# Sweet Science: Agent-Direct Score B (72.3%)

Site: http://sweetsciencebklyn.com/
Report: https://directindex.org/r/sweetsciencebklyn.com
Scanned: 2026-10-23 (Provisional, with the action test and the assistant citation check still to come. The hatched part of the bar isn't measured yet.)
Sweet Science is mostly ready for agents.
An AI assistant can open Sweet Science's website. It can read what Sweet Science offers. It finds a way to book or order directly, through Toast.

## Direct links
- Order directly: https://www.toasttab.com/sweet-science-135-graham-ave/ (through toast acting for the business)
- Menu: http://www.sweetsciencebklyn.com/#quarantine-menu-grubhub-section
- Phone: +13477630872
- Address: 135 Graham Ave, 11206-2623, Brooklyn

## Nearby, also direct
Places near Sweet Science that take a booking or an order on their own website, with no marketplace in between.
- Manny's Detox Juice Bar and Grill (130 m): https://directindex.org/r/mannysjuicebar.com
- B'klyn Burro (150 m): https://directindex.org/r/bklynburro.com
- The Brooklyn Tree (150 m): https://directindex.org/r/thebrooklyntree.com
- Casa Ora (170 m): https://directindex.org/r/casaoranyc.com

## What to fix first
- **Structured data is incomplete.** (+7 points) Missing: address, telephone, opening hours. Guide: https://directindex.org/guides/structured-data-restaurant
- **No working HTTPS.** (+3 points) The page is only served over plain http. Browsers and agents rank it lower or refuse it.
- **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": "Sweet Science",
  "url": "http://sweetsciencebklyn.com/",
  "telephone": "+13477630872",
  "address": "135 Graham Ave, 11206-2623, Brooklyn",
  "geo": {
    "@type": "GeoCoordinates",
    "latitude": 40.70644735,
    "longitude": -73.94316845
  },
  "potentialAction": [
    {
      "@type": "OrderAction",
      "target": {
        "@type": "EntryPoint",
        "urlTemplate": "https://www.toasttab.com/sweet-science-135-graham-ave/",
        "actionPlatform": [
          "http://schema.org/DesktopWebPlatform",
          "http://schema.org/MobileWebPlatform"
        ]
      }
    }
  ]
}
</script>
```

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

```
# Sweet Science

> local business (comfort food) in 135 Graham Ave, 11206-2623, Brooklyn, New York. Phone +13477630872.

## Book or order directly

- Order: https://www.toasttab.com/sweet-science-135-graham-ave/ (through toast acting for the business)
- Menu: http://www.sweetsciencebklyn.com/#quarantine-menu-grubhub-section

## About

- Website: http://sweetsciencebklyn.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.
- **Ordering through toast on your own domain.** There's no marketplace commission, and the customer stays yours.
- **Toast works with agents through its partners.** Toast's guest terms could not be read on 2026-10-15 (bot challenge); since August 2026 Google's Ask Maps completes orders at Toast restaurants through Toast Local under the UCP for Food standard. Terms read on 2026-10-15: https://www.digitaltransactions.net/square-toast-jump-into-ai-boosted-google-maps/. 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
3324 of 11000 in New York. Top 30% 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 | 100% | yes |
| Publish the menu or price list as HTML | 95% | yes |
| Let AI crawlers in (no block at the server or in robots.txt) | 96% | yes |
| Structured data with address, phone and hours | 59% | no |
| Have an llms.txt | 25% | no |

Nearest places in the index: Alytori (F, 105 m, https://directindex.org/r/alytori.com); Win Son (F, 113 m, https://directindex.org/r/winsonbrooklyn.com); Manny's Detox Juice Bar and Grill (C, 134 m, https://directindex.org/r/mannysjuicebar.com); Marcela's TFC (C, 144 m, https://directindex.org/r/marcelasnyc.com); East Wick (F, 146 m, https://directindex.org/r/eastwickny.com); B'klyn Burro (B, 149 m, https://directindex.org/r/bklynburro.com); The Brooklyn Tree (D, 153 m, https://directindex.org/r/thebrooklyntree.com); Gentle Perch (F, 161 m, https://directindex.org/r/gentleperch.com); Casa Ora (A, 169 m, https://directindex.org/r/casaoranyc.com); Caridad China (F, 173 m, https://directindex.org/r/caridadchinarestaurant.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 13 everyday questions about New York and named 69 places. Sweet Science wasn't one of them. See who was named: https://directindex.org/city/new-york/recommended


Compared with its peers: Sites built with Squarespace 61% (41% A or B, 32150 sites); Sites using Toast 73% (62% A or B, 6097 sites); This site 72.3%.

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

## Businesses like Sweet Science in New York

| Group | Sites | Avg score | A or B | This site |
|---|---|---|---|---|
| Businesses of the same kind in New York | 11000 | 52% | 34% | 72.3% |
| Sites built with Squarespace in New York | 1237 | 70% | 52% | 72.3% |
| Sites using Toast in New York | 610 | 74% | 63% | 72.3% |
| Sites built with Squarespace and using Toast in New York | 125 | 77% | 74% | 72.3% |

The best of the sites built with Squarespace and using Toast in New York: Barrio Chino (A 93.8%, https://directindex.org/r/barriochinony.com); Mokbar (A 93.8%, https://directindex.org/r/mokbar.com); Plue (A 93.8%, https://directindex.org/r/pluenyc.com); Puertas (A 93.8%, https://directindex.org/r/puertasrestaurant.com); Beach Cafe (A 92.3%, https://directindex.org/r/thebeachcafe.com).

With the two fixes above (Structured data is incomplete; No working HTTPS), the score would be about 87.7%. That would be 1187th of 11,000 in New York, up from 3324th.

## The direct record
What agents get for Sweet Science, as JSON: https://directindex.org/api/direct/sweetsciencebklyn.com
- Book: none on record
- Order: https://www.toasttab.com/sweet-science-135-graham-ave/ (vendor on own site: Toast; found by the scan of 2026-10-23, not yet tested)
- Menu: http://www.sweetsciencebklyn.com/#quarantine-menu-grubhub-section (html_page; from the scan)
- Hours: none on record
- Phone: +13477630872
- Stable links that count: https://directindex.org/go/sweetsciencebklyn.com/order, https://directindex.org/go/sweetsciencebklyn.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 (Toast): yes
- Vendor terms for agents, Toast: Through partners. Toast's guest terms could not be read on 2026-10-15 (bot challenge); since August 2026 Google's Ask Maps completes orders at Toast restaurants through Toast Local under the UCP for Food standard. Read 2026-10-15: https://www.digitaltransactions.net/square-toast-jump-into-ai-boosted-google-maps/

## Score breakdown
| Component | Points | Available |
|---|---|---|
| Reachable | 22 | 25 |
| Readable | 15 | 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/sweetsciencebklyn.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/sweetsciencebklyn.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/sweetsciencebklyn.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=sweetsciencebklyn.com&force=1
