revirkarlin.cz is hard for agents to use.
Menu: www.revirkarlin.cz/menus/menu_cs_24_2.pdf
See what an AI agent reads on this site →
Read by AI agents 4 times this month (ClaudeBot 4). The crawlers behind the assistants read this page when they answer questions about the business.
32.7 of 65 points available
agent-readiness level, Not Ready
things to fix
Provisional: the action test and the assistant citation check still to come; the hatched part of the bar is not measured yet.
Add schema.org JSON-LD for the business (CafeOrCoffeeShop, BarOrPub or the closest type, with name, address, telephone and openingHoursSpecification, plus servesCuisine). It is the one block every assistant reads first; the fix kit below has it filled in. How to fix it
Check that the provider keeps you as the merchant of record. How to fix it
Live fetches as ClaudeBot (http_429) were refused while a normal browser got the page. This is usually a hosting or firewall bot list the owner never chose. Ask the host to allow these user agents. How to fix it
Most agents skip PDFs or read them badly. Publish it as HTML, keep the PDF as a download. How to fix it
Optional today, cheap to add: a short text file describing the business for language models. How to fix it
No one is listed yet to fix this in Prague cafes and bars. List your agency or yourself: free, reviewed by hand.
Builder: unknown · Front: cloudflare · Cloudflare in front; AI crawlers blocked at the edge
Filled from the business's own record and this scan. Check every line before it goes live; where it goes on your builder is in the guides.
One block in the page's head, or in the builder's custom-code slot. Replace anything that is wrong. Guide.
<script type="application/ld+json">
{
"@context": "https://schema.org",
"@type": "BarOrPub",
"name": "Revír Karlín",
"url": "https://www.revirkarlin.cz",
"telephone": "+420725836320",
"address": {
"@type": "PostalAddress",
"streetAddress": "Karolinská 707/7",
"postalCode": "18600",
"addressLocality": "Praha"
},
"geo": {
"@type": "GeoCoordinates",
"latitude": 50.0949637,
"longitude": 14.4455116
},
"openingHours": "Tu-We 17:00-00:00; Th-Fr 17:00-02:00; Sa 18:00-02:00",
"openingHoursSpecification": [
{
"@type": "OpeningHoursSpecification",
"dayOfWeek": [
"Tuesday",
"Wednesday"
],
"opens": "17:00",
"closes": "00:00"
},
{
"@type": "OpeningHoursSpecification",
"dayOfWeek": [
"Thursday",
"Friday"
],
"opens": "17:00",
"closes": "02:00"
},
{
"@type": "OpeningHoursSpecification",
"dayOfWeek": [
"Saturday"
],
"opens": "18:00",
"closes": "02:00"
}
],
"hasMenu": "https://www.revirkarlin.cz/menus/menu_cs_24_2.pdf"
}
</script>
Save as /llms.txt at the root of the site. Guide.
# Revír Karlín > bar or pub in Karolinská 707/7 18600 Praha, Prague cafes and bars. Phone +420725836320. ## Book or order directly - Menu: https://www.revirkarlin.cz/menus/menu_cs_24_2.pdf ## Opening hours Tu-We 17:00-00:00; Th-Fr 17:00-02:00; Sa 18:00-02:00 ## About - Website: https://www.revirkarlin.cz - This file follows llms.txt (https://llmstxt.org): a short plain-text description for language models.
Top 41% of the sites scanned in this index. Just above: Dobrá čajovna D, Czech Inn Kafe D. Just below: Acai Poke D, Apetit D.
| What the top tenth of the index does | Top 10% | This site |
|---|---|---|
| Take bookings or orders on their own domain | 75% | no |
| Publish the menu or price list as HTML | 72% | no |
| Let AI crawlers in (no edge block, no robots.txt block) | 91% | no |
| Structured data with address, phone and hours | 28% | no |
| Have an llms.txt | 39% | no |
The top tenth is the 57 best-scoring reachable sites of the index at the last refresh.
| Place | Distance | Grade | Direct booking or ordering |
|---|---|---|---|
| Dva Kohouti | 188 m | D | no |
| kafe Karlín coffee_shop | 230 m | F | no |
| sedm° | 246 m | B | yes |
| Café MARTIN | 298 m | D | no |
| The Miners Coffee Karlín | 300 m | D | no |
| Frida mexican | 332 m | B | no |
| RESPEKTO - BAR Primator | 396 m | D | no |
| Parlor Café coffee_shop, breakfast, lunch | 416 m | C | no |
| Dharmasala tearoom, tibetan | 430 m | F | no |
| Rapid bar 65 | 445 m | F | no |
| Group | Sites | Avg score | A or B | This site |
|---|---|---|---|---|
| Same kind in Prague cafes and bars | 560 | 46% | 13% | 50.3% |
Sladká Cesta A 100% · ALIBI A 96.3% · Cacao A 95.4% · Hospůdka Sokol A 95.4% · Lavish Lounge A 95.4%
With the three fixes above (No structured data for the business; Booking through an unrecognised third party; The server turns AI crawlers away at the door) the score would be about 90.8%: 7th of 560 in Prague cafes and bars, up from 231st.
Peers are the businesses of the same index with a reachable site, latest scan of each; the rank uses the index's current ranking.
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/revirkarlin.cz, through the MCP tool direct_record and in the city feed /city/prague-cafes-bars/direct.json.
| Path | Link | Status |
|---|---|---|
| Book | none on record | |
| Order | none on record | |
| Menu | www.revirkarlin.cz/menus/menu_cs_24_2.pdf pdf | from the scan |
| Hours | Tu-We 17:00-00:00; Th-Fr 17:00-02:00; Sa 18:00-02:00 (closed now) | from OpenStreetMap |
| Phone | +420725836320 |
Stable links that count: /go/revirkarlin.cz/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.
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 | not measured |
| ACP discovery document /.well-known/acp.json, OpenAI and Stripe's Agentic Commerce Protocol | not measured |
| 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 | not measured |
Not measured at this scan; the next scan measures it.
The next scan also reads the contact, menu and booking pages one hop deeper; facts found there can change the score.
The standards an agent looks for before it reads a page, on the same criteria as Cloudflare's Agent Readiness scan. Not part of the score; each missing item links to a how-to. Cloudflare's report.
| Link headers on the homepage | no how |
| sitemap.xml | no how |
| AI bot rules in robots.txt | no how |
| 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 | no |
Each assistant is asked three questions about this business: the official website, where to book, where to order. The cell says where the answer sent people.
Not asked yet. Assistants are asked about the top-ranked businesses in each city index, and about every claimed business the moment it is claimed; claim this page to be included.
Owners who score well embed the badge; it links back here and updates with every scan.
<a href="https://directindex.org/r/revirkarlin.cz"><img src="https://directindex.org/badge/revirkarlin.cz.svg" alt="Agent-Direct Score D" width="236" height="40"></a>
Fixed something, or think a check is wrong? Rescans are free. Claiming takes one email to confirm; after that the three assistants are asked about the business right away, the site is rescanned weekly, and you get a message only when the score changes.
Deep report Ten questions the way people ask, each assistant's full answer, the eight nearest similar places, the fix plan and a PDF: 19 EUR, one-off.