# separé: Agent-Direct Score C (69.7%)

Site: https://separe-mikulandska.cz
Report: https://directindex.org/r/separe-mikulandska.cz
Scanned: 2026-10-14 (Provisional: the action test and the assistant citation check still to come; the hatched part of the bar is not measured yet.)
separé is partly visible to agents.
Some AI assistants are turned away by the website of separé. It finds no menu or price list, so it answers from other sites. It finds a way to book or order directly, through separe.choiceqr.com.

## Direct links
- Phone: +420 722 339 488

## What to fix first
- **Booking through an unrecognised third party.** (+9 points) Check that the provider keeps you as the merchant of record. Guide: https://directindex.org/guides/book-direct-on-your-own-website
- **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
- **robots.txt blocks GPTBot, ClaudeBot, Google-Extended.** (+3.7 points) These are the crawlers behind ChatGPT, Claude, Perplexity and Google's AI features. Remove the Disallow lines for them, or add explicit Allow rules. Guide: https://directindex.org/guides/robots-txt-for-ai-agents

## Fix kit: What to paste

robots.txt. Add these lines to /robots.txt and delete any Disallow rule that names these crawlers.

```
# Let AI assistants read the site: they send people to you; a marketplace keeps them.
# Remove any Disallow lines for these names elsewhere in this file.
User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Perplexity-User
Allow: /
```

## Already right
- **AI crawlers get the page.** GPTBot, ClaudeBot and PerplexityBot all received a normal response.
- **Structured data present (BarOrPub).** address, phone, opening hours

## Where it stands
75 of 545 in Prague cafes and bars. Top 14% 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 | 78% | no |
| Publish the menu or price list as HTML | 73% | no |
| Let AI crawlers in (no edge block, no robots.txt block) | 89% | no |
| Structured data with address, phone and hours | 29% | yes |
| Have an llms.txt | 38% | yes |

Nearest places in the index: Café Jericho (D, 83 m, https://directindex.org/r/cafejericho.cz); PATE (D, 119 m, https://directindex.org/r/patebakery.cz); Národní kavárna (C, 171 m, https://directindex.org/r/narodnikavarna.cz); Café Rybka (C, 180 m, https://directindex.org/r/rybkapub.cz); Vzorkovna (Dog bar) (C, 181 m, https://directindex.org/r/vzorkovna.biz); Q café (D, 183 m, https://directindex.org/r/q-cafe.cz); Kafe v Klidu (B, 195 m, https://directindex.org/r/kafevklidu.cz); The Dutch Pub (C, 203 m, https://directindex.org/r/dutchpub.cz); My Bistro & Cafe (C, 219 m, https://directindex.org/r/mybistrocafe.cz); Ebel Coffee Farm (B, 231 m, https://directindex.org/r/ebelcoffee.cz).

## 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.

See what an AI agent reads on this site: https://directindex.org/r/separe-mikulandska.cz/agent-view

## Businesses like separé in Prague cafes and bars

| Group | Sites | Avg score | A or B | This site |
|---|---|---|---|---|
| Businesses of the same kind in Prague cafes and bars | 545 | 48% | 13% | 69.7% |

The best of the businesses of the same kind in Prague cafes and bars: Sladká Cesta (A 100%, https://directindex.org/r/sladkacesta.cz); ALIBI (A 96.3%, https://directindex.org/r/alibi-bar.cz); Cacao (A 95.4%, https://directindex.org/r/cacaoprague.cz); Hospůdka Sokol (A 95.4%, https://directindex.org/r/restauracesokol.cz); Lavish Lounge (A 95.4%, https://directindex.org/r/lavish-lounge.cz).

With the three fixes above (Booking through an unrecognised third party; No menu or price list found; robots.txt blocks GPTBot, ClaudeBot, Google-Extended) the score would be about 100%: first of 545 in Prague cafes and bars.

## The direct record
What agents get for separé, as JSON: https://directindex.org/api/direct/separe-mikulandska.cz
- Book: none on record
- Order: none on record
- Menu: none on record
- Hours: Mo-Fr 17:00-00:00; Sa 17:00-00:00 (closed now) (from OpenStreetMap)
- Phone: +420 722 339 488

## 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): not measured
- ACP discovery document (/.well-known/acp.json, OpenAI and Stripe's Agentic Commerce Protocol): not measured
- 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): not measured

Not measured at this scan; the next scan measures it.

## Score breakdown
| Component | Points | Available |
|---|---|---|
| Reachable | 21.3 | 25 |
| Readable | 18 | 25 |
| Actionable | 6 | 15 (the action test: pending) |
| Cited | 0 | 0 (the assistant citation check: pending) |

## Agent readiness (Cloudflare)
Level 2 of 5, Bot-Aware. Cloudflare's report: https://isitagentready.com/separe-mikulandska.cz
- 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: yes
- Markdown on Accept: text/markdown: no (how: https://isitagentready.com/.well-known/agent-skills/markdown-negotiation/SKILL.md)
- llms.txt: yes
- 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/separe-mikulandska.cz/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/separe-mikulandska.cz/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=separe-mikulandska.cz&force=1