Independent AI Search Benchmarking
When someone asks an AI platform for a cosmetic dentist nearby, only a small number of practices may appear—and the answers can change across repeated searches.
We use predetermined question panels, repeated observations, and multiple AI platforms to measure which businesses appear—and how consistently.
Research Now in Development
A regional study in development examining how AI platforms answer the questions prospective patients ask. The benchmark will examine:
Why Measurement, Not Screenshots
AI recommendation lists can change between repeated queries, platforms, locations, and sessions. A practice may appear in one response and not another.
That's why the benchmark will use repeated runs of a predetermined question panel, spread across days, platforms, and phrasings, with sample sizes and variation reported clearly.
A single screenshot provides limited evidence of persistent visibility or meaningful change.
For Practices in the Study
The benchmark will analyze a predefined sample of cosmetic dentistry practices across the Philadelphia region. If your practice is included, you may request a private summary showing how often it appeared, the types of questions in which it appeared, and how it compared with an anonymized regional benchmark.
No charge, and no obligation attached.
Firefly Clover may also work with selected practices to interpret their results and address documented visibility gaps.
Request Your ResultsWho We Are
Firefly Clover Research is an independent measurement practice based in the Philadelphia area. It was founded by an actuary with nearly two decades of experience measuring uncertainty, evaluating evidence, and communicating risk.
We don't promise rankings. We measure visibility and quantify variation. The study methodology—including question selection, observation period, metrics, and limitations—will be published with the benchmark.