# Odette: Agent-Direct Score C (61.5%)

Site: https://www.odette-paris.com/fr/
Report: https://directindex.org/r/odette-paris.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.)
Odette is partly visible to agents.
An AI assistant can open the website of Odette. It finds no menu or price list, so it answers from other sites. It finds a way to book or order directly on the site.

## Direct links
- Order directly: https://www.odette-paris.com/fr/5boites-de-choux (on the business's own site)

## What to fix first
- **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). 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
- **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
- **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": "CafeOrCoffeeShop",
  "name": "Odette",
  "url": "https://www.odette-paris.com/fr/",
  "address": {
    "@type": "PostalAddress",
    "streetAddress": "Rue Galande 77"
  },
  "geo": {
    "@type": "GeoCoordinates",
    "latitude": 48.8520433,
    "longitude": 2.3465062
  },
  "openingHours": "Mo, Th, Fr 11:00-19:00; Sa, Su 11:00-20:00; Tu, We 12:00-19:00",
  "servesCuisine": [
    "Cream Puffs and Tea"
  ],
  "potentialAction": [
    {
      "@type": "OrderAction",
      "target": {
        "@type": "EntryPoint",
        "urlTemplate": "https://www.odette-paris.com/fr/5boites-de-choux",
        "actionPlatform": [
          "http://schema.org/DesktopWebPlatform",
          "http://schema.org/MobileWebPlatform"
        ]
      }
    }
  ]
}
</script>
```

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

```
# Odette

> cafe or coffee shop (Cream Puffs and Tea) in Rue Galande 77, Paris cafes and bars.

## Book or order directly

- Order: https://www.odette-paris.com/fr/5boites-de-choux (on the business's own site)

## Opening hours

Mo, Th, Fr 11:00-19:00; Sa, Su 11:00-20:00; Tu, We 12:00-19:00

## About

- Website: https://www.odette-paris.com/fr/
- 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.
- **AI crawlers get the page.** GPTBot, ClaudeBot and PerplexityBot all received a normal response.
- **Ordering on your own site.** Agents can order without a marketplace in the loop.

## Since the scan of 2026-10-14 (F then)
- Fixed: No booking or ordering path at all
- New: nothing

## Where it stands
389 of 772 in Paris cafes and bars. Top 50% 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 | 99% | yes |
| Publish the menu or price list as HTML | 92% | no |
| Let AI crawlers in (no edge block, no robots.txt block) | 100% | yes |
| Structured data with address, phone and hours | 58% | no |
| Have an llms.txt | 42% | no |

Nearest places in the index: Caveau des Oubliettes (C, 17 m, https://directindex.org/r/caveau-des-oubliettes.com); Aux Trois Mailletz (F, 17 m, https://directindex.org/r/lestroismailletz.fr); Shakespeare and Company Café (F, 77 m, https://directindex.org/r/shakespeareandcompany.com); Café Panis (B, 138 m, https://directindex.org/r/cafepanis.com); RoadHouse (D, 153 m, https://directindex.org/r/roadhouse.paris); Le Privé (D, 153 m, https://directindex.org/r/lepriveparis.com); Café Gisèle (A, 188 m, https://directindex.org/r/cafe-gisele.com); Le Lutèce (B, 231 m, https://directindex.org/r/leluteceparis.fr); The Long Hop (A, 251 m, https://directindex.org/r/the-long-hop.com); Le Saint Mich' (F, 281 m, https://directindex.org/r/lesaintmich.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.

Score over 2 scans since 2026-10-14: 2026-10-14 39%, 2026-10-15 62%.

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

## Businesses like Odette in Paris cafes and bars

| Group | Sites | Avg score | A or B | This site |
|---|---|---|---|---|
| Businesses of the same kind in Paris cafes and bars | 772 | 55% | 38% | 61.5% |

The best of the businesses of the same kind in Paris cafes and bars: 5 Pailles (A 100%, https://directindex.org/r/5pailles.com); Brasserie Valma (A 100%, https://directindex.org/r/brasserie-valma.fr); Cafe Français (A 100%, https://directindex.org/r/cafe-francais.fr); Café Gisèle (A 100%, https://directindex.org/r/cafe-gisele.com); La Belle Équipe (A 100%, https://directindex.org/r/labelleequipecharonne.fr).

With the two fixes above (No structured data for the business; No menu or price list found) the score would be about 95.4%: 14th of 772 in Paris cafes and bars, up from 389th.

## The direct record
What agents get for Odette, as JSON: https://directindex.org/api/direct/odette-paris.com
- Book: none on record
- Order: https://www.odette-paris.com/fr/5boites-de-choux (own site; found by the scan of 2026-10-15, not yet tested)
- Menu: none on record
- Hours: Mo, Th, Fr 11:00-19:00; Sa, Su 11:00-20:00; Tu, We 12:00-19:00 (closed now) (from OpenStreetMap)
- Phone: none on record
- Stable links that count: https://directindex.org/go/odette-paris.com/order

## 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

## Score breakdown
| Component | Points | Available |
|---|---|---|
| Reachable | 25 | 25 |
| Readable | 0 | 25 |
| Actionable | 15 | 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/odette-paris.com
- 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: 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/odette-paris.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/odette-paris.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=odette-paris.com&force=1
