Resolution Layer Case Study · Read & Diagnose
A Luxury Franchise Dealer Group
A cross-rooftop new-vehicle catalog analysis — 7 stores, 2 brands, one platform, zero manual setup
Before the findings
What's actually riding on seven rooftops' worth of vehicle data.
About this case study. This is an anonymized version of a client deliverable. The dealer group, its rooftops, its locations and its history have been removed; every finding, severity, count and field name is reproduced exactly as it appeared in the original analysis, and data values are quoted verbatim except where a value would identify the group, in which case it is described instead. Rooftops are labeled by number and franchise brand only.
This group's growth story looks nothing like the one-rooftop-at-a-time model most of the industry runs on. It has grown quickly, adding already-successful luxury stores rather than building each one from scratch. That speed is the asset. What this analysis examines is whether the catalog infrastructure inherited across seven of those rooftops is keeping pace with it.
Every rooftop feeds the same handful of channels that decide whether a shopper ever sees a given vehicle: the dealership's own site, the big three marketplaces — Autotrader, Cars.com, CarGurus — Mercedes-Benz's own certified-dealer and digital retail tools, and, increasingly, a channel most dealer teams haven't built for at all.
"By bringing CarMax's nationwide inventory and shopping tools into ChatGPT, we're giving customers a simple, reliable way to explore their options within a platform they are already using."
Diane Cafritz, Chief Innovation & People Officer, CarMax — press release, Feb. 27, 2026
We ran seven of the group's rooftops — six Mercedes-Benz stores and one Infiniti, all sourced through the same dealer-website platform — through EKOM's analysis pipeline exactly as we would a new customer's catalog. No hand-built schema, no per-store configuration, no one telling the system what to look for. What came back wasn't seven stores' worth of unrelated mistakes. It was the same handful of defect classes, surfacing independently, store after store.
At a glance
A machine-surfaced triage signal, not a verified defect list — the vast majority are real; a small share may reflect intentional dealer choices. Every item below is worth a human look.
What recurred everywhere
All 7 rooftops · both brands
Vehicle photos and options data missing catalog-wide
Every one of the seven rooftops we ran — six Mercedes-Benz stores and one Infiniti store — has some or all vehicles with a completely blank image_urls field. On a luxury catalog, a listing with no photo isn't a data nit — it's a vehicle no one clicks.
3 Mercedes-Benz rooftops · ~35 vehicles
GLE Coupe models categorized as SUVs
Stores 1, 4, and 7 each independently classify GLE Coupe body_style as "SUVs" instead of "Coupe" — the exact model each store's own dealer description identifies correctly. A shopper filtering for Coupe never sees them.
2 rooftops, independently
A G 63 AMG®'s engine field reads "Electric Motor"
Both Store 1 and Store 4 — two Mercedes-Benz rooftops — list a 2027 G 63 AMG®'s engine as "Electric Motor." It's a twin-turbocharged V8 — and two unrelated rooftops made the identical, specific mistake without any connection to each other.
5 of 6 Mercedes-Benz rooftops
AWD models invisible to AWD filters
Stores 1, 2, 3, 5, and 7 all carry vehicles tagged "4MATIC®" instead of the catalog-standard "AWD 4MATIC®" — the same drivetrain, formatted two different ways, splitting AWD shoppers away from AWD inventory.
4 rooftops
Identical powertrains labeled two different ways
GLC 300 and GLE 350 vehicles with the same 2.0L I4 mild-hybrid engine are labeled "Hybrid" at some stores and "Gasoline" at others — occasionally within the same rooftop's own catalog. A shopper filtering for either fuel type gets an incomplete result.
Store 6 · Infiniti · 15 vehicles
Drivetrain terminology breaks from the rest of the group
Eleven QX80s list drivetrain as "2WD" instead of "RWD," and fifteen 4WD QX80s carry an "AWD" tag in their features list — the same category of drivetrain-labeling defect found at the group's Mercedes-Benz stores, showing up independently at its one non-MB rooftop too.
By rooftop
Seven independent runs, no cross-talk between them — the pattern above emerged without any store informing another.
| Rooftop | Brand | Platform | Findings | Fixes Proposed | High-Sev. |
| Store 1 | Mercedes-Benz | Platform A | 73 | 122 | 67 |
| Store 2 | Mercedes-Benz | Platform A | 19 | 88 | 19 |
| Store 3 | Mercedes-Benz | Platform A | 17 | 19 | 15 |
| Store 4 | Mercedes-Benz | Platform A | 17 | 15 | 16 |
| Store 5 | Mercedes-Benz | Platform A | 15 | 32 | 14 |
| Store 6 | Infiniti | Platform A | 14 | 75 | 11 |
| Store 7 | Mercedes-Benz | Platform A | 13 | 28 | 12 |
| Total | 2 brands | 1 platform | 168 | 379 | 154 |
A focused pass
A handful of findings are worth pulling out on their own — not because they're the most common, but because of what they reveal about how the data actually broke.
Critical · Store 4 · Mercedes-Benz
A Sprinter Passenger Van carries an MSRP of $119,500 — roughly $32,000 above its own dealer price, a gap 15 times larger than anywhere else in the catalog. Whether it's a feed error or a live pricing conflict, it needs eyes today.
Critical · Store 2 · Mercedes-Benz
A Certified Pre-Owned vehicle is sitting inside the new-inventory feed — misrepresenting its condition to shoppers and to every marketplace and OEM tool that trusts that feed as a promise of "new."
