Original research · 2026-07 edition

AI SEO Statistics: Pool Service (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 service.

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

Why is my pool water cloudy even though the chlorine levels are fine?
Is it worth paying a pool service or can I just do the chemicals myself to save money?
What specific certifications or insurance should I ask a pool cleaning company for before hiring them?
How much does a weekly pool maintenance service typically cost for a 15,000-gallon inground pool?
What’s the difference between a full-service pool plan and a chemicals-only service?
How do I find a pool technician who specializes in saltwater systems in my area?
What are some warning signs that my pool guy isn't actually balancing the water correctly?
My pool pump started making a loud grinding noise and stopped pushing water, who do I call for an emergency repair?
Show all 15 questions
I just bought a house with a neglected pool that's turned green; what's a realistic budget to get it swimmable again?
Do pool service companies usually handle filter cleanings, or is that an extra charge I need to look out for?
When is the best time of year to schedule a pool opening, and how far in advance should I book?
I'm thinking about switching to a robotic cleaner; will a pool service still come out to check my chemistry?
Are the chemicals used by professional pool services safe for dogs and small children to swim in right after treatment?
Should I expect to sign a year-long contract with a pool maintenance company, or is month-to-month standard?
Why is my pool losing two inches of water a day and how can a pro tell if it's a leak or just evaporation?

Model by model

23-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 service buyers.

Behavior rates across 15 pool service buyer questions, 2026-07 edition. Last column: average across models.
ChatGPTClaudeGeminiConsensus
Recommends hiring a professional80%73%40%40%
Suggests DIY first27%27%20%80%
Names specific providers0%0%7%93%
Gives price or cost info20%20%27%73%
Tells to check reviews27%13%0%67%
Tells to verify credentials20%13%7%80%
Mentions case studies / portfolio0%7%0%93%
Mentions local proximity47%40%7%53%
Gives selection criteria47%53%7%40%
Warns about red flags7%13%13%80%
Asks a clarifying question60%60%0%20%
Recommends multiple quotes20%13%0%73%

By model

How each assistant handled Pool Service questions.

Reading the 45 answers model by model shows how differently the three assistants treat the same pool service questions. On the most consequential behavior — whether to send the buyer to a professional at all — the rate ranged from 80% (ChatGPT) down to 40% (Gemini), a 40-point gap on an identical question set.

Across the 15 pool service answers it produced, ChatGPT recommended hiring a professional in 80% of them and suggested a DIY approach first 26.7% of the time. It named a specific provider in 0% of answers (about 0 distinct providers per answer) and included price or cost information 20% of the time. ChatGPT asked a clarifying question before answering in 60% of cases, warned about red flags or scams in 6.7%, and told the buyer to verify credentials in 20%, averaging 468 words per answer. On the remaining cues it told the buyer to check reviews in 26.7%, pointed to case studies or a portfolio in 0%, and framed the choice around local proximity in 46.7%; a selection-criteria checklist appeared in 46.7% of its answers and a recommendation to gather multiple quotes in 20%.

Across the 15 pool service answers it produced, Claude recommended hiring a professional in 73.3% of them and suggested a DIY approach first 26.7% of the time. It named a specific provider in 0% of answers (about 0 distinct providers per answer) and included price or cost information 20% of the time. Claude asked a clarifying question before answering in 60% of cases, warned about red flags or scams in 13.3%, and told the buyer to verify credentials in 13.3%, averaging 268 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 40%; a selection-criteria checklist appeared in 53.3% of its answers and a recommendation to gather multiple quotes in 13.3%.

Across the 15 pool service 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 6.7% of answers (about 0 distinct providers per answer) and included price or cost information 26.7% of the time. Gemini asked a clarifying question before answering in 0% of cases, warned about red flags or scams in 13.3%, and told the buyer to verify credentials in 6.7%, averaging 272 words per answer. On the remaining cues it told the buyer to check reviews in 0%, pointed to case studies or a portfolio in 0%, and framed the choice around local proximity in 6.7%; a selection-criteria checklist appeared in 6.7% of its answers and a recommendation to gather multiple quotes in 0%.

Taken together, ChatGPT is the assistant most likely to route a pool service buyer to a professional (80%) and Gemini the least (40%). ChatGPT produced the longest answers, at 468 words on average. Specific providers were named most often by Gemini (6.7%) — even there, roughly one answer in 15 carried a name.

