Public sample · a real scan of a real market
How we grade: the band your client sits in is highlighted. Bands are read off the share of answers; the 90% intervals in the table below say how tight each share is, and never move a status by themselves.
This clientAverage of the 10 regulars: the businesses ChatGPT names most often
Share of voice is not drawn as a second line: it moves with visibility. Point at a report to read its figures.
This clientAverage of the 10 regulars: the businesses ChatGPT names most often
Point at a report to see how many of its answers showed this business as a card.
Click a metric to see every report. The shaded parts of each chart mark where OpenAI changed the engine under this market.
The rating shown beside the answer is the one on that Yelp listing: 3.4★ from 25 reviews. Whatever the Google profile says, it is not what they see here. Average card position 2.8 of 6.9 cards shown.
Every business ChatGPT named or showed a card for in report 4, sorted by visibility. Your client's row is highlighted.
| # | Business | Visibility | Share of voice | Written answer · 90% CI | Places block · 90% CI |
|---|---|---|---|---|---|
| 1 | Anderson Hills Plumbing (example client) | 83% [70-92] | 8.3% | ||
| 2 | Wake Plumbing | 83% [70-92] | 8.3% | ||
| 3 | Roto Rooter Plumbing & Water Cleanup | 80% [66-89] | 8.0% | ||
| 4 | Queen City Plumbing | 80% [66-89] | 8.0% | ||
| 5 | Ken Neyer Plumbing INC | 77% [62-87] | 7.6% | ||
| 6 | Plumb Tite Plumbing & Drains | 73% [59-84] | 7.3% | ||
| 7 | Mcguire Plumbing | 63% [48-76] | 6.3% | ||
| 8 | Herrmann Services | 60% [45-73] | 6.0% | ||
| 9 | Preston & Sons | 50% [36-64] | 5.0% | ||
| 10 | Blue Chip Plumbing | 47% [33-61] | 4.7% | ||
| 11 | Apollo Home | 37% [24-52] | 3.7% | ||
| 12 | Roberson Brothers Plumbing | 37% [24-52] | 3.7% | ||
| 13 | Schneller Knochelmann Plumbing Heating & Air Conditioning | 37% [24-52] | 3.7% | ||
| 14 | Halpin Plumbing | 20% [11-34] | 2.0% | ||
| 15 | Gardner Plumbing | 20% [11-34] | 2.0% | ||
| 16 | Trinity Plumbing and Water | 20% [11-34] | 2.0% | ||
| 17 | Narrow Path Plumbing | 17% [8-30] | 1.7% | ||
| 18 | Calla Plumbing | 13% [6-27] | 1.3% | ||
| 19 | Midwestern Plumbing | 13% [6-27] | 1.3% | ||
| 20 | Nieman Plumbing | 13% [6-27] | 1.3% | ||
| 21 | Chaney Services | 10% [4-23] | 1.0% | ||
| 22 | Jmw Plumbing & Fire Protection | 10% [4-23] | 1.0% | ||
| 23 | Tarvin Plumbing | 10% [4-23] | 1.0% | ||
| 24 | Elite Plumbing Services | 10% [4-23] | 1.0% | ||
| 25 | Safe Plumbing | 10% [4-23] | 1.0% | ||
| 26 | A Plumbing | 3% [1-14] | 0.3% | ||
| 27 | Chase Brothers Plumbing | 3% [1-14] | 0.3% | ||
| 28 | De Plumbing | 3% [1-14] | 0.3% | ||
| 29 | Hofmeyer Plumbing | 3% [1-14] | 0.3% | ||
| 30 | Jolly Heating Air Plumbing Electric | 3% [1-14] | 0.3% | ||
| 31 | Mr Rooter Plumbing of Greater Cincinnati | 3% [1-14] | 0.3% | ||
| 32 | Pembroke Plumbing | 3% [1-14] | 0.3% | ||
| 33 | Service Experts Cincinnati | 3% [1-14] | 0.3% | ||
| 34 | Knochelmann Service Experts (no Google Maps match) | 3% [1-14] | 0.3% |
Ratings and review counts exactly as the cards displayed them. Cards counts the answers that showed a card for this business.
| Business | Avg pos | ★ | Reviews | Cards | Source |
|---|---|---|---|---|---|
| Anderson Hills Plumbing (example client) | 2.8 | 3.4 | 25 | 24 | Yelp 24 |
| Roto Rooter Plumbing & Water Cleanup | 5.2 | 3.0 | 248 | 24 · 1 sl | Yelp 24 |
| Ken Neyer Plumbing INC | 3.4 | 4.0 | 33 | 22 | Yelp 22 |
| Plumb Tite Plumbing & Drains | 3.0 | 4.9 | 636 | 22 · 8 sl | Google 13 · Yelp 9 |
| Herrmann Services | 5.3 | 3.0 | 18 | 18 | Yelp 18 |
| Preston & Sons | 4.2 | 4.8 | 175 | 14 · 14 sl | Google 14 |
| Blue Chip Plumbing | 4.4 | 4.2 | 9 | 14 | Yelp 14 |
| Apollo Home | 2.8 | 1.8 | 223 | 11 · 2 sl | Yelp 11 |
| Roberson Brothers Plumbing | 4.5 | 4.8 | 185 | 11 · 17 sl | Google 11 |
| Schneller Knochelmann Plumbing Heating & Air Conditioning | 4.8 | 3.2 | 42 | 11 | Yelp 11 |
| Halpin Plumbing | 6.2 | 3.6 | 21 | 6 | Yelp 6 |
| Gardner Plumbing | 4.0 | 5.0 | 53 | 3 | Google 3 |
| Calla Plumbing | 5.8 | 4.8 | 135 | 4 · 12 sl | Google 4 |
| Midwestern Plumbing | 4.5 | 4.9 | 331 | 4 · 26 sl | Google 4 |
| Nieman Plumbing | 7.5 | 3.7 | 7 | 2 | Yelp 2 |
| Chaney Services | 5.7 | 5.0 | 221 | 3 · 26 sl | Google 3 |
| Jmw Plumbing & Fire Protection | 3.7 | 5.0 | 115 | 3 · 27 sl | Google 3 |
| Tarvin Plumbing | 5.0 | 4.3 | 50 | 3 · 1 sl | Yelp 3 |
| A Plumbing | 5.0 | 4.9 | 1075 | 1 · 29 sl | Google 1 |
| Chase Brothers Plumbing | 5.0 | 4.9 | 126 | 1 · 4 sl | Google 1 |
| De Plumbing | 3.0 | 5.0 | 36 | 1 · 6 sl | Google 1 |
| Hofmeyer Plumbing | 5.0 | 4.8 | 147 | 1 | Google 1 |
| Jolly Heating Air Plumbing Electric | 1.0 | 4.9 | 70 | 1 · 3 sl | Google 1 |
| Mr Rooter Plumbing of Greater Cincinnati | 3.0 | 1.0 | 3 | 1 | Yelp 1 |
| Pembroke Plumbing | 7.0 | 4.9 | 191 | 1 · 8 sl | Google 1 |
| Service Experts Cincinnati | 3.0 | 2.6 | 63 | 1 | Yelp 1 |
| Copper Pipe Plumbing Services INC | 4.9 | 140 | 5 sl | – | |
| Dixon Plumbing & Service | 5.0 | 412 | 25 sl | – | |
| Kings Plumbing | 4.9 | 35 | 6 sl | – | |
| Nobles Plumbing and Drain Cleaning Services LLC | 5.0 | 69 | 3 sl | – | |
| Salt Dog Plumbing LLC | 5.0 | 153 | 22 sl | – | |
| Tj's Plumbing Installation and Repair | 4.9 | 126 | 4 sl | – |
Every business ChatGPT built a card for in this report, at the coordinates ChatGPT itself sent with the card. Dot size = how many of the 30 answers named it.
Pins are plotted from the coordinates ChatGPT returned in its own answers, not from a directory lookup. Street layer: Protomaps, OpenStreetMap data, served from this domain.
Sites ChatGPT read before answering, by how many of the 30 answers cited them.
| Domain | Answers citing | Share |
|---|---|---|
| angi.com | 18 | 60% |
| homeadvisor.com | 18 | 60% |
| birdeye.com | 18 | 60% |
| yahoo.com | 17 | 57% |
| bestpickreports.com | 16 | 53% |
| consumeraffairs.com | 8 | 27% |
| serviceagent.ai | 7 | 23% |
| expertise.com | 7 | 23% |
| bestprosintown.com | 5 | 17% |
| seolium.com | 5 | 17% |
| recommended.app | 4 | 13% |
| threebestrated.com | 4 | 13% |
The searches ChatGPT actually fired before answering, with how many of the 30 answers fired each one.
| What an answer looks like | A Yelp or Google listing builds most of the cards in this market, but they are not the only sources: other directories, and pages from the answer's own web search, build cards too. Whichever listing built a card is where its rating and review count come from. |
|---|---|
| Where we asked | The real ChatGPT web app, asked the way a customer in your city would ask it, as a signed out visitor. Not a developer API. |
| How many times | 30 independent answers, spread across natural phrasings a real customer would use. A single answer proves nothing, because the model gives a different one every time. |
| What counts as a mention | Each answer is read on 2 surfaces: the written text and the places carousel, the block of business cards ChatGPT shows beside its answer. An answer counts once if either happened. |
| How your status is set | From the share of the 30 answers, against the five bands above. The 90% intervals say how tight that share is and never move a status by themselves. |
| Share of voice | The client's mentions divided by all business mentions in the same scan, counted once per answer per business. 25 of 301 here. |
| How businesses are matched | By map listing id, never by name text, so a business with a similar name in another town cannot be counted as this one. |
| Out of area | Of the 207 map card mentions whose coordinates ChatGPT gave us, 0 (0%) are businesses more than 62 miles from the center of this market; those rows are tagged with the distance. This is noise in the model's own answers, not a measurement error. |
| What the charts compare against | The 10 businesses ChatGPT names most often in this market, not every name it happened to mention. A market carries a long tail of names that come up once or twice, and averaging those in would flatter every business measured against them. The 10 are recomputed for every report, and a chain counts once, exactly as it does in the table above. |
| Measurement environment | Engine
gpt-5-6 in all 30 answers, map block present in
30 of 30, 6.9 cards per answer, 10.0
businesses named per answer. |
| What the chat window does not show | Every one of these 30 answers was also read underneath the text: which directory built each card, which cards ChatGPT prepared and then held back (the shortlist), and what position each card sat at. Reading the answers by eye gives you the names and nothing else, which is why this view exists. |
| What this does not tell you | Not how many people asked, and not what any one person saw. ChatGPT varies its answers by design and adapts to a person's own history, so these figures describe how often a business comes up for a stranger asking fresh, which is the only thing that can be measured the same way twice. |