Halcy Research

When a patient asks AI for a doctor, which practices get named?

Usually, no independent one. We sampled 200 independent practices at random and ran nearly 5,000 patient-realistic prompts through ChatGPT. It named zero of them.

This is the running record of what large language models actually say when people look for care – which practices surface, which sources the models trust, and what the visible practices do differently. Built from our own measurement corpus, shared openly.

Practices
200
Prompts
~4,950
Specialties
18
Metros
20
Model
GPT-5.5
Run
May 2026

ChatGPT mentioned and cited 0 of 200 randomly-sampled independent practices.

The findings

On-site · Deep dive

Why ChatGPT doesn’t mention your practice

The 0-of-200 result, the five on-site signals almost no practice has, and why your specialty and metro set your ceiling.

Read the on-site findings
Off-site · Interactive map

Where ChatGPT gets its answers

An interactive map of 38,178 citation events – the hospital rosters, associations, and magazines the model actually pulls from, pivotable by specialty.

Explore the citation map
Dental · Deep dive

ChatGPT’s top dental source is the practice’s own website

Across 1,405 dental questions, practice-owned websites drew 53.8% of the 13,152 sources ChatGPT cited – more than three times the next category. The full mix by sub-specialty and metro.

Read the dental findings

How we measured it

Every figure on this site comes from our own measurement corpora, not estimates.

For the medical corpus we drew a stratified random sample of independent practices from the NPPES registry across 18 specialties and 20 metros, then ran a fixed battery of patient-realistic prompts – scoped to each practice’s specialty and metro – through GPT-5.5 via the OpenAI API, with multiple runs per query to absorb variance. We separate a mention (your name in the answer a patient reads) from a citation (a URL the model pulls from), and anchor on mentions wherever the data supports it. In June and July 2026 we ran a parallel dental corpus the same way – 1,405 patient-realistic dental questions across 20 metros and seven areas of dentistry, with all 13,152 cited sources categorized by type. Single-platform, US-only, correlational. Behavior on Gemini and Google AI Overviews may differ.

New to AI search optimization? Our plain-language guides in Learn explain the concepts behind this research.

Disclosure. Halcy is a commercial service; the practices we work with pay for these deployments. We ran this corpus for our own product development and publish it openly so administrators can audit their own AI presence regardless of any vendor relationship.