aeogeoai.net
Miami AI Search Specialist
An Independent Cross-Sector Analysis of AI Citation Patterns Across 515 Miami-Dade Businesses — Health, Legal, and Real Estate.
The pattern holds across three completely different industries. ChatGPT, Claude, and Gemini almost never failed to answer — they answered by naming competitors while omitting the tested business, in health, law, and real estate alike.
The competitors that do get named are overwhelmingly large institutions — hospital systems, AmLaw firms, mega-developers — not comparable independent businesses. See Section 3.
This report documents observed AI citation patterns across 515 businesses tested during July 2026. It explains the methodology, presents the findings, discusses limitations, and explores what the results may mean for businesses seeking visibility in AI-generated recommendations.
This study measures AI citation presence — defined as whether a business is:
This study measures AI citation presence rather than Google rankings, website quality, reputation, or business tenure — and, uniquely among this report series, tests whether the pattern holds across sectors as different as healthcare, law, and real estate development. For businesses evaluating their own standing, the free AI Search Visibility Checker applies this same methodology on demand.
These findings should not be interpreted as measurements of:
Instead, they measure only AI citation presence — whether ChatGPT, Claude, or Gemini named a specific business by name — during the study period in July 2026.
Each business was queried individually across three AI systems using a standardised prompt. We tested whether the AI system included the named business in its recommendation-style answer.
This study measures observed output behaviour rather than internal model architecture. No conclusions are drawn regarding the proprietary ranking or retrieval mechanisms of ChatGPT, Claude, or Gemini beyond the responses produced during testing.
"best [category] in [city] FL"
Business selected
↓
Prompt generated ("best [category] in [city] FL")
↓
Query sent independently to ChatGPT, Claude, and Gemini
↓
Response collected from each model
↓
Automated secondary classifier scores each response
↓
Citation score assigned (0 / 1–34 / 35+) per model
↓
Highest score across the three models used as the business's headline result
Each business's category was used directly, or reduced to its primary field where a compound category was listed — e.g. "Physical Therapy / Rehabilitation" → "physical therapy". Example: a Coral Gables luxury real estate developer received the query "best luxury real estate developer in Coral Gables FL".
A binary name-match alone treats "AI discussed the right category and named three competitors, but not this business" identically to "AI has never heard of this business or its category" — both would score zero. This study distinguishes the two. A raw score of 35 or higher indicates the business's name was actually matched in the response — a genuine citation. Scores of 1–34 indicate category-adjacency: the right topic and location were discussed, and often specific competitors were named, but not the tested business. A score of 0 means no relevant signal was found at all — not even the category or competitors.
The 35-point threshold marks the point at which the classifier identified the business's own name as explicitly present in the response text, rather than only its category or general attributes being discussed. AEOGeoAI has not published a formal statistical derivation of this specific cutoff; it functions as a categorical boundary within our scoring system rather than a value derived from this dataset.
| Score | Meaning |
|---|---|
| 0 | No relevant signal — category not discussed |
| 1–34 | Category-adjacent — topic/competitors discussed, business not named |
| 35–59 | Genuine citation — business named, limited prominence |
| 60–79 | Genuine citation — consistently included |
| 80–100 | Genuine citation — prominently featured (none observed) |
The query format, scoring thresholds, and category-adjacency detection logic are documented in this section. Independent researchers with access to ChatGPT, Claude, and Gemini can reproduce the general approach using the identical query format and thresholds described above. Full row-level data is available on request — see the FAQ below.
Businesses were identified from commercially sourced contact lists, used only to identify candidate businesses to query — not to influence results. Commercial contact lists were used solely to identify businesses for inclusion; they were not used as sources for scoring, ranking, or classification. No business paid for inclusion in this study, and no business was excluded based on its citation outcome. Every business with a valid contact record in the source lists was queried and included in the published results, including the one true-zero result and the two genuine citations.
