What an AI agent reads on Takumi
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 restaurant-takumi.com, taken from the copy the scanner kept.
160
characters of text without JavaScript, too few to answer questions from
none
structured data for the business
2
of 3 AI crawlers turned away at the edge (GPTBot, ClaudeBot)
The words an agent gets
Title: 東京西麻布 Takumi レストラン タクミ · language ja. First 160 of 160 characters:
東京西麻布 Takumi レストラン タクミ 2024.09.29 クリスマス・年末特別コースのご案内 2023.10.19 クリスマス特別メニューのご案内 2023.10.18 2023年11月1日からのコース価格変更のお知らせ Copyright © takumi All Rights Reserved.
What it can say about the business
| A business type in JSON-LD | no |
| Name | no |
| Telephone | no |
| Address | no |
| Opening hours | no |
| Menu or price list | a menu or price-list page in HTML restaurant-takumi.com/menu/ |
| Cuisine in structured data | no |
| JSON-LD blocks | 0 |
The links it would act on
| Link | Role | Where it goes |
|---|---|---|
| restaurant-takumi.com/reservation/ | booking | the business's own site |
| pocket-concierge.jp/en/restaurants/244145?seat_date_eq=2023-11-08 | booking | an unrecognised third party |
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.