The Direct Index
Report · Christchurch · scanned 2026-11-13

Gunpowder Indian Restaurant & Bar - Christchurch City

gunpowdercity.co.nz is mostly ready for agents.

Listed by Overture Maps.

MenuCallWebsite

What agents are told

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.

The assistants haven't been asked about this business by name yet. They're asked about a sample of each restaurant index and about every claimed business; what they answer is shown here, beside the score, never in it.

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

Named instead

In the answers that didn't name Gunpowder Indian Restaurant & Bar - Christchurch City, the places named most often, and in how many answers.

  • INATI in 6 answers, with a link to this site
  • 50 Bistro in 4 answers, with a link to this site
  • Earl in 4 answers, with a link to this site
  • Miro in 4 answers, with a link to this site
  • Cellar Door in 3 answers, with a link to this site

See who was named →

Owners

The website's grade

An AI assistant can open Gunpowder Indian Restaurant & Bar - Christchurch City's website. It can read what Gunpowder Indian Restaurant & Bar - Christchurch City offers. It finds a phone number, but no link to book or order online.

76.4%

42 of 55 points available

2/5

agent-readiness level, Bot-Aware

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 crawlersblocked by robots.txt: GPTBot, ClaudeBot, Google-Extended, anthropic-ai, CCBot, Applebot-Extended, Bytespider, meta-externalagent, cohere-ainot scored
Requests under crawler names from Cloudflare's networkrefused: GPTBot, ClaudeBot, 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 Gunpowder Indian Restaurant & Bar - Christchurch City compares

Where it stands

106 of 420 in Christchurch

Ahead of 74% 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 domain100%no
Publish the menu or price list as HTML100%yes
Let the assistants in (robots.txt)100%yes
Structured data with address, phone and hours64%yes
Have an llms.txt49%no
Businesses like yours

Businesses like Gunpowder Indian Restaurant & Bar - Christchurch City in Christchurch

GroupSitesAvg scoreA or BThis site
Businesses of the same kind in Christchurch42060%30%76.4%

After the top fixes

With the fix above (No booking or ordering link on the website), the score would be about 100%, above every score in Christchurch today (420 sites). The others' scores move too, so this is an estimate.

Findings

What to fix first

  1. No booking or ordering link on the website +13 points no_channel

    There's only a phone number or WhatsApp, and agents can't use those yet. If you take bookings or orders through a platform, link to it from the site so agents can find it. Add a booking or ordering page. How to fix it

    Passes when the home page links a booking or ordering page on the site's own domain, or booking or ordering software. Recheck it

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

    Requests from Cloudflare's network naming themselves GPTBot (http_403), ClaudeBot (http_403), PerplexityBot (http_403) 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

  3. 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

  4. The phone number on the site doesn't match the open map data phone_conflict

    The site shows 0226007719, but OpenStreetMap or Overture Maps lists +64211221805. An assistant that sees two numbers can't tell which one to trust. Fix whichever is wrong, on the site or in the map data at openstreetmap.org.

    Passes when the phone number on the site and in the map listing are the same. 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. Training crawlers stay out (GPTBot, ClaudeBot, Google-Extended, anthropic-ai, CCBot, Applebot-Extended, Bytespider, meta-externalagent, cohere-ai): the owner's choice, and it costs nothing in the score. Google uses Google-Extended for Gemini's answers too (grounding in Gemini Apps), so blocking it also keeps the site out of those.
  • Structured data found (Restaurant) address, phone, opening hours
  • Menu or price list is an HTML page Agents can read the items and prices.

Builder: unknown · menu page /menu.html: 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