內容簡介
Georix 是一款專為 WordPress 設計的外掛，旨在提升網站在 AI 搜尋引擎中的可見度，並幫助用戶有效管理與 AI 相關的流量與數據。透過實時數據分析，Georix 讓用戶能夠優化內容，提升競爭力。
【主要功能】
• Answer Capsule Engine：檢查可引用的答案來源
• Lost-to-AI Question Finder：找出流失的問題
• AI Crawler Cost Report：分析 AI 爬蟲的成本
• Verified Bot Identity：驗證真實的爬蟲身份
• AI Traffic Insights：提供 AI 流量分析
• GEO Content Audit：即時地理內容評估
外掛標籤
開發者團隊
原文外掛簡介
Stop being invisible to AI. ChatGPT, Perplexity, and Google AI Overviews are answering your customers’ questions right now — and citing your competitors instead of you. Georix fixes that from inside WordPress. No coding, no API keys.
Most GEO plugins ask you to take their value on faith. Georix shows real, provable results from your own server data, then helps you improve them. If a claim can’t be proven from your data, it doesn’t ship.
What Georix does
Answer Capsule Engine (new in 1.3) — checks whether an AI engine could actually lift a citable answer from each page, and a block to publish one that it can.
Lost-to-AI Question Finder (new in 1.3) — connects your own Search Console data (opt-in) to find questions you’re losing to AI answers, ranked by opportunity.
AI Crawler Cost Report (new in 1.2) — see what GPTBot, ClaudeBot, and others actually cost you in requests and bandwidth, vs. what they send back.
Verified Bot Identity (new in 1.2) — catches spoofed “GPTBot” traffic with real reverse-DNS verification, not just a user-agent check.
Reality Check (new in 1.2) — an honest panel that tells you the truth about your setup, even when it’s unflattering.
AI Traffic Insights (new in 1.1) — first-party analytics showing which pages actually earn AI-engine click-throughs.
Answer Booster (new in 1.1) — an editor panel that flags unsourced stats, weak openings, and missing quotable lines.
llms.txt / llms-full.txt / ai.txt — auto-generated, live within 30 seconds, no files to upload.
Schema & structured data — LocalBusiness (100+ types), FAQ & HowTo blocks, Organization/Article/Breadcrumb JSON-LD.
GEO Content Audit & AEO Score — live per-post scoring across 9 GEO checks, right in the block editor.
AI Crawler Manager — per-bot allow/disallow control written straight to robots.txt.
Built for local service businesses, bloggers, SaaS sites, and agencies managing multiple client sites.
No data leaves your server except where explicitly disclosed (DNS lookups for bot verification, and your own opt-in Search Console connection). Full feature breakdown, privacy details, and FAQs below.
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
Features In Detail
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
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. The one exception is the optional Lost-to-AI Question Finder added in 1.3, which reads your own Google Search Console data — it is off by default and every other feature works without it.
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”.
Answer Capsule Engine (new in 1.3): every Liftability Check runs locally on your own server. Your content is never sent anywhere. The only things stored are the target question you typed and the cached verdict, both in your own database as post meta.
Lost-to-AI Question Finder (new in 1.3): opt-in and off by default. When connected it retrieves your own Google Search Console rows (query, page, date, impressions, clicks, average position) and stores them in your own database. No page content, visitor data or personal data is sent to Google — only a date range and the dimensions requested. Requests run on a daily scheduled task or when you click Refresh, never on a visitor page load. Credentials are encrypted at rest where the server supports it, deleted on disconnect and always deleted on uninstall. See External services below for the full disclosure.
External services
This plugin does not send site content or personal data to the plugin author’s servers or to third-party APIs.
Google Search Console API (new in 1.3, opt-in, off by default)
The Lost-to-AI Question Finder is the only feature in Georix that contacts a third-party service, and it does nothing at all until you explicitly connect it.
What is sent: a signed request to Google’s OAuth token endpoint (https://oauth2.googleapis.com/token) to obtain a short-lived access token from the service-account key you pasted, and then queries to the Google Search Console API (https://searchconsole.googleapis.com/) for your own verified property. Each API request body contains only a date range, the dimensions being requested (date, query, page), a row limit and a paging offset. No page content, no visitor data, no personal data and no IP addresses are sent.
When it is sent: only on a daily scheduled task, and when you click “Refresh data”. Never on a visitor page load, and never on an ordinary admin page load. Responses are cached for 12 hours.
What is stored: your own Search Console rows (query, page, date, impressions, clicks, average position) in a new table in your own database, plus your service-account credentials, encrypted at rest with the server’s sodium or openssl extension where available. If neither extension exists, the screen tells you plainly that the credentials are stored as ordinary text.
Disconnecting: one click. Stored credentials and the cached access token are deleted immediately, and the scheduled task is removed. On uninstall the credentials are always deleted; the stored Search Console data is preserved unless you opt in to removal.
Google’s terms apply to this API: Google APIs Terms of Service and the Google Privacy Policy. Service: Google Search Console API, provided by Google LLC.
Answer Capsule Engine (new in 1.3, no external service)
All Liftability Check analysis runs locally on your own server against your own rendered content. Nothing is sent anywhere and no analysis result leaves your database.
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.