| Parameter | Value |
|---|---|
| Report ID | AEOGEOAI-MIA-COMBINED-2026-001 |
| Dataset ID | MIA-COMBINED-515-v1 |
| Sector | Sample size | Top categories tested | Primary geography |
|---|---|---|---|
| Health | 298 | Dentistry (19), Medical spa/aesthetics (14), Physical therapy (24 combined) | Miami (120), Fort Lauderdale, Coral Gables |
| Legal | 120 | General law firm (44), Personal injury (24), Real estate attorney (10) | Miami (46), Coral Gables, Fort Lauderdale |
| Real estate | 97 | Luxury developer (63), Multifamily developer (17), Commercial (9) | Miami (54), Coral Gables, Fort Lauderdale |
Individual business names are not published in this report. The underlying dataset is structured as follows:
| Column | Description |
|---|---|
| Business | Business name (withheld in this published report) |
| Sector | Health / Legal / Real estate |
| City | City used in the query |
| Category | Category used in the query |
| Claude score | 0–100 |
| Gemini score | 0–100 |
| ChatGPT score | 0–100 |
| Classification | True zero / Category-adjacent / Genuine citation |
| Competitors named | De-duplicated list of businesses named in place of the tested business |
| Parameter | Value |
|---|---|
| Total sample size | 515 businesses across 3 sectors |
| Geography | Miami-Dade County, with additional Broward County coverage (Fort Lauderdale, Hollywood, Plantation, Pembroke Pines) |
| Test period | July 2026 |
| Rate control | 4-second delay per query |
| Tooling | AEOGeoAI visibility scoring system with automated secondary classifier for category-adjacency and competitor extraction |
Limitations: AI outputs are probabilistic and may vary across time and model updates. Results represent a snapshot of observed behaviour in July 2026 and should not be interpreted as permanent or universal. Category sizes vary substantially within each sector — real estate ranges from 63 luxury developers to a single residential homebuilder — which limits category-level comparison within sectors, though the overall cross-sector pattern is unaffected by this imbalance. This study only tested ChatGPT, Claude, and Gemini — it does not include Google AI Mode or Google AI Overviews specifically, which use different retrieval mechanisms and were not part of this dataset.
Scope of these findings: this study describes the observed sample of 515 Miami-Dade businesses and is not intended to estimate AI citation prevalence across all businesses in Florida, or in any market beyond the three states covered in this report series.
Scoring definitions used below are documented in Section 1: Methodology.
The highest score achieved on any model (Claude, Gemini, or ChatGPT), per business, was used as that business's headline score. Across all 515 businesses:
| Statistic | Value |
|---|---|
| Mean (highest score per business) | 13.68 |
| Median (highest score per business) | 12.0 |
| Standard deviation | 4.05 |
| Minimum | 0 |
| Maximum | 50 |
These figures describe the observed sample only. No confidence interval is reported, since the sample was not drawn as a random probability sample of all Miami-Dade businesses — it reflects the commercially sourced contact lists described in Section 1.
| Outcome | Meaning | Businesses |
|---|---|---|
| True zero | No relevant signal — category not discussed at all | 1 (0.2%) |
| Category-adjacent, unnamed | Category and often competitors discussed — business never named | 512 (99.4%) |
| Genuinely named | The business itself was named by at least one model | 2 (0.4%) |
The 99.4% figure is the sharper finding. These businesses aren't falling outside AI's field of view — the opposite is true. ChatGPT, Claude, and Gemini are actively discussing their exact category and, in the large majority of cases, naming their competitors in the same response. The business itself is simply omitted from the answer.
Each sector below has its own full report with sector-specific competitor analysis, statistics, and FAQ.
| Sector | Tested | Category-adjacent | Genuine citation | Cross-model citation |
|---|---|---|---|---|
| Health → | 298 | 99.3% | 0.7% (2) | 0 |
| Legal → | 120 | 100% | 0% | 0 |
| Real estate → | 97 | 99.0% | 0% | 0 |
Legal produced the most uniform outcome of the three sectors — 100% category-adjacency, zero genuine citations across all 120 Miami-Dade law firms tested. This is the most complete evidence in this report series that the institutional-dominance pattern is not specific to healthcare. See the full Miami Legal AI Search Visibility Study → for sector-specific detail.
Two businesses held a genuine, direct name citation — both in the health sector, both named by ChatGPT alone. Neither achieved citation on more than one model, so this study observed zero cross-model citations across all 515 businesses tested.
| Business | Sector | City | Claude | Gemini | ChatGPT |
|---|---|---|---|---|---|
| Weston Cosmetic Surgery Center | Health | Weston | 1 | 21 | 50 |
| Miami Obstetrics & Gynecology | Health | Miami | 11 | 21 | 50 |
Both genuine citations occurred in health — the largest of the three samples — and neither category (cosmetic surgery, obstetrics & gynecology) was among the highest-volume health categories tested, unlike the companion Pennsylvania study where all genuine citations clustered in the two largest categories. With only two data points, this dataset can't determine whether category volume predicts citation likelihood.