High · Store 1 · Mercedes-Benz
A one-letter misspelling of "towing" in a standard capability phrase appears across many vehicle descriptions — a small typo, repeated at scale, on the brand's own customer-facing copy.
Note on scope. Findings above the fold reflect the full run across all seven rooftops. The complete list — 168 findings — is summarized by theme on the next page.
Findings by theme
Every finding maps to one of six recurring defect classes across the seven rooftops.
| Finding | Sev. | Who feels it | Rooftops |
| Drivetrain & AWD Formatting |
| "4MATIC®" vs. catalog-standard "AWD 4MATIC®" split | HIGH | Shoppers · Marketplaces | 5 of 6 Mercedes-Benz rooftops |
| QX80 drivetrain "2WD" vs. "RWD," AWD tag on 4WD units | CRIT | Shoppers | Store 6 · Infiniti |
| Body Style & Classification |
| GLE Coupe classified as "SUVs" | CRIT | Shoppers | Stores 1, 4, 7 |
| Plural "SUVs" vs. singular convention | MED | Ops | Stores 6, 7 |
| Fuel Type & Powertrain |
| G 63 AMG® engine field reads "Electric Motor" | CRIT | Shoppers · Trust | Stores 1, 4 |
| Hybrid vs. Gasoline label conflicts on identical powertrain | HIGH | Shoppers | Stores 1, 2, 4, 7 |
| Engine field carries 5–6 inconsistent formats per catalog | HIGH | Ops | All 7 rooftops |
| Pricing & MSRP |
| Missing or blank MSRP / dealer price | CRIT | Shoppers · Commerce | Stores 1, 2, 3, 5, 7 |
| MSRP / dealer-price gap outlier ($32K, Sprinter) | CRIT | Finance | Store 4 |
| MSRP underpriced vs. comparables (~$8K) | CRIT | Finance | Store 5 |
| Imagery & Content |
| image_urls / features_raw blank | CRIT | Shoppers | All 7 rooftops |
| Boilerplate-only or truncated dealer descriptions | HIGH | Shoppers · SEO | Stores 1, 3, 7 |
| Certified Pre-Owned vehicle in new-inventory feed | CRIT | Compliance | Store 2 |
| Repeated typo / corrupted text in descriptions | HIGH | Shoppers · Brand | Stores 1, 7 |
| Vehicle Identity (Stock Numbers) |
| Stock numbers don't match VIN, or break format convention | HIGH | Ops · DMS | Stores 1, 2, 4, 5, 7 |
| Structural |
| engine / interior_color / dealer_description / features_raw combine multiple data types | HIGH | Ops · Engineering | All 7 rooftops |
Catalog structure
What's solid across all seven rooftops, and where the schema itself is working against the data.
Strong coverage
- VIN 100%
- Make / Model / Year 100%
- Body Style ~99%
- Trim ~97%
Structural gaps
- image_urls blank at all 7
- features_raw blank at most rooftops
- condition absent — let a CPO unit into the new feed
- fuel_type two parallel vocabularies
Compound-split candidates (flagged across the 7 rooftops)
| Field | What it's carrying | Rooftops affected |
| engine | Displacement, cylinder count, turbo designation, and fuel qualifier concatenated inconsistently | 5 of 7 |
| interior_color | Color name + seat material combined in one free-text string, with inconsistent casing | 5 of 7 |
| features_raw | A flat, unparsed feature list — no structured package or option data | 4 of 7 |
| dealer_description | Marketing copy, MPG figures, and disclaimers concatenated with no field-level separation | 3 of 7 |
Note. These are flagged as split candidates, not pre-transformed — the underlying values are intentionally left packed so the recommendation stays visible rather than silently applied.
What this means
nearly
30%
of vehicle shoppers now use a generative AI tool like ChatGPT to research their next car — and among AI-assisted shoppers, ChatGPT alone accounts for more usage than every other AI tool combined. The group's inventory feed is either structured for that channel, or it isn't.
Ekho, 2026 AI Vehicle Research Study
The group's growth has been fast and deliberate, anchored by high-volume luxury franchises. Two AMG G 63 listings that independently name the engine "Electric Motor," at two rooftops whose data teams have never spoken to each other, aren't a coincidence. They're a signal that the same class of defect is being re-created at rooftop after rooftop, faster than any one store can catch it.
The exposure is concrete. A GLE Coupe that reads as an SUV in body_style is invisible to the shopper specifically searching for a Coupe — on some of the group's highest-margin AMG trims. A Sprinter listed $32,000 above its own dealer price is either a lost sale or a live pricing conflict. Blank photos on a luxury vehicle detail page make a worse first impression than no listing at all.
The Certified Pre-Owned vehicle sitting in Store 2's new-inventory feed is worth flagging on its own — not a formatting inconsistency, but a condition disclosure, in a feed that shoppers and marketplaces alike treat as a promise of "new."
What EKOM brings is the ability to catch this at the speed the group is growing — running the same pipeline, unattended, on the next rooftop the same way it ran on the first, without asking a newly-added store to change its systems first. For a group built by operators who know exactly what the luxury standard looks like on the showroom floor, catching where the data quietly falls short of it is the same discipline applied to a different layer of the business.
This is what one unattended pass surfaces with no access, no schema, and no one pointing at the problem.
The same pipeline runs the same way on the next rooftop, and the next platform.