AI Commerce Research
Every claim on this page comes from Squiggle's Product Understanding Lab — research read directly from real, publicly published product listings, one category at a time. Explore the six categories we've published below, then see how we turn research into evidence without ever naming the stores we studied.
Buyer's question: "Can you recommend brake pads for a 2018 Volkswagen Golf?"
Before — thin product listing
Product title
Brake Pads Front
Description
High quality brake pads. Easy to fit. Made for most vehicles.
AI shopping assistant says
"I can see this store sells brake pads, but I can't find compatibility information for your vehicle in the listing. You may want to check with the manufacturer before purchasing."
After — complete product listing
Product title
EBC Greenstuff Sport Brake Pads — Front — VW Golf Mk7 (2013–2019)
Description
Greenstuff compound engineered for street driving. Low dust, strong initial bite. Fits Golf Mk7 1.4T, 2.0T, and 1.6 TDI. Direct OEM replacement.
AI shopping assistant says
"Yes — the EBC Greenstuff Front Pads are a strong match for your 2018 Golf. Listed as compatible with Golf Mk7 models, with low dust and strong initial bite. In stock."
Buyer's question: "What moisturiser is good for sensitive, acne-prone skin?"
Before — thin product listing
Product title
Daily Glow Moisturiser
Description
Lightweight daily moisturiser for radiant, healthy-looking skin.
AI shopping assistant says
"I can see this store sells a daily moisturiser, but the listing doesn't state whether it's fragrance-free or suitable for sensitive or acne-prone skin, so I can't confidently recommend it."
After — complete product listing
Product title
Daily Glow Moisturiser — Fragrance-Free, for Sensitive & Acne-Prone Skin
Description
Non-comedogenic, fragrance-free formula with 2% niacinamide and hyaluronic acid. Formulated for sensitive, acne-prone, and reactive skin.
AI shopping assistant says
"Yes — this moisturiser is fragrance-free, non-comedogenic, and formulated specifically for sensitive, acne-prone skin, with niacinamide to help manage breakouts."
Buyer's question: "Do you have a protein snack that's low in sugar?"
Before — thin product listing
Product title
Choc Protein Bar
Description
Delicious protein bar. High in protein, low in sugar. Great post-workout snack.
AI shopping assistant says
"I can see this store sells a protein bar marketed as low-sugar, but the listing doesn't state the actual sugar content or allergens, so I can't confirm it meets your needs."
After — complete product listing
Product title
Choc Protein Bar — 20g Protein, 2g Sugar
Description
230kcal, 20g protein, 8g fat, 12g carbs (2g sugar) per 60g bar. Gluten-free, no added sugar. Contains milk and soy; may contain nuts.
AI shopping assistant says
"Yes — this bar has 20g protein and just 2g sugar per serve, and it's gluten-free. It contains milk and soy, so check that against any allergies."
Buyer's question: "Will this 3-seater sofa fit my compact living room?"
Before — thin product listing
Product title
3-Seater Sofa — Charcoal
Description
Modern charcoal sofa. Stylish and comfortable. Great for any living room.
AI shopping assistant says
"I can see this store sells a 3-seater sofa, but the listing doesn't state its dimensions, so I can't confirm it will fit a compact space."
After — complete product listing
Product title
3-Seater Sofa — Charcoal — 210 × 88 × 84cm
Description
Packaged size 215×95×90cm — fits through a standard 80cm doorway. Stain-resistant weave fabric, solid pine frame. Legs-only assembly, one person, 10 minutes.
AI shopping assistant says
"Yes — at 210×88×84cm this sofa suits a compact living room, and it's listed as fitting through a standard doorway with quick one-person assembly."
Buyer's question: "Will this jacket fit me, and how does it run?"
Before — thin product listing
Product title
Relaxed Utility Jacket
Description
A relaxed utility jacket in durable cotton canvas. Available in sizes XS–XL.
AI shopping assistant says
"I can see this store sells a utility jacket in sizes XS to XL, but the listing doesn't state the measurements or how it fits, so I can't confirm whether it'll suit you."
After — complete product listing
Product title
Relaxed Utility Jacket — True to Size (Chest 104–112cm, Length 71cm)
Description
Relaxed fit utility jacket in durable cotton canvas. True to size — size down for a closer fit. Chest 104–112cm, length 71cm across the size range. Available XS–XL.
AI shopping assistant says
"Yes — this jacket runs true to size, with a relaxed fit at 104–112cm chest across the range. Size down if you'd prefer it closer-fitting. Available XS to XL."
Buyer's question: "What running shoes are good for flat feet?"
Before — thin product listing
Product title
Trail Runner Pro
Description
Great running shoes for everyday training. Lightweight and durable.
AI shopping assistant says
"I can see this store sells the Trail Runner Pro, but the listing doesn't state its arch support or suitability for flat feet, so I can't confirm it's a good match."
After — complete product listing
Product title
Trail Runner Pro — Stability Support for Overpronation
Description
Stability running shoe with medium arch support and a 10mm heel-to-toe drop. Designed for overpronation and flat feet. True to size.
AI shopping assistant says
"Yes — the Trail Runner Pro offers stability support built for overpronation and flat feet, with a 10mm drop suited to road running."
Every category asks a different question. The mechanism never changes — AI can only recommend a product when it can confidently answer that question.
The same product. The same store.
The only difference is whether AI has enough information to recommend it.
How this research happens
The Lab reads real, publicly published product listings — one category at a time — and asks a single question: could an AI shopping assistant confidently answer the question a real buyer would ask about this product?
We're not looking for one store's mistake. We're looking for a pattern that repeats — one that shows up across multiple brands, including brands that do almost everything else right. A pattern only becomes a registered finding once we've checked it against more than one brand and it holds.
From research to claim
Not everything the Lab observes becomes something we publish. Before an internal finding becomes a public claim — like the examples above, or the category write-ups in our research library — it has to clear three questions: is it accurate, is it genuinely useful to a merchant regardless of what platform or tools they use, and can it be described without identifying any individual store?
Only findings that clear all three get published. Everything else stays an internal working hypothesis until it does.
Research governance
We only ever read what's already public — the same product pages any shopper, or any AI assistant, can see. We never access a store's account, sales data, or private information to do this research. There's nothing to opt into and nothing to install; it's simply public information, read carefully.
Why we never name names
We never name an individual store's results in anything we publish without that store's consent. Findings are always described in aggregate — as a pattern across a category — never as a scorecard on any one business.
This matters for two reasons. First, it protects the brands we study during research, most of which do the majority of things well and none of which asked to be publicly graded. Second, it's the same protection your own store gets: if a pattern from your own audit ever informs future research, it will never be attributed to you without your permission.
Where each category stands
Live means findings are published and a detector runs in your audit today. Published means the Lab's findings are checked against real catalogues and in the Research Library, with broader engine support still being built. In preparation means the category is entering Product Understanding research next — the site is ready for it, but we show no findings until they're checked. Under investigation means the category is on our research roadmap but not yet actively studied. Your Store Audit today reflects Automotive fitment plus catalogue-wide checks (duplicate content, missing descriptions, technical data gaps) across every category.
Our research library carries the full category write-ups — what we found, why it happens, and exactly what to fix.