Instead of infinite prompt variations, this measurement framework tracks canonical core entities across AI models to score brand visibility over time.
TL;DR: We don't do prompt tracking because prompts are infinite variants of canonical core intent entities (we look at those instead).
Read on though. It's worth going beyond surface claims.
Let's start with an example:
Core Entity:
Queries:
Prompts:
I started running about three months ago and I'm now doing 3 runs a week, around 5 to 8 km each, mostly on footpaths and some gravel trails on the weekend. I've been using an old pair of gym trainers and my shins are starting to ache after longer runs. I'm based in Melbourne and my budget is about $200 AUD. I'd prefer to buy online if returns are free, but I'm open to going into a store if getting fitted makes a big difference. Where should I buy my first proper pair of running shoes?
User: I need new running shoes.
AI: Do you want help choosing a model, or finding where to buy them?
User: Where to buy. I already know I want something with good cushioning.
AI: Do you prefer to buy online or in a store?
User: Online is fine, but I want free returns in case they don't fit.
AI: What country are you in?
User: Australia.
So I see people do this:
I'm a 27 year old female from Sydney looking to buy some running shoes...
My expert opinion and comment on that is:
LOL.
Unethical, creepy and bundled with a looooooot of mathematical fudge, formulas and extrapolations between sparse data points. At this point you might as well just give up and make up synthetic prompts.
Even in cases where people willingly volunteer their chat history you're getting that demographic only. I bet you're not it yourself and don't know many people who are willing to surrender their most personal conversations for a small benefit or a tiny fee.
app.dejan.ai tracks the core entity. Each tracked entity, such as "running shoes", goes to Google, OpenAI and Anthropic models with web search on, using one fixed prompt:
Recommend brands for a user searching for the supplied query. When mentioning the brand in your response wrap each brand name like this:
`[[brand]] Text goes here.`
Example: `[[Microsoft]] A short blurb relevant to user query goes here.` `[[Google]] A short blurb relevant to user query goes here.`
Don't enumerate.
The markers let us record which brands the model names, in what order, and which pages it cites. We run the same probe for each target location on a daily, weekly or monthly cadence, and the results become visibility scores per entity, per location and per brand over time.
The wording never changes between runs, so when a brand's share moves, the cause is a change in the model or in the web results it retrieved.
We also ask the same question with web search off. That answer shows what the model knows about the market from its training data, separate from what it finds when it searches.
Answers vary from run to run even when the input is identical, so one answer is one sample. Our association probes repeat each entity up to 100 times, and our relevance probes take up to 100 independent samples per brand and entity pair. We report the share of answers in which a brand appears, because a single answer can change on the next run.
app.dejan.ai sends prompts to AI models in one place: Citation Mining. A run asks the models your prompts, queries or entities with web search on and records the pages they cite and the pages they read but do not cite. The prompt is only a way to reach the sources the models use for a topic, and we do not measure the prompt itself.
This is not what happens in the real world, it's also not how people search or what chat sessions look like or how models respond. There is no pretence here. This is a measurement framework.