Kiwop Labs · report
zalando.es
Under 55. Either it cannot get in, or it gets in and finds nothing it can use.
What we measure and how much it weighs
- AI crawlers 13.6/25
robots.txt locks out GPTBot, ClaudeBot, Google-Extended, Applebot-Extended, Bytespider. The rest can get in.
- Access for an identified bot 10/10
The home page answers a bot that identifies itself.
- llms.txt 0/15
No llms.txt. It is the cheapest way to tell an assistant what you sell and how.
- Structured data on the home page 0/10
The home page carries no JSON-LD. The assistant does not know which company is behind it.
- Readable product page 0/25
We found no product page with JSON-LD Product. Without it, the agent does not know what you sell or at what price.
- Declared sitemap 0/10
No sitemap declared. Crawlers have to guess the catalogue.
- HTTPS 5/5
The store is served over HTTPS.
What to do
In order of impact. The first item recovers the most points for the least effort.
- Readable product page (+25). Expose a JSON-LD Product with Offer (price, priceCurrency, availability) on every product page. It is what an agent reads to compare and buy. How we do it
- llms.txt (+15). Write your own llms.txt: what you sell, to whom, shipping, returns and the category URLs. Half an hour of work. How we do it
- AI crawlers (+11). Open robots.txt to the AI crawlers you want to be cited by. Blocking GPTBot while letting OAI-SearchBot through is a legitimate decision; blocking everything is disappearing. How we do it
- Structured data on the home page (+10). Add an Organization or OnlineStore JSON-LD to the home page with name, logo, contact and sameAs. Fix the broken blocks. How we do it
- Declared sitemap (+10). Declare the sitemap in robots.txt with a Sitemap: line. Without it, the catalogue is discovered in fits and starts. How we do it
Against the 300 stores in the study
Same signals, same method version. The study measures a stratified sample of Spanish stores.
| Signal | Your store | Study (%) |
|---|---|---|
| Blocks at least one AI crawler | Yes | 10.7 |
| Verified llms.txt | No | 26 |
| Product page with Product schema | No | 27.8 |
| Detectable chatbot | No | 23.2 |
Measurement detail
| Crawler | Policy in robots.txt |
|---|---|
GPTBot | Blocked · own rule |
OAI-SearchBot | Gets in, some paths disallowed |
ChatGPT-User | Gets in, some paths disallowed |
ClaudeBot | Blocked · own rule |
anthropic-ai | Gets in, some paths disallowed |
PerplexityBot | Gets in, some paths disallowed |
Google-Extended | Blocked · own rule |
Applebot-Extended | Blocked · own rule |
CCBot | Gets in, some paths disallowed |
Bytespider | Blocked · own rule |
meta-externalagent | Gets in, some paths disallowed |
- No llms.txt.
- No JSON-LD on the home page.
- Product page tested: https://www.zalando.es/consigue-el-look-mujer/. JSON-LD types: –.
- No detectable chatbot on the home page.
- No detectable third-party search.
A report is kept for 7 days. If you have changed something, measure again and the new result will appear at this same URL.
This report is public
It has its own URL and can be cited or linked: https://www.kiwop.com/en/labs/ai-readiness-check-ecommerce/zalando.es
Kiwop Labs (13 September 2026). AI readiness report for zalando.es. https://www.kiwop.com/en/labs/ai-readiness-check-ecommerce/zalando.es
Report data under CC BY 4.0. Method and scripts open at Kiwop Labs. If you own the store and do not want it listed, write to [email protected].
Let's talk.
Initial technical consultation
AI, security and performance. Diagnosis with phased proposal.
- NDA available
- Response <24h
- Phased proposal
Your first meeting is with a Solutions Architect, not a salesperson.
Request diagnosis