# Amélie: Agent-Direct Score C (67.7%)

Site: http://sfamelie.com/
Report: https://directindex.org/r/sfamelie.com
Scanned: 2026-10-24 (Provisional, with the action test and the assistant citation check still to come. The hatched part of the bar isn't measured yet.)
Amélie is partly visible to agents.
An AI assistant can open Amélie's website. It can read what Amélie offers. To book or order, it is sent to Resy, a marketplace.

## Direct links
- Menu: https://www.sfamelie.com/menu-1
- Phone: 4152926916
- Address: Polk Street 1754 San Francisco

## Nearby, also direct
Places near Amélie that take a booking or an order on their own website, with no marketplace in between.
- The Crepe House (30 m): https://directindex.org/r/thecrepehouse.com
- It's A Grind Coffee House (30 m): https://directindex.org/r/itsagrind.com
- Dokkaebier (40 m): https://directindex.org/r/enjoydkb.com
- Upfordayz Cafe & Bakery (50 m): https://directindex.org/r/upfordayz.com
- Harper & Rye (100 m): https://directindex.org/r/harperandrye.com

## What to fix first
- **Booking only through resy.** (+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
- **Structured data is incomplete.** (+6 points) Missing: address, telephone, opening hours. Guide: https://directindex.org/guides/structured-data-restaurant
- **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": "BarOrPub",
  "name": "Amélie",
  "url": "http://sfamelie.com/",
  "telephone": "4152926916",
  "address": {
    "@type": "PostalAddress",
    "streetAddress": "Polk Street 1754",
    "addressLocality": "San Francisco"
  },
  "geo": {
    "@type": "GeoCoordinates",
    "latitude": 37.7931005,
    "longitude": -122.421082
  },
  "hasMenu": "https://www.sfamelie.com/menu-1"
}
</script>
```

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

```
# Amélie

> bar or pub in Polk Street 1754 San Francisco, San Francisco cafes and bars. Phone 4152926916.

## Book or order directly

- Menu: https://www.sfamelie.com/menu-1

## About

- Website: http://sfamelie.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 main AI user agents.
- **AI crawlers get the page.** GPTBot, ClaudeBot and PerplexityBot all got a normal response.
- **Structured data found (LocalBusiness).** no address, phone or hours in it
- **Menu or price list is an HTML page.** Agents can read the items and prices.
- **Resy works with agents through its partners.** Resy's terms (9 June 2025) bar automated software that crawls, harvests or scrapes the service and require written consent for other automated use; Resy opened bookings inside ChatGPT on 10 August 2026. Terms read on 2026-10-15: https://resy.com/terms. An assistant that isn't a partner may not be able to finish there. A direct path on your own domain works for all of them.

## Where it stands
274 of 1053 in San Francisco cafes and bars. Top 26% 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 | 98% | no |
| Publish the menu or price list as HTML | 83% | yes |
| Let AI crawlers in (no block at the server or in robots.txt) | 98% | yes |
| Structured data with address, phone and hours | 32% | no |
| Have an llms.txt | 25% | no |

Nearest places in the index: Polkcha (F, 11 m, https://directindex.org/r/polkcha.com); The Crepe House (C, 25 m, https://directindex.org/r/thecrepehouse.com); It's A Grind Coffee House (C, 33 m, https://directindex.org/r/itsagrind.com); Dokkaebier (B, 39 m, https://directindex.org/r/enjoydkb.com); Upfordayz Cafe & Bakery (A, 53 m, https://directindex.org/r/upfordayz.com); Harper & Rye (B, 96 m, https://directindex.org/r/harperandrye.com); Kozy Kar (F, 196 m, https://directindex.org/r/kozykar.com); Sidewalk Café (C, 233 m, https://directindex.org/r/cheeseplus.com); Kutch Wines (D, 274 m, https://directindex.org/r/kutchwines.com); Souvenir Coffee (C, 278 m, https://directindex.org/r/souvenir-coffee.com).

## 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.

The assistants were asked 12 everyday questions about San Francisco cafes and bars and named 66 places. Amélie wasn't one of them. See who was named: https://directindex.org/city/san-francisco-cafes-bars/recommended


Compared with its peers: Sites built with Squarespace 61% (41% A or B, 32150 sites); Sites using Resy 67% (44% A or B, 2728 sites); This site 67.7%.

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

## Businesses like Amélie in San Francisco cafes and bars

| Group | Sites | Avg score | A or B | This site |
|---|---|---|---|---|
| Businesses of the same kind in San Francisco cafes and bars | 1053 | 48% | 24% | 67.7% |
| Sites built with Squarespace in San Francisco cafes and bars | 239 | 66% | 42% | 67.7% |
| Sites using Resy in San Francisco cafes and bars | 15 | 71% | 53% | 67.7% |
| Sites built with Squarespace and using Resy in San Francisco cafes and bars | 9 | 71% | 56% | 67.7% |

The best of the sites built with Squarespace and using Resy in San Francisco cafes and bars: Left Door (A 85%, https://directindex.org/r/leftdoor.com); Harrington's Bar & Grill (B 81.5%, https://directindex.org/r/harringtonssf.com); Arcana (B 78.8%, https://directindex.org/r/arcanasf.com); Cavaña (B 73.8%, https://directindex.org/r/cavanasf.com); The Snug (B 73.8%, https://directindex.org/r/thesnugsf.com).

With the two fixes above (Booking only through resy; Structured data is incomplete), the score would be about 95.4%. That would be 6th of 1,053 in San Francisco cafes and bars, up from 274th.

## The direct record
What agents get for Amélie, as JSON: https://directindex.org/api/direct/sfamelie.com
- Book: none on record
- Order: none on record
- Menu: https://www.sfamelie.com/menu-1 (html_page; from the scan)
- Hours: none on record
- Phone: 4152926916
- Stable links that count: https://directindex.org/go/sfamelie.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, Resy: Through partners. Resy's terms (9 June 2025) bar automated software that crawls, harvests or scrapes the service and require written consent for other automated use; Resy opened bookings inside ChatGPT on 10 August 2026. Read 2026-10-15: https://resy.com/terms

## Score breakdown
| Component | Points | Available |
|---|---|---|
| Reachable | 25 | 25 |
| Readable | 16 | 25 |
| Actionable | 3 | 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/sfamelie.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: yes

Keep watching this business (https://directindex.org/r/sfamelie.com/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/sfamelie.com/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=sfamelie.com&force=1