Exactly one business across all 515 tested returned no relevant signal on any model: Propolis, a Miami multifamily developer, scored 0 across Claude, Gemini, and ChatGPT for "best multifamily developer in Miami FL." Every other business in the dataset — including all 297 other health practices, all 120 law firms, and the remaining 96 real estate developers — received at least a category-adjacent response.
Because our detection method captures category-adjacent responses rather than discarding them, we can extract exactly which businesses get named in place of the tested business — using only names that actually appeared in the model's response, not inferred or invented data. This is the same entity-signal gap covered in our AI Search Optimization Guide.
Counts represent the number of distinct businesses in this study whose ChatGPT, Claude, or Gemini responses named this organisation at least once. Each business contributes at most one count per organisation, regardless of how many of the three models named it — so counts cannot exceed the 515 businesses tested.
| Business named | Sector | Type | Times cited | % of businesses |
|---|---|---|---|---|
| Related Group | Real estate | Mega-developer | 95 | 18.4% |
| Cleveland Clinic Florida | Health | Hospital system | 51 | 9.9% |
| Lennar | Real estate | National homebuilder | 51 | 9.9% |
| Baptist Health South Florida | Health | Hospital system | 47 | 9.1% |
| Terra Group | Real estate | Mega-developer | 47 | 9.1% |
| Greenberg Traurig | Legal | AmLaw 100 firm | 46 | 8.9% |
| Arquitectonica | Real estate | Architecture firm | 42 | 8.2% |
| Shutts & Bowen | Legal | Regional firm | 40 | 7.8% |
| Akerman | Legal | AmLaw 200 firm | 36 | 7.0% |
| Swire Properties | Real estate | Mega-developer | 36 | 7.0% |
| Holland & Knight | Legal | AmLaw 100 firm | 33 | 6.4% |
| Fortune International Group | Real estate | Mega-developer | 31 | 6.0% |
| Jackson Memorial Hospital | Health | Hospital system | 29 | 5.6% |
| Mount Sinai Medical Center | Health | Hospital system | 27 | 5.2% |
| Kolter Group | Real estate | Mega-developer | 25 | 4.9% |
Across the sampled responses, AI systems most frequently recommended larger institutions — not independents — in every sector tested. When an independent business isn't named, the fallback is almost never "a different independent competitor." In health, it's a hospital system. In law, an AmLaw firm. In real estate, a mega-developer. For an independent business in any of these three sectors, the competition for an AI citation isn't the business down the street — it's Related Group, Cleveland Clinic Florida, or Greenberg Traurig.
Where AI names a specific alternative, the qualities it associates with them cluster around a small set of themes — consistent across sectors, despite the sectors themselves having nothing in common:
| Attribute | Times mentioned (combined across sectors) |
|---|---|
| Personalized care / service / approach | 88 |
| Luxury / high-end positioning | 81 |
| Comprehensive services / care | 47 |
| Multiple locations | 43 |
| Strong / excellent reputation | 20 |
| Advanced technology / modern facilities | 18 |
| Full-service firm / wide range of services | 14 |
| Long-established / strong local presence | 16 |
None of these are differentiators unique to large institutions — "personalized care" and "comprehensive services" are exactly the kind of claims an independent business's own website already makes, in any of the three sectors tested. The gap isn't in what independent businesses offer; it's in whether AI has independent, third-party confirmation of it.
See Full Methodology → for how these scores were generated.
The observed citation patterns are consistent with systems that rely heavily on externally confirmed entities drawn from multiple indexed sources, though this study did not have access to any model's internal retrieval process and cannot confirm the underlying mechanism directly. Based on the patterns observed in this dataset, inclusion is associated with:
Most businesses in this dataset lack sufficient third-party entity signals for inclusion in AI recommendations — independent of Google rankings, website quality, reputation, and tenure, and independent of which of the three sectors they operate in.
