AI Commerce Research

What AI actually sees when it reads your product page.

These patterns come from Squiggle's Product Understanding Lab, reading public product listings one category at a time. The before-and-after examples are illustrations of those patterns, not captures of any one store.

Squiggle's category guidance is informed by ongoing analysis of publicly available ecommerce product information. Illustrative examples explain common product-understanding principles and do not represent findings from any one merchant or the entire category.

Buyer's question: "Can you recommend brake pads for a 2018 Example Motors Aurora?"

Before — thin product listing

Product title

Brake Pads Front

Description

High quality brake pads. Easy to fit. Made for most vehicles.

AI shopping assistant — illustrative

"The listing shows brake pads, but nothing about which vehicles they fit, so I can't tell whether they suit your Aurora. You'd want to check with the manufacturer first."

After — complete product listing

Product title

Sport Ceramic Brake Pads — Front — Example Motors Aurora AR2 (2013–2019)

Description

Ceramic compound engineered for street driving. Low dust, strong initial bite. Fits Aurora AR2 1.4T, 2.0T and 1.6 diesel. Direct OEM replacement.

AI shopping assistant — illustrative

"The Sport Ceramic front pads fit your 2018 Aurora. Listed for the AR2 generation, low dust, strong initial bite, in stock."

The gap: Missing vehicle compatibility and fitment data.

The same product. The same store.
The only difference is whether an AI shopping assistant has enough information to recommend it.

How the Product Understanding Lab works

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.

What we look at, and what we never do

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, and there's nothing to opt into or install. Before a finding is published it has to clear three questions: is it accurate, is it useful to a merchant on any platform, and can it be described without identifying any individual store? Everything else stays an internal working hypothesis.

We never name an individual store's results 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. That protects the brands we study, and it's the same protection your own store gets: a pattern from your audit is never attributed to you without your permission.

Current research coverage

The badge on each row is the publication status of our category guidance, and nothing else. Published means the guidance is written, reviewed and in the Research Library — it does not mean we are making a claim about how common anything is across that category. In preparation means the category is entering Product Understanding research next and the site is ready for it. Under investigation means the category is on our research roadmap but we haven't written it up yet. Separately, and shown underneath, Available in Store Audit means the audit engine has a check built specifically for that category — today that is Automotive fitment. Every store also gets the catalogue-wide checks (duplicate content, missing descriptions, technical data gaps), whatever it sells.

Read the published findings

Our research library carries the full category write-ups — what we found, why it happens, and exactly what to fix.