Old Boy
oldboyrestaurant.be is mostly ready for agents.
Listed by OpenStreetMap · Overture Maps.
Ways to reach Old Boy directly, with no marketplace in between. Checked 2026-10-18. Through sevenrooms acting for the business. Report a mistake
Hours, from OpenStreetMap · Overture Maps: Mo 18:30-21:15; Tu,Th-Sa 12:00-14:15,18:30-21:30
The website's grade
An AI assistant can open Old Boy's website. What Old Boy offers is in a PDF or an image, and assistants read those badly. It finds a way to book or order directly, through SevenRooms.
47 of 65 points available
agent-readiness level, Basic Web Presence
things to fix
Provisional, with the action test and the assistant citation check still to come. The hatched part of the bar isn't measured yet.
What assistants answer
Each assistant gets three questions about this business: the official website, where to book and where to order. Each cell shows where the answer sent people.
The assistants haven't been asked about this business yet. They're asked about the top-ranked businesses in each city index, and about any business as soon as it's claimed. Claim this page to be included.
The assistants were asked 13 everyday questions about Brussels and named 67 places. Old Boy wasn't one of them. See who was named →
How Old Boy compares
531 of 1,568 in Brussels
Top 34% of the sites scanned in this index. Just above: Matiate B, OMI restaurant B. Just below: Omonni Fried Chicken B, Philema B.
| What the top 10% of the index does | Top 10% | This site |
|---|---|---|
| Take bookings or orders on their own domain | 100% | yes |
| Publish the menu or price list as HTML | 100% | no |
| Let AI crawlers in (no block at the server or in robots.txt) | 100% | yes |
| Structured data with address, phone and hours | 94% | no |
| Have an llms.txt | 3% | no |
The top 10% are the 159 highest-scoring reachable sites in the index at the last update.
Compared with its peers
| Average score | A or B | This site | |
|---|---|---|---|
| Sites built with WordPress 68,857 sites | 58% | 30% | 72.3% |
| Sites using SevenRooms 1,201 sites | 70% | 53% | 72.3% |
Nearest places in the index
| Place | Distance | Grade | Direct booking or ordering |
|---|---|---|---|
| Le Fruit Défendu french | 21 m | F | no |
| Le 17.45 deli, cheese | 47 m | B | yes |
| Elise | 111 m | A | yes |
| Milano Torino pizza | 137 m | D | no |
| L'Atelier de Nicolas breakfast_and_brunch | 150 m | D | no |
| Kamo japanese | 163 m | B | yes |
| Seino french, japanese | 181 m | A | yes |
| Le garage à manger french, cafe | 221 m | D | no |
| BamBosh Kitchen | 229 m | F | no |
| Al Bacio pizza | 232 m | C | no |
Businesses like Old Boy in Brussels
| Group | Sites | Avg score | A or B | This site |
|---|---|---|---|---|
| Businesses of the same kind in Brussels | 1,568 | 58% | 36% | 72.3% |
| Sites built with WordPress in Brussels | 508 | 64% | 41% | 72.3% |
| Sites using SevenRooms in Brussels | 4 | 55% | 25% | 72.3% |
| Sites built with WordPress and using SevenRooms in Brussels | 2 | 62% | 50% | 72.3% |
The best of the sites using SevenRooms in Brussels
Le Petit Bon Bon C 58.5% · Tigermilk D 50.8% · Lila29 D 40%
After the top fixes
With the two fixes above (Structured data is incomplete; Menu or price list is a PDF), the score would be about 87.7%. That would be 226th of 1,568 in Brussels, up from 531st.
Peers are the businesses in the same index that have a reachable site, using the latest scan of each. The rank comes from the index's current ranking.
What to fix first
- Structured data is incomplete +7 points
Missing: address, telephone, opening hours. How to fix it
- Menu or price list is a PDF +3 points
Most agents skip PDFs or read them badly. Publish it as an HTML page and keep the PDF as a download. How to fix it
- No llms.txt no points, but worth doing
Optional for now and cheap to add. It's a short text file that describes the business for language models. How to fix it
Send the fixes to your web person
No one is listed yet to fix this in Brussels. List your agency or yourself. It's free, and every listing is reviewed by hand.
Already right
- robots.txt lets AI crawlers in No rule blocks the main AI user agents.
- AI crawlers get the page GPTBot, ClaudeBot and PerplexityBot all got a normal response.
- Structured data found (Organization) no address, phone or hours in it
- Booking through sevenrooms on your own domain There's no marketplace commission, and the customer stays yours.
- SevenRooms works with agents through its partners SevenRooms' terms (17 April 2026) bar any robot, spider, scraper or other automated means except bona fide search engines; Google names SevenRooms as an AI Mode booking partner. Terms read on 2026-10-15: https://sevenrooms.com/terms-of-service/. An assistant that isn't a partner may not be able to finish there. A direct path on your own domain works for all of them.
Builder: wordpress · Front: cloudflare · menu page /pdf/evening: answered 200
What to paste
Filled in from the business's own record and this scan. Check every line before it goes live. The guides show where it goes on wordpress.
Where to paste it on WordPress: a plugin that adds code to every page's header, such as WPCode (Insert Headers and Footers), in its Header box. the official help page.
Show the code to paste
Structured data (JSON-LD)
Paste it as one block in the page's head, or in the builder's custom code box. Change anything that's wrong. Guide.
