# Château Kaputt: Agent-Direct Score D (46.2%)

Site: https://kaputt.berlin
Report: https://directindex.org/r/kaputt.berlin
Scanned: 2026-10-17 (Provisional, with the action test and the assistant citation check still to come. The hatched part of the bar isn't measured yet.)
Château Kaputt is hard for agents to use.
An AI assistant can open Château Kaputt's website. What Château Kaputt offers is in a PDF or an image, and assistants read those badly. To book or order, it is sent to Quandoo, a marketplace.

## Direct links
- Menu: https://kaputt.berlin/CK_Karte.pdf
- Phone: 0491 7621951494

## What to fix first

## What the site tells visitors (Measured, not scored)
- **No English version declared.** Visitors from abroad, and assistants answering in English, read the page as it is. In Berlin, 16% of comparable sites declare one.

- **No structured data for the business.** (+15 points) Add schema.org JSON-LD for the business (CafeOrCoffeeShop, BarOrPub or the closest type, with name, address, telephone and openingHoursSpecification, plus servesCuisine). Every assistant reads this block first, and the fix kit below has it filled in. Guide: https://directindex.org/guides/structured-data-restaurant
- **Booking only through quandoo.** (+12 points) Every transaction an agent makes goes through the marketplace, which takes its commission. Add a direct way on your own site. Even a simple form will do. Guide: https://directindex.org/guides/book-direct-on-your-own-website
- **Quandoo's terms ban bots and automated use, but a direct form on your own site has no such limit.** (+12 points) Quandoo's end-user terms (London, May 2018, section 3.3.1) bar robots, spiders, scrapers or any other automated means of access to the website for any purpose; the operator, Quandoo UK Limited, is in members' voluntary liquidation and the German company is in liquidation too. Terms read on 2026-10-15: https://www.quandoo.co.uk/terms-conditions. An agent that books or orders there goes against the vendor's terms unless the vendor allows it. A form or booking page on your own domain has no such limit. Guide: https://directindex.org/guides/book-direct-on-your-own-website
- **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. Guide: https://directindex.org/guides/menu-pdf-ai
- **Almost no text without JavaScript.** (+2 points) Crawlers that don't run scripts see an empty page. Put the menu, hours and address in plain HTML. Guide: https://directindex.org/guides/website-blank-without-javascript
- **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. Guide: https://directindex.org/guides/llms-txt-for-a-business

## Fix kit: What 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.

```html
<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "LocalBusiness",
  "name": "Château Kaputt",
  "url": "https://kaputt.berlin",
  "telephone": "0491 7621951494",
  "address": "Leberstrasse 57, 10829, Berlin",
  "geo": {
    "@type": "GeoCoordinates",
    "latitude": 52.48164377330938,
    "longitude": 13.361614647949956
  }
}
</script>
```

llms.txt. Save as /llms.txt at the root of the site.

```
# Château Kaputt

> local business in Leberstrasse 57, 10829, Berlin, Berlin cafes and bars. Phone 0491 7621951494.

## Book or order directly

- Menu: https://kaputt.berlin/CK_Karte.pdf

## About

- Website: https://kaputt.berlin
- This file follows llms.txt (https://llmstxt.org): a short plain-text description for language models.
```

## Already right
- **robots.txt lets AI crawlers in.** There's no robots.txt, which means everything is allowed.
- **AI crawlers get the page.** GPTBot, ClaudeBot and PerplexityBot all got a normal response.

## Where it stands
928 of 2381 in Berlin cafes and bars. Top 39% of the sites scanned in this index.

| What the top 10% of the index does | Top 10% | This site |
|---|---|---|
| Take bookings or orders on their own domain | 91% | no |
| Publish the menu or price list as HTML | 57% | no |
| Let AI crawlers in (no block at the server or in robots.txt) | 90% | yes |
| Structured data with address, phone and hours | 24% | no |
| Have an llms.txt | 25% | no |

Nearest places in the index: Schöneberger Pinte (F, 88 m, https://directindex.org/r/edan.io); Isola Rossa (C, 132 m, https://directindex.org/r/isolarossacafeberlin.de); Jansen Bar (F, 171 m, https://directindex.org/r/jansenbar.de); PapalaCup (F, 217 m, https://directindex.org/r/papalacup.de); Café im Wasserturm (B, 374 m, https://directindex.org/r/euref.de); Le Bateau Ivre (D, 375 m, https://directindex.org/r/le-bateau-ivre.de); Sully (F, 410 m, https://directindex.org/r/muetlich.de); Bella Vita Berlin (F, 424 m, https://directindex.org/r/pizzeria-bella-vita-berlin.de); Naumann Dr3i (F, 489 m, https://directindex.org/r/naumann-drei.de); Caffein & Vinoin (F, 492 m, https://directindex.org/r/caffein.de).

## What assistants answer
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.


Compared with its peers: Sites using Quandoo 52% (12% A or B, 115 sites); This site 46.2%.

