CiteCue AI Auto-Fix is the WordPress end of CiteCue , an answer engine optimization (AEO) platform. It decides, per request, which version of a page WordPress returns — the optimized one to a recognised AI crawler, your normal page to everyone else — and it can do that only from inside WordPress, be
PricingFree downloadThe WordPress.org download is free. Pro versions, add-ons or external services may cost extra.
CompatibilityRequires WordPress 5.8 and PHP 7.4.
SourceWordPress plugins · Oct 20, 2026
01 / Source details
About this tool.
CiteCue AI Auto-Fix is the WordPress end of CiteCue , an answer engine optimization (AEO) platform. It decides, per request, which version of a page WordPress returns — the optimized one to a recognised AI crawler, your normal page to everyone else — and it can do that only from inside WordPress, before the theme renders.
Per-request delivery to AI crawlers — when GPTBot, ClaudeBot, PerplexityBot, ChatGPT-User or any other agent in the crawler registry requests a page, the plugin returns the CiteCue-optimized version of that URL. Human visitors always see your normal site, and optimized responses are never cached for regular traffic. Any miss, timeout or outage passes straight through to the normal page.
Gap-filling page metadata — adds CiteCue’s title, meta description, OpenGraph, canonical and structured-data tags to your live pages, so search engines and AI answer engines see them on the page a human sees. It fills gaps only: it reads what your theme, WordPress and your SEO plugin actually printed into <head> and adds only what none of them emitted, so there is never a second title or canonical.
Page enhancements — where you have approved one in CiteCue, adds a short facts-and-FAQ section to the end of a page you already have, built from your own answered facts and grounded FAQ entries rather than generated. It is placed only if the page does not already carry one, and it is the only thing this plugin adds that your visitors can see.
Recognises 18 AI crawlers, and learns new ones on its own — GPTBot, ChatGPT-User, ClaudeBot, PerplexityBot, GoogleOther, Amazonbot, Bytespider, CCBot, meta-externalagent, MistralAI-User, DuckAssistBot and more. The registry refreshes daily from CiteCue, so an agent that launched last week is recognised without updating the plugin.
Never makes a visitor wait — the path that renders a page for a person reads cache only; nothing on it calls out to the network. A URL with nothing cached yet renders untouched and the fetch is queued for afterwards, so the first visitor to a cold page pays one un-enriched view rather than one slow one. Requests from AI crawlers are the deliberate exception — only a bot is waiting there — and even those are bounded by a three-second timeout, a per-minute lookup budget and a circuit breaker that stops the plugin trying at all while CiteCue is unreachable.
Content from CiteCue — a signed endpoint through which CiteCue can push new brand-building content (content briefs, FAQ packs, gap-filling pages) into WordPress as drafts for your review.
WooCommerce-aware — cart, checkout, account pages and cart-modifying links are never intercepted, while product and shop pages are served optimized. Pushed content can also create or enrich WooCommerce products (draft by default, matched by SKU with explicit consent).
This plugin requires a CiteCue account — citecue.com — and does nothing until you connect one. See “External services” below for exactly what is sent where.
What the plugin actually does
Everything above happens on a live request, and that is where the design decisions are:
It serves a different representation per requester, safely. Crawler matching runs against a registry that refreshes daily, so an agent launched last week is recognised without a plugin update. A logged-in user, a cart URL, a WooCommerce endpoint or a cart-modifying link is never intercepted. A circuit breaker, a per-minute lookup budget, negative caching and a stale-while-revalidate cache mean an outage at CiteCue costs a passthrough, never a broken page or a slow one.
It composes with your SEO plugin rather than replacing it. The metadata layer detects what was actually printed into <head> rather than looking for particular plugins, so it behaves correctly beside Yoast, Rank Math, a plugin nobody has heard of, or none at all. Every tag it adds carries a data-citecue attribute, so View Source tells you exactly which ones came from CiteCue.
Nothing from the API is trusted as markup. Every returned tag is parsed, matched against an allowlist of shapes and rebuilt from escaped values, with structured data re-encoded so it cannot escape its own script element.
It never makes a visitor wait on a third party. The render path reads cache only; a URL with nothing cached yet renders untouched and the fetch is queued to WP-Cron.
Content flows back in. The signed citecue/v1 endpoint is how CiteCue delivers new content into WordPress — as drafts, with replayed signatures rejected — so the loop from “this page is missing” to “this page exists” closes without anyone copying and pasting.
The service behind all of it is at citecue.com .
