Fashion stores: can an AI agent find the right size, in stock, with returns it can quote?
In clothing, footwear and accessories the decision turns on size, fabric, stock in the chosen size and how returns work. An agent can only compare what your product page states in a form it can read.
Requests a shopper might give an agent
- “Find a linen shirt in size M under ₺1,500 that I can return for free.”
- “Waterproof hiking boots in EU 42, delivered by Friday.”
- “A leather belt, 95 cm, in black or dark brown, with at least a one-year warranty.”
Examples written by us to show the kind of constraints shoppers set. They are not measured question frequencies.
The questions an agent needs your product page to answer
The free test reads one of your product pages and checks whether it answers the questions expected for that type of product: first in the structured data, then in the visible page text (a rule-based dictionary in Turkish and English, no AI). The result appears as the “Product question coverage” line, which doesn’t affect the score.
| Question | Why it matters here | Expected for |
|---|---|---|
| size / dimensions | The first filter in almost every clothing request. A size chart only in an image can’t be read. | clothing, footwear, accessories |
| material / ingredients | Fabric and fibre percentages separate “linen shirt” from “linen-look shirt”. | clothing, footwear, accessories |
| care | Washing instructions answer “machine washable?” and similar questions. | clothing, footwear, accessories |
| warranty | Expected for accessories such as watches and bags, not for clothing. | accessories |
| returns | Shoppers buying sizes they can’t try on set return conditions; the agent needs the period and who pays. | clothing, footwear, accessories |
| delivery time | Deadlines (“by Friday”) are common; without a delivery time the agent can’t confirm it. | clothing, footwear, accessories |
| stock / variants | The agent must know that the chosen size and colour, not just the product, is in stock. | clothing, footwear, accessories |
Where the test looks for each answer
- size / dimensions: additionalProperty named size/dimension, or size, width, height, depth; in text: a size chart, “dimensions:”, measurements like 40 × 60 cm or 50 ml.
- material / ingredients: material in the product data or additionalProperty named material/fabric/ingredients; in text: “material:”, “ingredients:”, fibre percentages.
- care: additionalProperty named care/wash; in text: care or washing instructions, dry clean only, 30°C wash.
- warranty: warranty in the product or offer; in text: “2-year warranty”, warranty period, manufacturer’s warranty.
- returns: hasMerchantReturnPolicy in the product or offer data; in text: “14-day free returns”, return period.
- delivery time: shippingDetails with handling and transit time; in text: estimated delivery, ships within N days, same-day dispatch.
- stock / variants: availability in the offer, or variants (hasVariant); in text: in stock, out of stock, only N left.
The checks that matter most in this category
All 27 checks run on every store and the weights are the same for everyone; these are the ones most often decisive in this category, and why. Each name opens the check’s own page.
| Weight | |
|---|---|
| Can variants (size, color) be addressed? Each size and colour needs its own address and offer, or the agent can’t point to the exact variant. | 2 |
| Stock consistency Stock in the structured data must match what the page shows for the chosen variant. | 3 |
| Price, currency, availability and URL Price, currency, availability and URL are the minimum an agent needs to quote a variant. | 6 |
| Machine-readable return policy A machine-readable return policy lets the agent compare return periods across stores. | 5 |
| Returns page and window The returns page and window must also be stated in plain words on the site. | 4 |
| Images and description Images and a real description carry fit and fabric details an agent quotes. | 2 |
Run the free test on your store → How the free test works →
Simulator scenarios that fit
The agent simulator sends AI agents through your store in a real browser. They stop at checkout: they never order, sign in or type personal data.
Free simulator
- Conditional search: Size, colour and budget in one request: the core fashion task.
- Policy reading (return period, shipping cost): Reads the return period and shipping cost before adding to cart.
Paid project panel (one extra scenario each month, in rotation)
- Filter and variant: Uses a size, colour or price filter on a listing, then picks an in-stock variant.
- Honesty when out of stock: Checks that an agent stops and says so when the size is sold out, instead of silently picking another.
- Multi-item cart and removing an item: Two sizes of one item in the cart, then removes one: common when shoppers aren’t sure of their size.
Send the agents to your store → · Pricing →
What we don’t claim
- The free test reads one product page; size charts that open in a pop-up or load later by script may not be in the initial HTML it reads.
- Fit advice (“runs small”) is not checked; only whether size information exists.
- We don’t publish averages for this category: no figure without our own sample size and date.
- The question check is a dictionary signal on one product page, not a verdict: a phrase it finds may not fully answer the question, which is why the result shows the excerpt.
- Nobody can guarantee that an AI assistant recommends your products; we measure whether agents can read and use your store.
Questions
Our size chart is an image. Is that a problem?
For agents, usually yes: they read text and structured data. Keep the image if you like, but put sizes in text on the product page and, where you can, in the product data (size, additionalProperty).
Do you check every size and colour?
The free test checks whether variants are addressable and whether stock is consistent on the page it reads. The simulator and the panel’s deep audit go further on real product pages.