What an AI agent reads on Kaiju
An assistant's crawler fetches the page once, without running JavaScript, and reads the text, the structured data and the links. Below is what it gets from kaijurestaurant.be, taken from the copy the scanner kept.
310
characters of text without JavaScript, too few to answer questions from
LocalBusiness
structured data for the business
3
of 3 AI crawlers turned away at the edge (GPTBot, ClaudeBot, PerplexityBot)
The words an agent gets
Title: HOME 26 | Kaiju Restaurant · language fr. First 310 of 310 characters:
HOME 26 | Kaiju Restaurant top of pagePasser au contenu principalANTWERP, GHENTRESERVATIONS KAIJU PHILOSOPHY NEKO ROOFTOPBAR JOBS CONTACTKaiju, Gaspar De Crayerstraat 2, 9000 Ghent Neko Rooftop Bar, Gaspar De Crayerstraat 2, 9000 Ghent Kaiju x Wolf, Felix Pakhuis, Godefriduskaai 30, 2000 Antwerpbottom of page
What it can say about the business
| A business type in JSON-LD | LocalBusiness |
| Name | Kaiju |
| Telephone | 02/537.10.05 |
| Address | yes |
| Opening hours | no |
| Menu or price list | nothing |
| Cuisine in structured data | no |
| JSON-LD blocks | 2 (LocalBusiness, PostalAddress, WebSite) |
The links it would act on
No booking or ordering link found. An agent has nothing to act on.
Everything here comes from fetching the homepage once as a crawler. The report turns it into a score and a list of fixes, with code to paste.