Original research · 2026-07 edition

AI SEO Statistics: Pool Company (2026-07 edition)

15 questions · 45 AI responses · 3 models · measured 2026-07-04

See how AI talks about YOUR businessFull data table

The question bank

The questions we tested — sampled from real buyer journeys in pool company.

Each model answered every question once, same wording, same day. These are the prompts behind every percentage on this page.

Why is my pool losing two inches of water every day even when it's not that hot out?
Is it actually cheaper to do my own pool chemicals or should I just pay a monthly service?
What specific certifications should I look for when hiring a pool technician in my state?
How much does it typically cost to resurface an inground concrete pool that's about 15x30?
Should I convert my old chlorine pool to a saltwater system and what's the upfront cost?
When is the best time of year to schedule a pool opening to avoid the spring rush?
What are some warning signs that a pool contractor might be overcharging me for repairs?
My pool pump started making a loud screeching noise and stopped moving water, do I need an emergency repair?
Show all 15 questions
I have a $50,000 budget, can I get a decent inground pool installed or should I look at high-end above ground options?
How often should a professional pool company come out to check the equipment versus just cleaning the surface?
Is it worth upgrading to a variable speed pool pump to save on my monthly electric bill?
Do pool companies usually handle the local permits and safety fencing requirements or is that on the homeowner?
My pool turned dark green overnight after a big storm and the shock isn't working, what should I ask a pro to do?
If a pool company doesn't have a physical showroom, is that a reason to be concerned about their legitimacy?
What does a professional winterization package usually include and is it worth the cost?

Model by model

22-point average divergence: which AI you ask changes the answer.

The divergence index is the average gap between the most and least likely model per behavior. Higher = the models disagree more about pool company buyers.

Behavior rates across 15 pool company buyer questions, 2026-07 edition. Last column: average across models.
ChatGPTClaudeGeminiConsensus
Recommends hiring a professional73%53%40%40%
Suggests DIY first20%13%20%87%
Names specific providers0%0%0%100%
Gives price or cost info27%47%47%60%
Tells to check reviews20%13%0%80%
Tells to verify credentials40%20%13%73%
Mentions case studies / portfolio20%7%7%87%
Mentions local proximity27%27%13%67%
Gives selection criteria53%33%20%53%
Warns about red flags27%20%13%80%
Asks a clarifying question67%53%7%13%
Recommends multiple quotes27%13%0%73%

By model

How each assistant handled Pool Company questions.

Reading the 45 answers model by model shows how differently the three assistants treat the same pool company questions. On the most consequential behavior — whether to send the buyer to a professional at all — the rate ranged from 73.3% (ChatGPT) down to 40% (Gemini), a 33-point gap on an identical question set.

Across the 15 pool company answers it produced, ChatGPT recommended hiring a professional in 73.3% of them and suggested a DIY approach first 20% of the time. It named a specific provider in 0% of answers (about 0 distinct providers per answer) and included price or cost information 26.7% of the time. ChatGPT asked a clarifying question before answering in 66.7% of cases, warned about red flags or scams in 26.7%, and told the buyer to verify credentials in 40%, averaging 505 words per answer. On the remaining cues it told the buyer to check reviews in 20%, pointed to case studies or a portfolio in 20%, and framed the choice around local proximity in 26.7%; a selection-criteria checklist appeared in 53.3% of its answers and a recommendation to gather multiple quotes in 26.7%.

Across the 15 pool company answers it produced, Claude recommended hiring a professional in 53.3% of them and suggested a DIY approach first 13.3% of the time. It named a specific provider in 0% of answers (about 0 distinct providers per answer) and included price or cost information 46.7% of the time. Claude asked a clarifying question before answering in 53.3% of cases, warned about red flags or scams in 20%, and told the buyer to verify credentials in 20%, averaging 288 words per answer. On the remaining cues it told the buyer to check reviews in 13.3%, pointed to case studies or a portfolio in 6.7%, and framed the choice around local proximity in 26.7%; a selection-criteria checklist appeared in 33.3% of its answers and a recommendation to gather multiple quotes in 13.3%.

Across the 15 pool company answers it produced, Gemini recommended hiring a professional in 40% of them and suggested a DIY approach first 20% of the time. It named a specific provider in 0% of answers (about 0 distinct providers per answer) and included price or cost information 46.7% of the time. Gemini asked a clarifying question before answering in 6.7% of cases, warned about red flags or scams in 13.3%, and told the buyer to verify credentials in 13.3%, averaging 249 words per answer. On the remaining cues it told the buyer to check reviews in 0%, pointed to case studies or a portfolio in 6.7%, and framed the choice around local proximity in 13.3%; a selection-criteria checklist appeared in 20% of its answers and a recommendation to gather multiple quotes in 0%.

Taken together, ChatGPT is the assistant most likely to route a pool company buyer to a professional (73.3%) and Gemini the least (40%). ChatGPT produced the longest answers, at 505 words on average. No model named a specific provider in more than 0% of answers.

Where they disagree

The behaviors where the choice of model changes the answer.

The divergence index for this study is 21.5 points — the average distance between the most and least likely model across the coded behaviors. The gaps below are where which assistant a pool company buyer happens to ask matters most:

  • Asks a clarifying question: from 6.7% (Gemini) to 66.7% (ChatGPT) — a 60-point spread.
  • Recommends hiring a professional: from 40% (Gemini) to 73.3% (ChatGPT) — a 33-point spread.
  • Gives selection criteria: from 20% (Gemini) to 53.3% (ChatGPT) — a 33-point spread.
  • Tells the buyer to verify credentials: from 13.3% (Gemini) to 40% (ChatGPT) — a 27-point spread.
  • Recommends multiple quotes: from 0% (Gemini) to 26.7% (ChatGPT) — a 27-point spread.

