you configure for the project, so "who is winning AI answers in my category" is one chart, not a research project.