Georix – GEO & AI Citation

Description

Stop being invisible to AI. While everyone focuses on Google rankings, AI engines like ChatGPT, Perplexity, and Google AI Overviews are answering your customers’ questions — and citing your competitors instead of you.

Georix fixes that from inside WordPress, with no coding and no API keys required.

Most GEO tools ask you to take their value on faith — they generate files and signals but never prove anything happened. Georix is built on the opposite idea: show real results, then help you improve them.

New in 1.2: the honest instrument panel

Georix v1.2 stops selling belief and starts showing evidence. Every number below comes from your own server logs — if a claim cannot be proven from your data, it does not ship.

• AI Crawler Cost Report — measures what AI crawlers actually cost you: how many requests they make, what share of your traffic that is, an estimated bandwidth figure (always labelled as an estimate), and — joined to AI Traffic Insights — how many visitors each one sends back. Googlebot is shown too, on purpose, so you can see which crawlers give something back before you block anything. Georix measures; it does not block — by the time WordPress runs, the request is already paid for. To actually block bots, we point you to Cloudflare, which does it at the edge for free.
• Verified Bot Identity — a spoofed «GPTBot» user-agent is trivial to fake, and most sites never check. Georix confirms crawlers using forward-confirmed reverse DNS plus bundled IP ranges, entirely on a scheduled task (never during a page load). Raw IPs are used only for the check and deleted the moment it finishes. The wording is always «unverified», never «fake» — vendors add IP ranges without notice.
• Reality Check — one panel that tells you the truth about your own configuration, including truths that make Georix look bad. It will tell you if nothing has requested your llms.txt, if a bot you «blocked» is still crawling, and if a page builder is hiding your content from crawlers behind JavaScript.

All existing features are unchanged. These are additions only. Removing the new feature files returns the plugin to its previous behaviour.

New in 1.1: proof and action

• AI Traffic Insights — passive, first-party analytics that show which of your pages are actually getting click-throughs from AI engines (ChatGPT, Perplexity, Gemini, Claude, Copilot, and more), pulled straight from your own site’s traffic. No API key. No data leaves your server. See which content AI is really recommending — and which pages need work. It even names its own blind spots (Google AI Overviews and no-click answers), so the number you see is an honest, verified minimum rather than an inflated estimate.
• Answer Booster — a new editor panel that finds the exact sentences hurting your AI visibility (numbers with no source, claims with no date, weak openings, no quotable line) and helps you fix them with one click. It never rewrites your words or invents a source — it hands you a blank template to fill in. 100% offline.

Adding sourced statistics, quotable claims, and cited sources is the single highest-impact tactic for getting cited by AI. Answer Booster removes the friction; AI Traffic Insights proves it worked. Everything else Georix does — llms.txt, schema, LocalBusiness, crawler control — is the agent-readiness infrastructure underneath.

All existing features are unchanged. These are additions only.

How it works

The plugin automatically creates two live URLs on your site:

• yoursite.com/llms.txt — a structured plain-text summary: who you are, your key pages, topics, services, and authors
• yoursite.com/llms-full.txt — an extended version with full content excerpts, dates, and attribution

These files are served automatically by WordPress — no manual file creation, no FTP, no file permissions to worry about. The moment you activate the plugin and save your settings, the URLs are live. AI crawlers (GPTBot, ClaudeBot, PerplexityBot, and others) read these files to understand your site before deciding whether to cite you in their answers.

Traditional SEO gets you into Google blue links. GEO (Generative Engine Optimisation) gets you cited inside AI-generated answers. They are different disciplines — this plugin handles both from a single settings page.

About llms.txt, plainly: Google has confirmed it does not use llms.txt, and there is no proven evidence it drives AI citations today. We still generate it because it is free, standards-friendly, and may matter later — and the new Reality Check panel tells you honestly whether anything on your site is actually requesting it. We would rather show you that number than pretend the file is doing more than it is.

