# Pouliche: Agent-Direct Score C (61.1%)

Site: https://www.poulicheparis.com/
Report: https://directindex.org/r/poulicheparis.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.)
Pouliche is partly visible to agents.

## Direct links
- Book directly: https://bookings.zenchef.com/results?rid=353381&fullscreen&lang=fr (through zenchef acting for the business)
- Menu: https://www.poulicheparis.com/
- Phone: +33 1 45 89 07 56

## What to fix first
- **No structured data for the business.** (+14 points) Add schema.org JSON-LD for the business (Restaurant, LocalBusiness or the closest type, with name, address, telephone and openingHoursSpecification, plus servesCuisine and acceptsReservations). It is the one block every assistant reads first; the fix kit below has it filled in. Guide: https://directindex.org/guides/structured-data-restaurant
- **The server turns AI crawlers away at the door.** (+3.3 points) Live fetches as PerplexityBot (cloudflare_challenge) 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. Guide: https://directindex.org/guides/blocking-ai-crawlers-without-knowing
- **No llms.txt.** (no points, still worth doing) Optional today, cheap to add: a short text file describing the business for language models. Guide: https://directindex.org/guides/llms-txt-for-a-business

## 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": "Restaurant",
  "name": "Pouliche",
  "url": "https://www.poulicheparis.com/",
  "telephone": "+33 1 45 89 07 56",
  "email": "contact@poulicheparis.com",
  "address": {
    "@type": "PostalAddress",
    "streetAddress": "Rue d'Enghien 11"
  },
  "geo": {
    "@type": "GeoCoordinates",
    "latitude": 48.8717154,
    "longitude": 2.3522617
  },
  "servesCuisine": [
    "french"
  ],
  "acceptsReservations": "https://bookings.zenchef.com/results?rid=353381&amp;fullscreen&amp;lang=fr",
  "hasMenu": "https://www.poulicheparis.com/",
  "potentialAction": [
    {
      "@type": "ReserveAction",
      "target": {
        "@type": "EntryPoint",
        "urlTemplate": "https://bookings.zenchef.com/results?rid=353381&amp;fullscreen&amp;lang=fr",
        "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.

```
# Pouliche

> restaurant (french) in Rue d'Enghien 11, Paris. Phone +33 1 45 89 07 56.

## Book or order directly

- Book: https://bookings.zenchef.com/results?rid=353381&amp;fullscreen&amp;lang=fr (through zenchef acting for the business)
- Menu: https://www.poulicheparis.com/

## About

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

## Already right
- **robots.txt lets AI crawlers in.** No rule blocks the key AI user agents.
- **Menu or price list is an HTML page.** Agents can read items and prices directly.
- **Booking through zenchef on your own domain.** No marketplace commission, and the guest stays yours.
- **Zenchef works with agents through its partners.** Zenchef's website terms (19 February 2024) forbid robots, scripts or automated systems that extract content and forbid crawling or scraping; agents book only through partner integrations a restaurant enables. Read 2026-10-15: https://www.zenchef.com/terms-conditions. An assistant that is not a partner may not finish the step there; a direct path on your own domain works for all of them.

## Since the scan of 2026-10-14 (F then)
- Fixed: The site could not be read at all
- New: The server turned AI crawlers away at the door; No structured data for the business; No llms.txt

## Where it stands
1540 of 2889 in Paris. Top 53% 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% | yes |
| Publish the menu or price list as HTML | 98% | yes |
| Let AI crawlers in (no edge block, no robots.txt block) | 100% | no |
| Structured data with address, phone and hours | 88% | no |
| Have an llms.txt | 65% | no |

Nearest places with a similar menu: Brasserie Floderer (A, 96 m, https://directindex.org/r/floderer-paris.com); Marie Belle (C, 322 m, https://directindex.org/r/mariebelleparis.fr); Dante (A, 357 m, https://directindex.org/r/danterestaurant.info); L'Appartement Saint-Martin (F, 380 m, https://directindex.org/r/we-eats.com); L'Alsacien (B, 490 m, https://directindex.org/r/lalsacien.com); Elbi (B, 497 m, https://directindex.org/r/restaurantelbi.fr); La Tarte au carré (C, 511 m, https://directindex.org/r/latarteaucarre.com); L’Altro Frenchie (C, 558 m, https://directindex.org/r/altro-frenchie.com); Milo (A, 562 m, https://directindex.org/r/brasseriemilo.fr); Folie's Café (B, 598 m, https://directindex.org/r/folies-cafe-paris.fr).

## 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.

Against its peers: Sites built with Wix 58% (35% A or B, 3255 sites); Sites using Zenchef 76% (63% A or B, 829 sites); This site 61.1%.

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

## Businesses like Pouliche in Paris

| Group | Sites | Avg score | A or B | This site |
|---|---|---|---|---|
| Same kind in Paris | 2889 | 59% | 41% | 61.1% |
| Built with Wix in Paris | 138 | 56% | 32% | 61.1% |
| Using Zenchef in Paris | 383 | 79% | 72% | 61.1% |
| Built with Wix and using Zenchef in Paris | 23 | 61% | 43% | 61.1% |

The best of Built with Wix and using Zenchef in Paris: Café A (A 87.7%, https://directindex.org/r/cafea.fr); Gangnam (A 87.7%, https://directindex.org/r/gangnamparis.com); Le Bouche à Oreille (A 87.7%, https://directindex.org/r/le-bouche-a-oreille.fr); Relais Odéon (A 87.7%, https://directindex.org/r/relaisodeon.com); Comer (B 83.1%, https://directindex.org/r/parismexico.fr).

With the two fixes above (No structured data for the business; The server turns AI crawlers away at the door) the score would be about 87.7%: 335th of 2,889 in Paris, up from 1540th.

## The direct record
What agents get for Pouliche, as JSON: https://directindex.org/api/direct/poulicheparis.com
- Book: https://bookings.zenchef.com/results?rid=353381&amp;fullscreen&amp;lang=fr (vendor on own site: Zenchef; found by the scan of 2026-10-15, not yet tested)
- Order: none on record
- Menu: https://www.poulicheparis.com/ (html_page; from the scan)
- Hours: none on record
- Phone: +33 1 45 89 07 56
- Stable links that count: https://directindex.org/go/poulicheparis.com/book, https://directindex.org/go/poulicheparis.com/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, Zenchef: Through partners. Zenchef's website terms (19 February 2024) forbid robots, scripts or automated systems that extract content and forbid crawling or scraping; agents book only through partner integrations a restaurant enables. Read 2026-10-15: https://www.zenchef.com/terms-conditions

## Score breakdown
| Component | Points | Available |
|---|---|---|
| Reachable | 21.7 | 25 |
| Readable | 8 | 25 |
| Actionable | 10 | 15 (the action test: pending) |
| Cited | 0 | 0 (the assistant citation check: pending) |

## Agent readiness (Cloudflare)
Level 1 of 5, Basic Web Presence. Cloudflare's report: https://isitagentready.com/poulicheparis.com
- Link headers on the homepage: no (how: https://isitagentready.com/.well-known/agent-skills/link-headers/SKILL.md)
- sitemap.xml: yes
- AI bot rules in robots.txt: yes
- 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/poulicheparis.com/plan): the assistants asked again every month, with what changed; 2 EUR a month or 19 EUR a year.
Deep report: https://directindex.org/r/poulicheparis.com/deep. Ten questions the way people ask, each assistant's full answer, the eight nearest similar places, the fix plan and a PDF: 5 EUR, one-off. 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=poulicheparis.com&force=1