Research
Original research on who AI recommends in real estate.
Each report states the market, the provider, the question set, the repetitions, the sample size and what the data cannot prove.
Research library
- Proprietary benchmarkPublished
ChatGPT Real Estate Visibility Benchmark
The primary citable dataset: how often ChatGPT (OpenAI) recommends real estate teams across repeated captured answers, with the prompt taxonomy, share definitions, exclusion rules and source-class taxonomy published in full.
- Market
- Greenville, SC and Jersey City, NJ · residential (both anonymized)
- Provider
- ChatGPT (OpenAI)
- Prompts
- 64 buyer and seller questions per market
- Repetitions
- 4 per question
- Sample size
- 256 valid captured answers per market edition
- Published
- September 2026
- Last updated
- September 2026
- Market benchmarkPublished
Jersey City AI Visibility Report
A single-market benchmark comparing verified production against how often each team was recommended across repeated captured answers, with the cited sources behind those answers.
- Market
- Jersey City, NJ · residential
- Provider
- ChatGPT (OpenAI)
- Prompts
- 64 buyer and seller questions
- Repetitions
- 4 per question
- Sample size
- 256 answers maximum
- Published
- September 2026
- Last updated
- September 2026
- Recurring benchmarkIn progress
Real Estate AI Visibility Index
A recurring cross-market benchmark of how often AI recommends real estate teams, and how those recommendations compare with verified production.
- Market
- Multiple US markets (in progress)
- Provider
- ChatGPT (OpenAI)
- Prompts
- Fixed buyer and seller question set per market
- Repetitions
- 4 per question
- Sample size
- Published per market edition
- Published
- First edition pending
- Last updated
- September 2026
- Source analysisPublished
AI Citation Sources in Real Estate
Which classes of sources appear most often around AI recommendations in a measured real estate market — reported as observed association, not causal proof.
- Market
- Jersey City, NJ · residential
- Provider
- ChatGPT (OpenAI)
- Prompts
- 64 buyer and seller questions
- Repetitions
- 4 per question
- Sample size
- 256 answers maximum
- Published
- September 2026
- Last updated
- September 2026
- ReferencePublished
Real Estate AI Search Statistics
Third-party statistics on AI use in the homebuying journey, each attributed to its original publisher with what was actually measured.
- Market
- United States
- Provider
- Third-party publishers (not our measurement)
- Prompts
- Not applicable
- Repetitions
- Not applicable
- Sample size
- Stated per statistic where published
- Published
- September 2026
- Last updated
- September 2026
Additional reports will be published as new benchmarks are completed. We do not publish findings that cannot be traced to preserved evidence.
What every data asset must state
- Produced by
- Recommended First · Francisco Zuluaga
- Captured
- Date and provider recorded with every answer
- Tested
- Fixed question set, locked for the measurement window
- Classified
- Recommended · mentioned · absent, per answer
- Cannot prove
- Causation, future answers, or private ranking behavior
Reports are versioned against the published methodology. When the method changes, the report says which version produced the numbers so historical comparisons stay honest.
Keep reading
See who AI recommends in your market — and where you stand.
One client per market. Start by telling me where you work.