Who is it for

• Local service businesses — dental clinics, law firms, accountants, restaurants, salons, gyms, medical practices
• Bloggers and content publishers who want AI engines to summarise and cite their articles
• SaaS and product sites that want to appear in AI-generated comparisons and recommendations
• Agencies managing multiple client sites — one plugin, consistent GEO setup across all sites

Core Features

AI Traffic Insights — first-party proof (new in 1.1)

• Shows which of your pages get real click-throughs from AI engines (ChatGPT, Perplexity, Gemini, Claude, Copilot, You.com, Grok, Meta AI, and more), read straight from your own visitors’ referrers
• Scoreboard, trend chart, and a ranked «top AI-cited pages» table so you can see your winners at a glance
• «Opportunities» panel highlights pages AI already likes that have no FAQ/HowTo schema yet
• Privacy-first: stores only the AI source, landing path, a UTC day, and a count — never an IP address or raw user agent, and nothing is transmitted anywhere
• Honest by design: names its blind spots (Google AI Overviews, no-click answers) and frames the total as a verified minimum, not a guess
• CSV export, configurable retention, and a one-click data reset

Answer Booster — turn advice into a fix (new in 1.1)

• A separate editor panel (the existing GEO Content Audit is untouched) that finds the highest-impact content weaknesses and helps you fix them
• Flags unsourced statistics, time-sensitive claims with no year, filler section openings, and a missing quotable claim
• Safe by design: one-click fixes insert a blank template you complete — never rewrites your words, never fabricates a source
• Dual-layer copy: plain-English «why this matters» for everyone, with a technical details expander for power users
• Every check is individually toggle-able, with a master on/off switch; 100% offline, no API calls

Automatic File Generation (No files to create manually)

• Auto-generates /llms.txt, /llm.txt (alias), /llms-full.txt, and optional /ai.txt served live from your WordPress site
• Works entirely through WordPress URL rewriting — no disk writes, no file permissions, no FTP
• <head> discoverability links, robots.txt AI crawler rules, and discovery-file comment block
• llms.txt Health Panel, physical file conflict detection, and robots.txt conflict alerts
• Crawler visit logging with 40+ bot registry (90-day history, CSV export)
• Intelligent content filtering — skips cart, checkout, login, privacy, and other non-content pages automatically
• Configurable minimum word count to exclude thin or placeholder pages
• Quality-scored post ordering — posts with excerpts, schema, and recent updates rank higher in the output
• WPML and Polylang support — discovery files grouped by language with correct per-locale URLs and content

Schema & Structured Data (Helps both AI and Google)

• LocalBusiness Schema Wizard — 100+ schema.org business types (Dentist, Solicitor, Restaurant, Accountant, and many more including India-specific types like Ayurvedic Clinic, CA Firm, Tiffin Service), opening hours, price range, address, phone number, and social profiles — output as JSON-LD on every page automatically
• FAQ Gutenberg Block — add Q&A items formatted as clean, answer-first content that AI engines can quote directly. The block also outputs FAQPage JSON-LD, which remains valid and harmless. Note: Google removed FAQ rich results from Search on 7 May 2026, so add the block for content structure, not for rich snippets.
• HowTo Gutenberg Block — step-by-step guides with clearly structured steps AI can lift. The block outputs HowTo JSON-LD; Google deprecated HowTo rich results in 2023, so this too is for content structure rather than search appearance.
• Organization, Article, BreadcrumbList, and speakable schema output site-wide

GEO Content Tools (Unique to this plugin)

• GEO Content Audit sidebar — live per-post checklist in the block editor scoring your content across 9 GEO checks: H2 headings, word count, FAQ block, HowTo block, manual excerpt, freshness, definition paragraph, statistics, and quotable sentence. Updates in real time as you edit — no save required.
• FAQ Question Suggester — detects your page’s niche (dental, legal, medical, accounting, restaurant, or generic) from the title, categories, tags, and content. Returns 8 ready-to-use question/answer pairs. Inserts directly as a FAQ block at the bottom of your post with one click. No API call — works completely offline.
• EEAT & AEO Readiness Score — 0–100 score across 5 pillars: Clarity, Authority, Comprehensiveness, Recency, and Structure. Shows exactly what is passing and what needs attention.