Where they disagree

The behaviors where the choice of model changes the answer.

The divergence index for this study is 22.6 points — the average distance between the most and least likely model across the coded behaviors. The gaps below are where which assistant a pool service buyer happens to ask matters most:

  • Asks a clarifying question: from 0% (Gemini) to 60% (ChatGPT) — a 60-point spread.
  • Gives selection criteria: from 6.7% (Gemini) to 53.3% (Claude) — a 47-point spread.
  • Recommends hiring a professional: from 40% (Gemini) to 80% (ChatGPT) — a 40-point spread.
  • Mentions local proximity: from 6.7% (Gemini) to 46.7% (ChatGPT) — a 40-point spread.
  • Tells the buyer to check reviews: from 0% (Gemini) to 26.7% (ChatGPT) — a 27-point spread.

The widest single gap — asks a clarifying question, 60 points — means a pool service 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 service market.

Where they agree

The points of near-consensus in Pool Service.

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

  • Warns about red flags or scams: 6.7%–13.3% across all three (a 7-point spread).
  • Suggests a DIY approach first: 20%–26.7% across all three (a 7-point spread).
  • Names a specific provider: 0%–6.7% across all three (a 7-point spread).
  • Gives price or cost information: 20%–26.7% across all three (a 7-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 93.3% of questions) and least consistently on "asks a clarifying question" (20%).

Every behavior, measured

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

The behaviors AI models reproduce most often for pool service are recommends hiring a professional (64.4% on average), asks a clarifying question (40%) and gives selection criteria (35.6%); the rarest are mentions case studies or portfolio (2.2%), names a specific provider (2.2%) and recommends multiple quotes (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: 64.4% on average (ChatGPT 80%, Claude 73.3%, Gemini 40%) — a 40-point spread.
  • Asks a clarifying question: 40% on average (ChatGPT 60%, Claude 60%, Gemini 0%) — a 60-point spread.
  • Gives selection criteria: 35.6% on average (ChatGPT 46.7%, Claude 53.3%, Gemini 6.7%) — a 47-point spread.
  • Mentions local proximity: 31.1% on average (ChatGPT 46.7%, Claude 40%, Gemini 6.7%) — a 40-point spread.
  • Suggests a DIY approach first: 24.5% on average (ChatGPT 26.7%, Claude 26.7%, Gemini 20%) — a 7-point spread.
  • Gives price or cost information: 22.2% on average (ChatGPT 20%, Claude 20%, Gemini 26.7%) — a 7-point spread.
  • Tells the buyer to check reviews: 13.3% on average (ChatGPT 26.7%, Claude 13.3%, Gemini 0%) — a 27-point spread.
  • Tells the buyer to verify credentials: 13.3% on average (ChatGPT 20%, Claude 13.3%, Gemini 6.7%) — a 13-point spread.
  • Warns about red flags or scams: 11.1% on average (ChatGPT 6.7%, Claude 13.3%, Gemini 13.3%) — a 7-point spread.
  • Recommends multiple quotes: 11.1% on average (ChatGPT 20%, Claude 13.3%, Gemini 0%) — a 20-point spread.
  • Names a specific provider: 2.2% on average (ChatGPT 0%, Claude 0%, Gemini 6.7%) — a 7-point spread.
  • Mentions case studies or portfolio: 2.2% on average (ChatGPT 0%, Claude 6.7%, Gemini 0%) — a 7-point spread.

Trust signals

How well the models protect the pool service buyer.

Beyond whether to hire, the rubric codes how carefully each assistant protects the pool service buyer once a decision is made. Telling the buyer to check reviews or ratings appeared in 13.3% of answers on average. Verifying credentials or certifications appeared in 13.3%. Warning about red flags or scams appeared in 11.1%.

On structuring the decision, a selection-criteria checklist showed up in 35.6% of answers on average and a recommendation to gather multiple quotes in 11.1%. The single least-reproduced protective signal for pool service is "warns about red flags or scams" 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 Service providers?

For service providers the decisive question is whether these systems name anyone at all. Across 45 pool service answers, a specific provider was named in 2.2% 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 service: visibility comes from being the reasoning a model reproduces, not from being the named recommendation.

The question set

What these 15 Pool Service questions cover.

The 15 questions behind every percentage on this page were drawn from real pool service (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 service 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 service 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 →