Named, Not Booked: What ChatGPT and Gemini Actually Do When Homeowners Ask for a Local Service Company — 5,788 Paired Answers Across 20 Southeast US Metros (October 2026)

When a homeowner asks an AI assistant to recommend — or book — a local home-service company, what happens next? We asked ChatGPT and Gemini the same 12 homeowner-style questions for each of 12 home-service trades in 20 Southeast US metros, capturing 5,788 AI answers in October 2026. The assistants almost always name companies (99% of answers), but the two platforms named the identical #1 company in only 10.3% of paired questions. Being named rarely leads anywhere bookable: 79.1% of answers contained no booking path and no connector mention of any kind, and the connectors that were mentioned were overwhelmingly directories and marketplaces (Angi, HomeAdvisor, Yelp, Thumbtack) rather than the operator's own scheduling system — an operator's own scheduling platform (Housecall Pro, Jobber class) was named in just 4 of 5,788 answers. AI assistants have become a recommendation surface for local services; they are not yet a booking surface. The deposit includes the paper and a CSV of metro × trade × platform aggregates computed from the full dataset.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-10-28
DOI
https://doi.org/10.5281/zenodo.23745741
Primary Topic
AI in Service Interactions
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Named, Not Booked: What ChatGPT and Gemini Actually Do When Homeowners Ask for a Local Service Company — 5,788 Paired Answers Across 20 Southeast US Metros (October 2026)

Copp Oak Advisors
2 links
Zenodo (CERN European Organization for Nuclear Research)
AI in Service Interactions
article

Named, Not Booked: What ChatGPT and Gemini Actually Do When Homeowners Ask for a Local Service Company — 5,788 Paired Answers Across 20 Southeast US Metros (October 2026)

Copp Oak Advisors
article en

Abstract

When a homeowner asks an AI assistant to recommend — or book — a local home-service company, what happens next? We asked ChatGPT and Gemini the same 12 homeowner-style questions for each of 12 home-service trades in 20 Southeast US metros, capturing 5,788 AI answers in October 2026. The assistants almost always name companies (99% of answers), but the two platforms named the identical #1 company in only 10.3% of paired questions. Being named rarely leads anywhere bookable: 79.1% of answers contained no booking path and no connector mention of any kind, and the connectors that were mentioned were overwhelmingly directories and marketplaces (Angi, HomeAdvisor, Yelp, Thumbtack) rather than the operator's own scheduling system — an operator's own scheduling platform (Housecall Pro, Jobber class) was named in just 4 of 5,788 answers. AI assistants have become a recommendation surface for local services; they are not yet a booking surface. The deposit includes the paper and a CSV of metro × trade × platform aggregates computed from the full dataset.

Zenodo (CERN European Organization for Nuclear Research)
Openalex Percentile: Top 13%
AI in Service Interactions
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon