Skip to content

The AI Recommendation Gap 2026 Method

How the AI Recommendation Gap was measured

Fieldwork 20 October 2026 (Sweden, the UK and the US) and 28 October 2026 (the UAE). Alfred sells services in this area. Alfred’s own products and prices are not part of any comparison in the study.

Design

The study asks one question the way a customer asks it: who are the best plumbers, electricians, painters, roofers or builders in this city? It puts the question to ChatGPT and Perplexity, records every business they name and every source they cite, and sets each pick beside the three businesses Google shows in its map results for the same search, and beside every local listing of the trade.

A cell is one trade in one city. There are 65: five trades in each of three cities in the United Kingdom, the United States and the United Arab Emirates, and in four Swedish cities for comparison. Plumbers, electricians and painters are the three trades every city shares; the other two differ by market. The first run, 50 cells in Sweden, the UK and the US, took one night, 20 October 2026: 32,731 category-listings, 110 AI answers and 648 first-run picks. The UAE run, 15 cells on 28 October 2026, used the same pipeline, metrics and matching rule: 3,124 category-listings, 33 answers and 172 first-run picks.

MarketFieldworkCellsCategory-listingsAI answersFirst-run picks
United Kingdom20 October 20261518,49533186
United States20 October 20261510,34833203
Sweden20 October 2026203,88844259
United Arab Emirates28 October 2026153,12433172

Each market has its own page with its cities, searches, prompts and cells: United Kingdom , United States , United Arab Emirates . The nine consumer industries measured on 28 October 2026 have a method page of their own: Local search by industry 2026.

CityMarketCentreRadiusLocation for the Google results
LondonUK51.5074, −0.127820 kmLondon, England, United Kingdom
ManchesterUK53.4808, −2.242615 kmManchester, England, United Kingdom
BirminghamUK52.4862, −1.890415 kmBirmingham, England, United Kingdom
HoustonUS29.7604, −95.369825 kmHouston, Texas, United States
ChicagoUS41.8781, −87.629820 kmChicago, Illinois, United States
PhoenixUS33.4484, −112.074025 kmPhoenix, Arizona, United States
DubaiUAE25.2048, 55.270820 kmDubai, Dubai, United Arab Emirates
Abu DhabiUAE24.4539, 54.377320 kmAbu Dhabi, Abu Dhabi, United Arab Emirates
SharjahUAE25.3463, 55.420912 kmSharjah, Sharjah, United Arab Emirates
StockholmSweden59.3293, 18.068620 kmStockholm, Stockholm County, Sweden
GöteborgSweden57.7089, 11.974615 kmGothenburg, Vastra Gotaland County, Sweden
MalmöSweden55.6050, 13.003812 kmMalmo, Skane County, Sweden
UppsalaSweden59.8586, 17.638910 kmUppsala, Uppsala County, Sweden

The radius follows the size of the city, so the number of listings differs between cities while the shares need not.

Trades, categories and searches

Each trade is defined by one Google category. A listing counts when the category is its primary category or one of its additional ones, so a firm with two trades counts once in each. The Google search is the query below followed by the city’s name; the AI question uses the noun below.

MarketTradeGoogle categoryGoogle searchNoun in the AI question
UKPlumbersplumberplumberplumbers
UKElectricianselectricianelectricianelectricians
UKPainters and decoratorspainterpainter and decoratorpainters and decorators
UKRoofersroofing_contractorrooferroofers
UKBuildersgeneral_contractorbuilderbuilders
USPlumbersplumberplumberplumbers
USElectricianselectricianelectricianelectricians
USHouse painterspainterhouse painterhouse painting companies
USRoofersroofing_contractorrooferroofing companies
USHVAC contractorshvac_contractorhvac companyHVAC companies
UAEPlumbersplumberplumberplumbers
UAEElectricianselectricianelectricianelectricians
UAEPainterspainterpainterpainting companies
UAEAC repairair_conditioning_repair_serviceac repairAC repair companies
UAEHandymenhandymanhandymanhandyman services
SwedenPlumbersplumberrörmokarerörmokarna
SwedenElectricianselectricianelektrikerelektrikerna
SwedenPainterspaintermålaremålerifirmorna
SwedenRoofersroofing_contractortakläggaretakläggarna
SwedenBuildersconstruction_companybyggfirmabyggfirmorna

Builder figures are not like for like across markets. The UK builder cells use general_contractor, because builder returned 306 listings in London against 1,030 for general_contractor; Sweden uses construction_company. The US replaces builders with HVAC companies, and the UAE replaces roofers and builders with AC repair and handymen. Comparisons across markets therefore use the three shared trades.

Listing counts

Listing data came from a business listings search, one count per measure and cell. The measures were all listings with the category in the circle, unclaimed listings, listings that link to a website, and listings with at least 1, 10 and 100 Google reviews. The Swedish cells also counted photos and ratings, which the Swedish index uses.

The counts are category-listings, not distinct firms: a firm listed in two trades counts once in each, and closed listings are included. The Basics Score is the mean of three shares, with every trade pooled per city: listings that are claimed, that link to a website and that have at least ten Google reviews.

Google results and the top three

For each cell, Google’s organic search was asked for the trade’s query and the city, at city level, on desktop, ten results deep. Each search recorded whether an AI Overview appeared, the businesses in the map results with their rating and review count, the “People also ask” questions and the domains of the organic top ten. The “top three” means places 1–3 of the map results. In two Malmö cells Google showed six map entries in two blocks; only places 1–3 count. UAE searches returned seven to nine organic results each. AI Overviews load separately, so whether one appeared was recorded and its text was not.

The AI answers

  • UK: “Who are the best {plumbers | electricians | painters and decorators | roofers | builders} in {city}?”
  • US: “Who are the best {plumbers | electricians | house painting companies | roofing companies | HVAC companies} in {city}?”
  • UAE: “Who are the best {plumbers | electricians | painting companies | AC repair companies | handyman services} in {city}?”
  • Sweden: «Vilka är de bästa {rörmokarna | elektrikerna | målerifirmorna | takläggarna | byggfirmorna} i {stad}?»
  • ChatGPT: collected from ChatGPT’s consumer interface, logged out, location set to the country, language English (Swedish in Sweden). The answer carries named businesses with the rating and review count it shows, and its sources. The model is not always reported.
  • Perplexity: the sonar-pro model through its API, with web search on. The API takes no location.
  • Gemini: returned no answers and is not part of any figure.

Each cell had one ChatGPT answer and one Perplexity answer. The plumber question was put to ChatGPT a second time in each city, the re-run. Every named business was recorded, up to ten per answer, with the rating and review count shown and every cited link. Approximate figures such as “500+” were recorded as their lower bound.

In Birmingham, Perplexity answered for Birmingham, Alabama first in three of five cells. US firms named in Birmingham answers were taken out of the picks, and UK picks keep their position in the answer, so places above ten occur.

Matching rule

To compare an AI pick with Google’s top three, both names are normalised: lower case, accents and punctuation removed, legal forms such as Ltd, LLC and Inc dropped. The city’s name is removed only when it is a whole word at the start or end and a distinctive word remains. Two names are the same business when their token-set similarity is at least 85 and they share at least one distinctive word, never only words such as “Plumbing”, “Electrical” or a place name. A name with no distinctive word matches only an identical name.

For the UAE the vocabulary of generic words was extended with UAE legal forms, the Arabic article “al”, UAE place names and trade words such as “technical”, “general”, “contracting” and “maintenance”. Names written only in Arabic script are matched on their Arabic words. One Dubai match, a business written three ways, was set by hand on matching evidence (the same phone number and the same 4.9 rating from 218 reviews), and three spelling variants were merged.

Google figures for picks

A pick’s Google rating and review count come from the top three, from a lookup by name (up to three per cell, chosen selectively) or from Google panels noted during fieldwork. “Best available” means the Google figure where it was verified and the figure the answer showed otherwise. A figure shown in an answer “matches” Google when it is within 10% or five reviews.

How cited sources are classed

Every cited domain was classed as a directory, a review platform, a marketplace, a “best of” list, the business’s own website, Google Maps, social media or other. A cited site “does not rank on Google” when its domain was not in the organic top ten for the same search in the same city. That measure covers the aggregator domains (directories, review platforms, marketplaces and lists) and leaves out business sites and Google itself.

Limits

  • One question per assistant and cell, plus one re-run per city. Answers change between runs, so the results describe patterns, not any single business’s place.
  • ChatGPT was read logged out through a collection service and Perplexity through its API without a location; real users may see something else.
  • Lookups were selective and by name. Verified Google figures exist for 44 UK, 99 US and 82 Swedish picks, and for 16 ChatGPT and 35 Perplexity picks in the UAE.
  • Listing counts double-count firms in several categories, include closed listings and use radii that differ by city.
  • The UAE universes are small (Abu Dhabi has 61 plumbers and Sharjah 27 handymen), and its trade mix differs, so like-for-like comparisons use the three shared trades.
  • AI Overview text was not captured. Gemini is not included.
  • Two snapshots, taken on 20 and 28 October 2026. Results and profiles change all the time.

Data about individual businesses is not released, and a business named in the study appears only in a neutral or positive context.

How to cite this method

Alfred, The AI Recommendation Gap 2026: method, October 2026, https://tryalfred.ai/reports/ai-recommendation-gap/method

Quote the figures with credit to Alfred and a link to this page. Data about individual businesses is not released.

The same measures, for your business

Check my business reads your own listing and the map from 49 points, and measures each line against a fixed target.