<script type="application/ld+json">
{
"@context": "https://schema.org",
"@type": "Restaurant",
"name": "Old Boy",
"url": "http://www.oldboyrestaurant.be/",
"geo": {
"@type": "GeoCoordinates",
"latitude": 50.8208039,
"longitude": 4.3610839
},
"openingHours": "Mo 18:30-21:15; Tu,Th-Sa 12:00-14:15,18:30-21:30",
"openingHoursSpecification": [
{
"@type": "OpeningHoursSpecification",
"dayOfWeek": [
"Monday"
],
"opens": "18:30",
"closes": "21:15"
},
{
"@type": "OpeningHoursSpecification",
"dayOfWeek": [
"Tuesday",
"Thursday",
"Friday",
"Saturday"
],
"opens": "12:00",
"closes": "14:15"
},
{
"@type": "OpeningHoursSpecification",
"dayOfWeek": [
"Tuesday",
"Thursday",
"Friday",
"Saturday"
],
"opens": "18:30",
"closes": "21:30"
}
],
"acceptsReservations": "https://www.sevenrooms.com/explore/oldboy/reservations/create/search",
"hasMenu": "https://oldboyrestaurant.be/pdf/evening",
"potentialAction": [
{
"@type": "ReserveAction",
"target": {
"@type": "EntryPoint",
"urlTemplate": "https://www.sevenrooms.com/explore/oldboy/reservations/create/search",
"actionPlatform": [
"http://schema.org/DesktopWebPlatform",
"http://schema.org/MobileWebPlatform"
]
},
"result": {
"@type": "Reservation",
"name": "Reservation"
}
}
]
}
</script>
llms.txt
Save as /llms.txt at the root of the site. Guide.
# Old Boy > restaurant in Brussels. ## Book or order directly - Book: https://www.sevenrooms.com/explore/oldboy/reservations/create/search (through sevenrooms acting for the business) - Menu: https://oldboyrestaurant.be/pdf/evening ## Opening hours Mo 18:30-21:15; Tu,Th-Sa 12:00-14:15,18:30-21:30 ## About - Website: http://www.oldboyrestaurant.be/ - This file follows llms.txt (https://llmstxt.org): a short plain-text description for language models.
Own this business?
If you fixed something or think a check is wrong, rescan. Rescans are free. Claiming takes one email to confirm. After that, the three assistants are asked about the business right away and the site is rescanned every week. You get a message only when the score changes.
Rescan now · Markdown · Dispute a check
Keep watching this business: the assistants are asked again every month, and you see what changed. 2 EUR a month or 19 EUR a year. Deep report: ten questions to each assistant, plus the places nearby. 5 EUR, paid once. Reading and scanning stay free. These few euros pay for the questions sent to the assistants and for the servers.
Show the score
Owners who score well put the badge on their site. It links back here and updates with every scan.
<a href="https://directindex.org/r/oldboyrestaurant.be"><img src="https://directindex.org/badge/oldboyrestaurant.be.svg" alt="Agent-Direct Score B" width="236" height="40"></a>
What agents get, and what the site publishes
The direct record agents get for this business, the rails an agent could transact through, and the agent standards the site publishes.
Show the details
What agents get for Old Boy
The links an assistant is sent when it books, orders or reads the menu for this business, where each leads, and when a browser last checked it. The same record is served as JSON at /api/direct/oldboyrestaurant.be, through the MCP tool direct_record and in the city feed /city/brussels/direct.json.
| Path | Link | Status |
|---|---|---|
| Book | www.sevenrooms.com/explore/oldboy/reservations/create/search vendor on own site: SevenRooms | found by the scan of 2026-10-18, not yet tested |
| Order | none on record | |
| Menu | oldboyrestaurant.be/pdf/evening pdf | from the scan |
| Hours | Mo 18:30-21:15; Tu,Th-Sa 12:00-14:15,18:30-21:30 (closed now) | from OpenStreetMap |
| Phone | none on record |
Stable links that count: /go/oldboyrestaurant.be/book, /go/oldboyrestaurant.be/menu answer 302 to the links above; the count is the line "followed N direct links" on this page.
Owners: claim the business below to correct this record; the claim email carries the link.
Can an agent transact?
Measured, not scored: the Agent-Direct Score stays at specification v1.0. This says which rails an agent could transact through today, and what the booking or ordering vendor's terms allow.
| UCP profile /.well-known/ucp, Google and Shopify's Universal Commerce Protocol | no |
| ACP discovery document /.well-known/acp.json, OpenAI and Stripe's Agentic Commerce Protocol | no |
| MCP server card /.well-known/mcp/server-card.json | no |
| Ordering vendor that takes agent orders Square, Toast, or a vendor whose terms allow agents | no |
| Vendor terms for agents SevenRooms, read 2026-10-15 | Through partners |
SevenRooms' terms (17 April 2026) bar any robot, spider, scraper or other automated means except bona fide search engines; Google names SevenRooms as an AI Mode booking partner. Source. About SevenRooms · all vendors.
Level 1 of 5, Basic Web Presence
These are the standards an agent looks for before it reads a page, checked the same way as Cloudflare's Agent Readiness scan. They don't count toward the score. Each missing item links to a how-to. Cloudflare's report.
| Link headers on the homepage | no how |
| sitemap.xml | yes |
| AI bot rules in robots.txt | yes |
| Content Signals in robots.txt | no how |
| Markdown on Accept: text/markdown | no how |
| llms.txt | no how |
| API catalog (RFC 9727) | no how |
| MCP server card | no how |
| A2A agent card | no how |
| Agent Skills index | no how |
| OAuth or OIDC discovery | no how |
| OAuth protected resource metadata | no how |
| auth.md | no how |
| Web Bot Auth key directory | no how |
| ARD capability manifest | no how |
| DNS-AID records | no how |
| WebMCP tools on the page | no how |
| JSON-LD for the business | yes |