Technical Controls

• AI Crawler Manager — per-bot Allow/Disallow toggles for GPTBot, ClaudeBot, PerplexityBot, Google-Extended, Applebot-Extended, Bytespider, cohere-ai, and FacebookBot written to robots.txt
• Custom Sections builder — add your own sections with headings and links directly to llms.txt from the admin UI (no code)
• Check File Status — live HTTP test confirms your llms.txt and llms-full.txt are serving correctly
• Flush Rewrite Rules — one-click fix if the URLs ever return a 404 after a theme or plugin change

No API Keys. No Coding. No File Uploads.

Everything works out of the box after activation. Fill in your organisation name and description, save, and your llms.txt is live within 30 seconds.

Privacy

This plugin does not collect, store, or transmit personal data to the plugin author’s servers. Crawler visit logs (bot name, user agent, IP address, timestamp) are stored only in your WordPress database when logging is enabled. All other processing happens on your own site.

AI Traffic Insights (new in 1.1): this feature records only the AI source (for example «ChatGPT»), the landing page path, a UTC date, and a coarse visit count. It does not store IP addresses, does not store raw user-agent strings, and strips query strings from referrers. This data is stored only in your own site’s database and is never transmitted anywhere. It is preserved if you uninstall unless you explicitly opt in to removal.

Answer Booster (new in 1.1): all content analysis runs locally on your own server. Your content is never sent to any external service, and no analysis results are stored.

AI Crawler Cost Report (new in 1.2): stores only per-day, per-bot aggregate counts (bot name, vendor, request count, an estimated byte figure, and a date). It does not store IP addresses or raw user agents. Bandwidth is an estimate — crawler requests multiplied by a rolling average HTML response size sampled from your own site — and is always labelled as an estimate.

Verified Bot Identity (new in 1.2): to confirm a crawler is genuine, the plugin performs reverse-DNS and forward-DNS lookups on the crawler’s IP address, and compares it to IP ranges bundled locally with the plugin. This runs only on a scheduled task, never during a visitor page load. A raw IP is written to a verification queue row only while the check is pending and is deleted the moment the check completes — only the verdict (verified / unverified) and the resolving organisation are kept. No raw IP is ever shown in the admin UI or included in any CSV export. The wording is always «unverified», never «fake».

External services

This plugin does not send site content or personal data to the plugin author’s servers or to third-party APIs.

Site health checks (your own site only)

When you click «Check File Status» or when the Health panel runs validation, the plugin makes HTTP requests from your WordPress install to your own site’s public URLs (for example /llms.txt and /robots.txt). These self-requests confirm that discovery files are reachable. No data is sent to external servers. The Reality Check «visibility» check (new in 1.2) works the same way — it requests your own homepage only, to count the words a crawler can see.

Bot identity verification (new in 1.2, DNS only, your own database)

To confirm a crawler is genuine, Verified Bot Identity performs standard DNS lookups (reverse DNS on the crawler’s IP, then a forward DNS lookup to confirm it) using your server’s resolver. These are DNS queries, not data transfers — no site content or personal data is sent anywhere. IP ranges used for the check are bundled with the plugin and refreshed with each release; the plugin does not fetch them from any external service. All verification runs on a scheduled task, never on a visitor request.

WPML / Polylang (optional, if installed)

If WPML or Polylang is active, the plugin reads language configuration from those plugins locally to group llms.txt output by locale. The plugin does not make additional outbound requests to WPML or Polylang services beyond what those plugins already do on your site.

Bot documentation links (admin reference only)

The AI Crawlers admin tab lists known crawlers with links to each provider’s public documentation (for example OpenAI GPTBot, Google crawlers, Anthropic, Amazonbot). These are display-only reference URLs in the WordPress admin. The plugin does not connect to those services or transmit your site data to them.