The widest single gap — asks a clarifying question, 60 points — means a pool company buyer can receive materially different guidance on the same question depending only on which assistant they happen to open, so any visibility strategy built on a single model's behavior describes only part of the pool company market.

Where they agree

The points of near-consensus in Pool Company.

On other behaviors the three models move almost in lockstep — the points of near-consensus for pool company, where all three landed within a few points of each other:

  • Names a specific provider: 0% across all three models.
  • Suggests a DIY approach first: 13.3%–20% across all three (a 7-point spread).
  • Mentions case studies or portfolio: 6.7%–20% across all three (a 13-point spread).
  • Mentions local proximity: 13.3%–26.7% across all three (a 13-point spread).

Measured question by question, the three assistants coded a response the same way most consistently on "names a specific provider" (identical coding in 100% of questions) and least consistently on "asks a clarifying question" (13.3%).

Every behavior, measured

All twelve coded behaviors for Pool Company, averaged across the three models.

The behaviors AI models reproduce most often for pool company are recommends hiring a professional (55.5% on average), asks a clarifying question (42.2%) and gives price or cost information (40%); the rarest are names a specific provider (0%), mentions case studies or portfolio (11.1%) and tells the buyer to check reviews (11.1%). Each figure below is the share of a model's 15 answers in which the behavior appeared at least once, averaged across the 3 models with the full per-model range in parentheses:

  • Recommends hiring a professional: 55.5% on average (ChatGPT 73.3%, Claude 53.3%, Gemini 40%) — a 33-point spread.
  • Asks a clarifying question: 42.2% on average (ChatGPT 66.7%, Claude 53.3%, Gemini 6.7%) — a 60-point spread.
  • Gives price or cost information: 40% on average (ChatGPT 26.7%, Claude 46.7%, Gemini 46.7%) — a 20-point spread.
  • Gives selection criteria: 35.5% on average (ChatGPT 53.3%, Claude 33.3%, Gemini 20%) — a 33-point spread.
  • Tells the buyer to verify credentials: 24.4% on average (ChatGPT 40%, Claude 20%, Gemini 13.3%) — a 27-point spread.
  • Mentions local proximity: 22.2% on average (ChatGPT 26.7%, Claude 26.7%, Gemini 13.3%) — a 13-point spread.
  • Warns about red flags or scams: 20% on average (ChatGPT 26.7%, Claude 20%, Gemini 13.3%) — a 13-point spread.
  • Suggests a DIY approach first: 17.8% on average (ChatGPT 20%, Claude 13.3%, Gemini 20%) — a 7-point spread.
  • Recommends multiple quotes: 13.3% on average (ChatGPT 26.7%, Claude 13.3%, Gemini 0%) — a 27-point spread.
  • Tells the buyer to check reviews: 11.1% on average (ChatGPT 20%, Claude 13.3%, Gemini 0%) — a 20-point spread.
  • Mentions case studies or portfolio: 11.1% on average (ChatGPT 20%, Claude 6.7%, Gemini 6.7%) — a 13-point spread.
  • Names a specific provider: 0% on average (ChatGPT 0%, Claude 0%, Gemini 0%).

Trust signals

How well the models protect the pool company buyer.

Beyond whether to hire, the rubric codes how carefully each assistant protects the pool company buyer once a decision is made. Telling the buyer to check reviews or ratings appeared in 11.1% of answers on average. Verifying credentials or certifications appeared in 24.4%. Warning about red flags or scams appeared in 20%.

On structuring the decision, a selection-criteria checklist showed up in 35.5% of answers on average and a recommendation to gather multiple quotes in 13.3%. The single least-reproduced protective signal for pool company is "tells the buyer to check reviews" at 11.1% on average — the clearest opening for content that supplies it, since the models are not yet reliably surfacing that guidance on their own.

Referral behavior

Do AI models name Pool Company providers?

For service providers the decisive question is whether these systems name anyone at all. Across 45 pool company answers, a specific provider was named in 0% of responses on average — roughly 0 distinct providers per answer. In practice the assistants behave far more as an explanatory layer than as a referral engine for pool company: visibility comes from being the reasoning a model reproduces, not from being the named recommendation.

The question set

What these 15 Pool Company questions cover.

The 15 questions behind every percentage on this page were drawn from real pool company (home services; buyer hiring decisions for this specific service) buyer journeys. Each was put to all 3 models once, with identical wording, so the rates above describe how the assistants handled this exact pool company question set — not a general prior or a hand-picked subset. The full list is shown earlier on this page; the coded percentages are what those specific questions produced.

How to read this

A note on the numbers.

A percentage here is the share of a model's 15 answers in which the behavior appeared at least once — not a confidence score. Because each model answered every question exactly once on 2026-07-04, the figures describe this specific pool company question set and snapshot rather than a general prior. The full protocol and coding rubric are documented in the study methodology.

Methodology

A controlled snapshot, documented end to end.

15 standardized buyer questions per industry, one response per model per question (ChatGPT (gpt-5-mini), Claude (claude-sonnet-5), Gemini (gemini-3-flash-preview)), collected 2026-07-04, coded against a fixed 12-behavior rubric with human QA. AI outputs vary with model version, location and time — figures describe this sample and window, and are refreshed each edition. Read the full methodology →