External services
This plugin is the WordPress end of CiteCue, a hosted service at citecue.com that generates AI-optimized versions of your pages. The optimized pages, your llms.txt and the pushed draft content are all produced by that service, so the plugin cannot work without it. Nothing below happens until an administrator connects the site.
Terms of Service: citecue.com/terms Privacy Policy: citecue.com/privacy
The service is reached at https://app.citecue.com (or the origin you pin with the CITECUE_API_BASE constant, for self-hosted CiteCue deployments).
Connecting the site — once, when an administrator clicks “Connect to CiteCue”. Your browser is sent to app.citecue.com/connect/wordpress with this site’s address so CiteCue can show you which project you are pairing. WordPress then posts to /api/delivery/v2/connect/claim : the one-time code from that redirect, this site’s address, its REST API address, this site’s content-push secret, the plugin version, whether WooCommerce is active, and whether enriched page metadata is switched on. CiteCue returns the API key it issued for this site. The API-key fallback instead sends the key you paste to /api/delivery/v2/config , which returns your organization’s projects.
Serving a page to an AI crawler — on each request from a matched AI crawler, and never for a human visitor or a logged-in user. The plugin sends the requested URL, the matched crawler’s User-Agent token and the site’s project key to /api/delivery/v2/page . No visitor data — no IP address, no cookies, no personal data — is sent. CiteCue records the crawler hit so it can report it back to you. Responses are cached, misses are remembered for a minute, and a per-minute budget caps the total.
Enriching a page’s metadata — in the background, on WP-Cron, for a URL a visitor has requested while enriched metadata is switched on. The requested URL and the site’s project key are sent to /api/delivery/v2/seo-head . No visitor data — no IP address, no cookies, no personal data — is sent, and this never happens while a visitor is waiting: a page with no cached block yet is rendered untouched and the fetch is queued for afterwards.
Before a URL is cached, queued or sent, every query argument WordPress does not recognise as a query variable is removed from it, so tokens, order keys and nonces that happen to be in the address are never included. WooCommerce cart, checkout, account and order pages are skipped entirely. Responses are cached, empty answers are remembered for a minute, the same per-minute budget caps outbound calls, and a second per-minute cap limits how many refreshes a burst of traffic can queue.
Serving llms.txt — when /llms.txt is requested and the feature is on. The site’s project key is sent to /api/delivery/v2/llms.txt . The response is cached.
Refreshing the AI-crawler list — once a day, on WP-Cron, for a connected site only. An unauthenticated request to /api/delivery/v1/crawlers fetches the current list of AI crawler User-Agent tokens, so newly launched crawlers are recognised without a plugin update.
Verifying the installation — when you connect, and whenever you click “Verify installation”. The plugin requests your own site’s /llms.txt over HTTP, identifying itself as an AI crawler, to confirm the plugin answers rather than a cache or CDN. This request goes to your site, not to CiteCue.
Every outbound request identifies itself with a CiteCue-WordPress/<version> (+<your site URL>) User-Agent.
In the other direction: when content pushes are enabled, CiteCue sends new content to this site’s citecue/v1 REST route. Each request is signed with the shared secret exchanged during connection, replayed signatures are rejected, and the content is created as a draft unless you raise that limit yourself.
02 / Source details
Getting started.
You need a CiteCue account before step 2 — sign up at citecue.com .
01Install and activate the plugin from Plugins → Add New, or upload it under Plugins → Add New → Upload Plugin.
02Go to Settings → CiteCue and click “Connect to CiteCue”.
03Confirm the project for this site in CiteCue. You are redirected back and the plugin checks itself.
04Add and generate optimized pages on CiteCue’s Auto-Fix page.
There is nothing to copy or paste: the connection brings the API key back to WordPress and hands CiteCue this site’s address and content-push secret. Sites that cannot complete a browser round-trip to CiteCue can still connect with an organization API key — “Connect with an API key instead” on the settings screen.
Until you complete step 2, the plugin makes no outbound requests at all.
03 / Source details
Frequently asked questions.
Do I need to create an API key by hand?
No. Clicking “Connect to CiteCue” issues a key for this site and stores it for you. The manual route stays available for installs that cannot redirect through CiteCue.
How do I check it is working?
Settings → CiteCue → “Verify installation” requests your own llms.txt as an AI crawler and confirms the plugin answered. It runs automatically right after you connect. The usual cause of a failure is a full-page cache or CDN answering before WordPress loads.
