The Direct Index
Report · Durban · scanned 2026-11-14

Lord Prawn Fish and Grill

lordprawnumhlanga.co.za is hard for agents to use.

Listed by Overture Maps.

MenuCallWebsite

What agents are told

Its menu mentions: a lunch or set menu

Read by AI agents 10 times this month (GPTBot 10). The crawlers behind the assistants read this page when they answer questions about the business.

Assistants

Why the assistants send people elsewhere

One sentence on why

2026-11-15 ChatGPT and Gemini sent users to third-party platforms like Uber Eats and Mr D because the server blocks AI crawlers and the website provides no direct online ordering system of its own.

A model wrote this from the stored answers and the scan's facts, and nothing else. The answers themselves are quoted below, under "What assistants answer".

Assistants

What assistants answer

Each assistant gets three questions about this business: the official website, where to book and where to order. Each cell shows where the answer sent people.

AssistantOfficial website?Where to book?Where to order?
ChatGPTown siteown sitemarketplace: ubereats
Geminiown siteown sitemarketplace: ubereats

Asked on 2026-11-15 with web search on. 67% of the answers pointed to the business's own site or to a vendor working for it. That share is the Cited part of the score.

Named in none of the 44 answers to 22 everyday questions about Durban.

Named instead

In the answers that didn't name Lord Prawn Fish and Grill, the places named most often, and in how many answers.

See who was named →

What ChatGPT said 2026-11-15, three questions

Official website?
https://lordprawnumhlanga.co.za/ (lordprawnumhlanga.co.za (https://lordprawnumhlanga.co.za/wp-content/uploads/2025/09/Lp-menu-2025.pdf?utmsource=openai))

Where to book?
Book online through Lord Prawn’s website: lordprawnumhlanga.co.za (https://lordprawnumhlanga.co.za/) (wanderlog.com (https://wanderlog.com/place/details/2802596/lord-prawn-fish--grill?utmsource=openai))

Where to order?
Order Lord Prawn through Uber Eats: https://www.ubereats.com/za/store/lord-prawn/nbfsxezxRMWiOvcLFju0w (https://www.ubereats.com/za/store/lord-prawn/nbfsxezxRMWiOvcLFju0w) (ubereats.com…

What Gemini said 2026-11-15, three questions

Official website?
The official website for Lord Prawn Fish and Grill, a restaurant in Durban, South Africa, is www.lordprawnumhlanga.co.za.

Where to book?
You can book a table at Lord Prawn Fish and Grill by using the booking system available on the FindMy website. You can find their page and booking option here: https://www.findmy.co.za/companies/lord-prawn-fish-grill-umhlanga-rocks-durban-110006.html Alternatively, you can visit the official Lord Prawn Umhlanga website, which has a "Contact Us" section for inquiries: https://www.lordprawnumhlanga.co.za/

Where to order?
You can order food online from Lord Prawn Fish and Grill in Durban, South Africa, through the following delivery platforms: Uber Eats: https://www.ubereats.com/za/store/lord-prawn/C0f9rK7uT3mJ59kM7VptA (https://www.ubereats.com/za/store/lord-prawn/C0f9rK7uT3mJ59kM7VptA) Mr D: https://www.mrdfood.com/durban/restaurants/lord-prawn-umhlanga-rocks/72007…

Owners

The website's grade

An AI assistant can open Lord Prawn Fish and Grill's website. It can read what Lord Prawn Fish and Grill offers. It finds a link to book or order on another site, order.mrdfood.com, which the scanner doesn't recognise.

52.7%

29 of 55 points available

1/5

agent-readiness level, Basic Web Presence

4

things to fix

Scored on what the scan measures for every site, the same way for everyone. The action test and what the assistants answer are shown beside the score, never in it (specification 1.1, 18 November 2026).

Who can read the site, by kind of agent
Kind of agentWhat the scan sawIn the score
Search crawlers (OAI-SearchBot, Claude-SearchBot, PerplexityBot)let in by robots.txt10 points, the two rows together
Fetchers that read a page for a person (ChatGPT-User, Claude-User, Perplexity-User)let in by robots.txt10 points, the two rows together
Training crawlerslet in by robots.txtnot scored
Requests under crawler names from Cloudflare's networkrefused: GPTBot, PerplexityBotnot scored
The scanner's own signed requestgot the page2 points: the text without JavaScript

See what an AI agent reads on this site →

Where it stands

How Lord Prawn Fish and Grill compares

Where it stands

126 of 283 in Durban

Ahead of 55% of the other sites scanned in this index.

What the top 10% of the index doesTop 10%This site
Take bookings or orders on their own domain93%no
Publish the menu or price list as HTML97%yes
Let the assistants in (robots.txt)100%yes
Structured data with address, phone and hours27%no
Have an llms.txt33%no

Compared with its peers

Average scoreA or BThis site
Sites built with WordPress 276,714 sites53%22%52.7%
Businesses like yours

Businesses like Lord Prawn Fish and Grill in Durban

GroupSitesAvg scoreA or BThis site
Businesses of the same kind in Durban28347%17%52.7%
Sites built with WordPress in Durban14556%21%52.7%

After the top fixes

With the two fixes above (No structured data for the business; Ordering through an unrecognised third party), the score would be about 95%. Against today's scores in Durban, that would rank about 5th of 283 (it is 126th today). The others' scores move too, so this is an estimate.

Findings

What to fix first

  1. No structured data for the business +14 points no_structured

    Add schema.org JSON-LD for the business (Restaurant, LocalBusiness or the closest type, with name, address, telephone and openingHoursSpecification, plus servesCuisine and acceptsReservations). Every assistant reads this block first, and the fix kit below has it filled in. How to fix it

    Passes when the home page has schema.org JSON-LD that names the business and its type. Recheck it

  2. Ordering through an unrecognised third party +9 points ordering_other

    Check that the provider keeps your business as the seller of record. How to fix it

    Passes when the home page links an ordering page on the site's own domain, or ordering software the scanner knows. Recheck it

  3. Requests under AI crawler names were turned away not scored, worth checking edge_blocks

    Requests from Cloudflare's network naming themselves GPTBot (http_429), PerplexityBot (http_429) were refused, while a browser got the page. The real crawlers come from their companies' addresses, and a host that checks the address lets them in, so this alone does not show that assistants are refused. Measured, not scored. If assistants can't read the site, ask the host which crawlers it lets in. How to fix it

    Passes when requests named GPTBot, ClaudeBot and PerplexityBot get the page the way a browser does (not scored). Recheck it

  4. No llms.txt no points, but worth doing no_llms_txt

    Optional for now and cheap to add. It's a short text file that describes the business for language models. How to fix it

    Passes when /llms.txt answers with a short text file (not scored). Recheck it

Send the fixes to your web person

One email with the fixes and the link. Nothing is stored.

Already right

  • robots.txt lets the assistants in No rule blocks the main AI user agents.
  • Menu or price list is an HTML page Agents can read the items and prices.

Builder: wordpress · contact page /contact-us/: nothing new; menu page /our-menu/: nothing new · What to paste

Owners

Own this business?

Own this business? Claim it, correct what agents are told, recheck a fix, or hand the list to your assistant: For the owner

For developers and agents

What agents get, and what the site publishes

The direct record agents get for this business, the rails an agent could transact through, and the agent standards the site publishes. Show the details