See what an AI agent reads on this site: https://directindex.org/r/kaputt.berlin/agent-view

## Businesses like Château Kaputt in Berlin cafes and bars

| Group | Sites | Avg score | A or B | This site |
|---|---|---|---|---|
| Businesses of the same kind in Berlin cafes and bars | 2381 | 41% | 11% | 46.2% |
| Sites using Quandoo in Berlin cafes and bars | 5 | 46% | 20% | 46.2% |

The best of the sites using Quandoo in Berlin cafes and bars: Charlotte (B 81.5%, https://directindex.org/r/cbb-charlotte.de); OASE Georgenstrasse (D 50.8%, https://directindex.org/r/cocktailoase-berlin.de); Newton Bar (F 34.3%, https://directindex.org/r/newton-bar.de); Tor Eins (F 15.4%, https://directindex.org/r/toreins-berlin.de).

With the three fixes above (No structured data for the business; Booking only through quandoo; Quandoo's terms ban bots and automated use, but a direct form on your own site has no such limit), the score would be about 100%, which would be first of 2,381 in Berlin cafes and bars.

## The direct record
What agents get for Château Kaputt, as JSON: https://directindex.org/api/direct/kaputt.berlin
- Book: none on record
- Order: none on record
- Menu: https://kaputt.berlin/CK_Karte.pdf (pdf; from the scan)
- Hours: none on record
- Phone: 0491 7621951494
- Stable links that count: https://directindex.org/go/kaputt.berlin/menu

## Can an agent transact?
Measured, not scored (the score stays at spec v1.0).
- 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, Quandoo: No. Quandoo's end-user terms (London, May 2018, section 3.3.1) bar robots, spiders, scrapers or any other automated means of access to the website for any purpose; the operator, Quandoo UK Limited, is in members' voluntary liquidation and the German company is in liquidation too. Read 2026-10-15: https://www.quandoo.co.uk/terms-conditions

## Score breakdown
| Component | Points | Available |
|---|---|---|
| Reachable | 23 | 25 |
| Readable | 4 | 25 |
| Actionable | 3 | 15 (the action test: pending) |
| Cited | 0 | 0 (the assistant citation check: pending) |

## Agent readiness (Cloudflare)
Level 0 of 5, Not Ready. Cloudflare's report: https://isitagentready.com/kaputt.berlin
- Link headers on the homepage: no (how: https://isitagentready.com/.well-known/agent-skills/link-headers/SKILL.md)
- sitemap.xml: no (how: https://isitagentready.com/.well-known/agent-skills/sitemap/SKILL.md)
- AI bot rules in robots.txt: no (how: https://isitagentready.com/.well-known/agent-skills/ai-rules/SKILL.md)
- Content Signals in robots.txt: no (how: https://isitagentready.com/.well-known/agent-skills/content-signals/SKILL.md)
- Markdown on Accept: text/markdown: no (how: https://isitagentready.com/.well-known/agent-skills/markdown-negotiation/SKILL.md)
- llms.txt: no (how: https://isitagentready.com/.well-known/agent-skills/llms-txt/SKILL.md)
- API catalog (RFC 9727): no (how: https://isitagentready.com/.well-known/agent-skills/api-catalog/SKILL.md)
- MCP server card: no (how: https://isitagentready.com/.well-known/agent-skills/mcp-server-card/SKILL.md)
- A2A agent card: no (how: https://isitagentready.com/.well-known/agent-skills/a2a-agent-card/SKILL.md)
- Agent Skills index: no (how: https://isitagentready.com/.well-known/agent-skills/agent-skills/SKILL.md)
- OAuth or OIDC discovery: no (how: https://isitagentready.com/.well-known/agent-skills/oauth-discovery/SKILL.md)
- OAuth protected resource metadata: no (how: https://isitagentready.com/.well-known/agent-skills/oauth-protected-resource/SKILL.md)
- auth.md: no (how: https://isitagentready.com/.well-known/agent-skills/auth-md/SKILL.md)
- Web Bot Auth key directory: no (how: https://isitagentready.com/.well-known/agent-skills/web-bot-auth/SKILL.md)
- ARD capability manifest: no (how: https://isitagentready.com/.well-known/agent-skills/ard/SKILL.md)
- DNS-AID records: no (how: https://isitagentready.com/.well-known/agent-skills/dns-aid/SKILL.md)
- WebMCP tools on the page: no (how: https://isitagentready.com/.well-known/agent-skills/webmcp/SKILL.md)
- JSON-LD for the business: no

Keep watching this business (https://directindex.org/r/kaputt.berlin/plan): the assistants are asked again every month, and you see what changed. 2 EUR a month or 19 EUR a year.
Deep report: https://directindex.org/r/kaputt.berlin/deep. Ten questions phrased the way people ask them, each assistant's full answer, the eight nearest similar places, the fix plan and a PDF. 5 EUR, paid once. Reading and scanning stay free. These few euros pay for the questions sent to the assistants and for the servers.
Methodology: https://directindex.org/methodology · Rescan now: https://directindex.org/scan?url=kaputt.berlin&force=1
