# Juicebaby: Agent-Direct Score F (12.3%)

Site: https://www.juicebaby.co.uk/index/
Report: https://directindex.org/r/juicebaby.com
Scanned: 2026-10-15 (Provisional: the action test and the assistant citation check still to come; the hatched part of the bar is not measured yet.)
Juicebaby is largely invisible to agents.

## Direct links
- Phone: +44 20 7221 2144

## What to fix first
- **The site turns every visitor without a browser away, AI agents included.** (+25 points) A plain fetch was refused (cloudflare_challenge); only a real browser got the page. Every AI crawler and agent is turned away the same way, so Reachable scores 0 and the rest is measured on the rendered page. Ask the host to let the AI user agents through. Guide: https://directindex.org/guides/blocking-ai-crawlers-without-knowing
- **No booking or ordering path at all.** (+15 points) Agents have nothing to act on. Add a booking or ordering page on your own domain. Guide: https://directindex.org/guides/book-direct-on-your-own-website
- **Structured data is incomplete.** (+7 points) Missing: address, telephone, opening hours. Guide: https://directindex.org/guides/structured-data-restaurant
- **No menu or price list found.** (+7 points) Agents answer 'what do they offer' from marketplaces instead. Add a menu or price list page and link it from the homepage. Guide: https://directindex.org/guides/menu-pdf-ai

## Fix kit: What to paste

Structured data (JSON-LD). One block in the page's head, or in the builder's custom-code slot. Replace anything that is wrong.

```html
<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "BarOrPub",
  "name": "Juicebaby",
  "url": "https://www.juicebaby.co.uk/index/",
  "telephone": "+44 20 7221 2144",
  "address": {
    "@type": "PostalAddress",
    "streetAddress": "Westbourne Grove 181",
    "addressLocality": "London"
  },
  "geo": {
    "@type": "GeoCoordinates",
    "latitude": 51.5145861,
    "longitude": -0.1980214
  }
}
</script>
```

## Already right
- **robots.txt lets AI crawlers in.** There is no robots.txt, which allows everything.
- **Structured data present (Organization).** but without address, phone or hours

## Since the scan of 2026-10-14 (D then)
- Fixed: nothing
- New: The site turned every visitor without a browser away

## Where it stands
1965 of 2491 in London cafes and bars. Top 79% of the sites scanned in this index.

| What the top tenth of the index does | Top 10% | This site |
|---|---|---|
| Take bookings or orders on their own domain | 100% | no |
| Publish the menu or price list as HTML | 96% | no |
| Let AI crawlers in (no edge block, no robots.txt block) | 97% | no |
| Structured data with address, phone and hours | 67% | no |
| Have an llms.txt | 12% | no |

Nearest places in the index: The Cock and Bottle (B, 98 m, https://directindex.org/r/cockandbottlew11.com); The Prince Bonaparte (B, 357 m, https://directindex.org/r/theprincebonapartew2.co.uk); The Prince Edward (F, 360 m, https://directindex.org/r/theprince-edward.co.uk); Sun in Splendour (B, 406 m, https://directindex.org/r/suninsplendourpub.co.uk); The Butter Bakery (F, 418 m, https://directindex.org/r/google.com); Milk Cool (F, 440 m, https://directindex.org/r/milkcool.co.uk); Trailer Happiness (A, 459 m, https://directindex.org/r/trailerh.com); The Hill Cafe (C, 468 m, https://directindex.org/r/hillcafe.co.uk); The Hayden (C, 470 m, https://directindex.org/r/haydennottinghill.com); Alounak Express (D, 471 m, https://directindex.org/r/alounakrestaurant.co.uk).

## What assistants answer
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.

Score over 2 scans since 2026-10-14: 2026-10-14 51%, 2026-10-15 12%.

Against its peers: Sites built with Shopify 58% (37% A or B, 1345 sites); This site 12.3%.

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

Read by AI agents 7 times this month.

## Businesses like Juicebaby in London cafes and bars

| Group | Sites | Avg score | A or B | This site |
|---|---|---|---|---|
| Same kind in London cafes and bars | 2491 | 52% | 37% | 12.3% |
| Built with Shopify in London cafes and bars | 59 | 54% | 44% | 12.3% |

The best of Built with Shopify in London cafes and bars: Kipferl Cafe & Kitchen (A 96.3%, https://directindex.org/r/kipferl.co.uk); Peggy Porschen Belgravia (A 90.8%, https://directindex.org/r/peggyporschen.com); Kybelle (A 90%, https://directindex.org/r/kybelle.co.uk); The Bike Shed (A 86.2%, https://directindex.org/r/bikeshedmoto.co.uk); Bears Ice Cream Company (B 84.6%, https://directindex.org/r/bearsicecream.co.uk).

With the three fixes above (The site turns every visitor without a browser away, AI agents included; No booking or ordering path at all; Structured data is incomplete) the score would be about 84.6%: 316th of 2,491 in London cafes and bars, up from 1965th.

## The direct record
What agents get for Juicebaby, as JSON: https://directindex.org/api/direct/juicebaby.com
- Book: none on record
- Order: none on record
- Menu: none on record
- Hours: none on record
- Phone: +44 20 7221 2144

## 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

Only a real browser got this page (a plain fetch got cloudflare_challenge); Readable and Actionable were measured on the rendered page.

## Score breakdown
| Component | Points | Available |
|---|---|---|
| Reachable | 0 | 25 |
| Readable | 8 | 25 |
| Actionable | 0 | 15 (the action test: pending) |
| Cited | 0 | 0 (the assistant citation check: pending) |

## Agent readiness (Cloudflare)
Not measured for this scan.
- JSON-LD for the business: yes

Deep report: https://directindex.org/r/juicebaby.com/deep. 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.
Methodology: https://directindex.org/methodology · Rescan now: https://directindex.org/scan?url=juicebaby.com&force=1