How we measure who AI recommends

These rankings aren't opinions, votes, or paid placements. They are a record of what AI actually answers when we ask it — the same way a real homeowner would — who to hire.

The steps, in plain language

1. 1

   We ask the questions real homeowners ask.

   In each market we ask leading AI assistants for a solar company 4 different ways per service — everyday phrasings like "Who is the best solar company near me?", "I want to put solar panels on my house — who should I hire?", and "Who should I call to clean my solar panels?". We ask separately about two kinds of work: putting panels on a roof, and cleaning panels that are already up. No trick prompts, no leading questions. Across 30 markets and both services, that came to 204 checks for this edition.

2. 2

   We record every company it names.

   Each answer gets logged exactly as given. We then match every recommendation against the 1,043 solar companies in our dataset. Each business AI names is credited to exactly one company — and when we can't tell for certain which local company it meant, no one gets the credit. No company is ever double-counted.

3. 3

   We publish the count, not a number one.

   We tested this. Running the identical questions on the identical list a second time, the same day, changed which company came out on top in more than a third of markets — and in most markets the top spot was already shared by two to five of them. What did NOT move was the count: a company named in most checks was named in most checks again. So each service list shows how many of the 4 checks named each company. Companies with the same count are shown together, alphabetically, because the measurement does not separate them.

4. 4

   Named once doesn't make the list.

   Companies named in exactly one check reappeared less than half the time when we re-ran the same questions. That is a coin flip, not a recommendation, so we keep the data and don't publish the name. Two mentions came back 86% of the time; four came back every time. Each market page shows only the companies AI named more than once, service by service. We never publish a bottom list and never name who didn't make it.

5. 5

   National brands are left out on purpose.

   Our dataset is independent, local solar companies. The big national installers and dealer networks are filtered out before we measure, because a homeowner looking for a local company to stand behind the work in five years is not choosing between them and a national sales operation. The lists are a scoreboard for local companies.

6. 6

   We only cover solar-primed markets.

   We benchmark the markets where home solar actually pays off for a homeowner — strong sun, high power bills, or state rules that pay fairly for the power your panels send back to the grid. That is why you will find Phoenix, Newark, and Pittsburgh here and not every U.S. city.

7. 7

   We re-run it quarterly.

   The same benchmark, the same way, every quarter. Companies that improve their AI visibility can appear in the next edition — and the run date is printed on every page. This edition: July 2026.

This edition

What this is — and what it isn't

Being on this list means AI recommended that company when we asked, in that edition, in that market. It is a measurement of AI visibility — not a judgment of the quality of anyone's work, and not a claim that unlisted companies are worse at what they do. AI answers also change over time, which is exactly why we re-measure quarterly and date every edition.