Signal gap vs ranking gap. This does not look like a ranking problem. It looks like an entity visibility problem — these AI systems surface entities with sufficient external confirmation signals, and large institutions simply have vastly more of that confirmation than any independent business, regardless of sector or care quality.
Zero businesses in this 515-business dataset achieved citation on more than one model — a stronger version of the pattern observed in the earlier Pennsylvania study, where only 1 of 163 achieved cross-model citation. Even genuine citation, where it occurs at all, appears to be largely model-specific rather than a stable, transferable form of entity authority.
Testing health, legal, and real estate together is a stronger test of the institutional-dominance thesis than testing any one sector alone. If the pattern were specific to healthcare — where hospital systems have unusually dense digital footprints — it might be a healthcare artifact rather than a structural finding. Finding a closely similar ~99% pattern in law firms and real estate developers, sectors with entirely different competitive dynamics and content ecosystems, is more consistent with something general about how these AI systems build local recommendations — though this remains an observed association across three sectors, not a proven causal mechanism.
Using the same query methodology and detection thresholds, we can compare Miami's three sectors against each other, and Miami's health results specifically against the earlier New Jersey and Pennsylvania health studies.
| Metric | Health (n=298) → | Legal (n=120) → | Real estate (n=97) → |
|---|---|---|---|
| True zero | 0% | 0% | 1.0% |
| Category-adjacent, unnamed | 99.3% | 100% | 99.0% |
| Genuinely named (1+ model) | 0.7% | 0% | 0% |
| Genuine cross-model citation | 0 | 0 | 0 |
| Metric | New Jersey (n=216) | Pennsylvania (n=163) | Miami (n=298) |
|---|---|---|---|
| Category-adjacent, unnamed | 98.6% | 96.3% | 99.3% |
| Genuinely named (1+ model) | 0.5% | 2.5% | 0.7% |
| Genuine cross-model citation | 0 | 1 | 0 |
The overall pattern replicates closely across three independently tested states and, within Miami, across three independently tested sectors: roughly 96–100% of independent businesses have no genuine AI citation, and the near-total majority of that group is category-adjacent — discussed by ChatGPT, Claude, or Gemini, but never named — rather than genuinely invisible. This consistency — across states and now across sectors — is more consistent with a structural feature of how these AI systems build local recommendations than with a single-state or single-industry anomaly. That said, the finding has only been tested in three states and three sectors; broader generalisation would require additional data.
Businesses without AI citation presence risk reduced discovery in AI-native search, and increasing dependence on traditional SEO channels as AI-driven local discovery grows — while their most likely "competitor" in a ChatGPT, Claude, or Gemini answer is a large institution with a permanent structural advantage in third-party coverage, regardless of sector.
Based on the observed citation patterns and inspection of the cited entities in Section 3, businesses that were genuinely cited tended to also have broader third-party representation, including:
This is our interpretation of an observed pattern, not a causal factor we directly measured or isolated in this dataset — with only 2 genuine citations in 515 businesses, this dataset is not large enough to establish causation.
Third-party citation signals are associated with a higher likelihood of AI citation presence but do not guarantee inclusion in any specific AI-generated answer. AI model outputs are probabilistic and change over time.
For full detail behind these answers, see Full Methodology → and the AEOGeoAI methodology page.
AEOGeoAI.
Miami AI Search Visibility Study 2026.
Report ID: AEOGEOAI-MIA-COMBINED-2026-001.
Version 1.0. Published July 2026.
https://aeogeoai.net/miami-ai-visibility-study
@report{aeogeoai_miami_combined_2026, title = {Miami AI Search Visibility Study 2026}, author = {{AEOGeoAI}}, year = {2026}, month = {7}, institution = {AEOGeoAI}, url = {https://aeogeoai.net/miami-ai-visibility-study}, note = {Report ID: AEOGEOAI-MIA-COMBINED-2026-001} }
| Version | Date | Changes |
|---|---|---|
| 1.0 | July 2026 | Initial publication |
We publish structured entity articles about Miami-Dade businesses — health, legal, and real estate alike — on verified local publications already indexed by AI systems, creating additional third-party entity references that may improve the likelihood of AI citation over time.
View Miami service and pricing →From $399 · One-time publication · No retainer · Miami-Dade & Broward Counties · See full AI Search Optimization pricing