To check a page by hand, request one you have optimized on CiteCue’s Auto-Fix page and look for the “x-citecue: served” header:
curl -si -A GPTBot https://your-site.com/a-page-you-optimized/ | grep -i x-citecue
Use curl or a logged-out browser — logged-in users always get the normal site.
My llms.txt works, but pages are not being served. Why?
Almost always because CiteCue has no optimized version of that URL yet. Connecting sets up delivery; it does not generate pages. Add and generate them on CiteCue’s Auto-Fix page, then re-test — waiting a minute first, because a miss is remembered for 60 seconds and an immediate retry will not call CiteCue at all.
Settings → CiteCue → “Recent AI crawler activity” tells you which it is. A “passthrough” row for the URL means the plugin ran and CiteCue reported no optimized page. An “error” row means the call to CiteCue failed. No row at all can mean either that the plugin declined before calling CiteCue (a recent miss, a backed-off connection, serving switched off) or that a full-page cache or CDN answered before WordPress ran.
Is this cloaking?
No, and the distinction is the one search engines draw: cloaking is showing a crawler different content than a person in order to manipulate ranking.
The optimized page goes only to AI assistants that identify themselves in their User-Agent, never to a person, and it carries the same facts as the page it stands for. Google appears on both sides of that line and the difference matters: GoogleOther , which Google uses for its AI products, is in the crawler registry and is served the optimized page; Googlebot , which crawls for Search, is not in the registry and gets your ordinary page.
What a person and Googlebot both receive is your page, plus CiteCue’s metadata in the head, plus a page enhancement on the pages where you approved one. All three are identical for both — nothing is shown to a crawler and withheld from a reader, which is the test that actually matters.
Will it slow my site down?
Not for your visitors. On a page CiteCue has something for, the plugin reads a cached block and adds it to the response; nothing on that path calls out to the network. On a page it has nothing cached for, it injects nothing and queues the fetch for WP-Cron, so the first visitor to a cold URL pays one un-enriched view rather than one slow one.
Requests from recognised AI crawlers are handled differently on purpose: that path may make a live lookup, because only a bot is waiting for it. It is bounded by a three-second timeout and a per-minute lookup budget, and a circuit breaker stops the plugin trying at all while CiteCue is unreachable, so a slow or failing CiteCue costs those requests a passthrough rather than an open-ended wait.
Will human visitors ever see the optimized version?
No. Only requests whose User-Agent matches the AI-crawler registry are served the optimized page , and those responses are never cached for regular traffic.
Two things are added for everyone, deliberately. Enriched metadata is head-only tags describing the page a visitor is already looking at. A page enhancement, where you have approved one, is a short facts-and-FAQ section at the end of that page. Both are additions to your page; neither rewrites it, and neither is shown to crawlers and withheld from people.
Will this conflict with Yoast SEO, Rank Math, All in One SEO or SEOPress?
No. CiteCue reads what your theme, WordPress and your SEO plugin actually printed into <head> , and adds only the tags none of them emitted — checking the output rather than looking for a particular plugin, so it is equally correct with an SEO plugin nobody has heard of. A site where Yoast already handles the title, description, canonical, OpenGraph and schema gets nothing added, which is the right answer. A site where it handles the basics but emits no OpenGraph gets the OpenGraph tags.
CiteCue’s tags carry a data-citecue attribute, so View Source tells you exactly which ones it added.
To hand a slot back to CiteCue, remove your SEO plugin’s copy of that tag and re-add CiteCue’s through the citecue_seo_head_tags filter. To switch the whole thing off, untick “Enrich page metadata” under Settings → CiteCue.
What happens if CiteCue is down?
Nothing visible: a circuit breaker stops API calls for a minute and every crawler request falls through to your normal page (or a cached optimized copy).
Does pushed content go live automatically?
By default it is created as a draft. You can raise the cap to “Pending review” or “Published” in the settings.
Is WooCommerce supported?
Yes. Store pages (cart, checkout, account, all WooCommerce endpoints) are never intercepted, and product/shop pages are served optimized like any other page. With WooCommerce active, pushed content may also create draft products or enrich existing ones (matched by SKU, only with an explicit force flag).
Website LLMs.txt and LLMs-Full.txt Generator is an LLMs.txt generator and llms-full.txt generator for WordPress. It helps site owners generate, manage, preview, validate, and serve AI discovery files from published public content. Use it to create structured /llms.txt and optional /llms-full.txt end
EngageDock AI is a customizable floating contact widget for WordPress websites that want more leads and faster visitor communication. It helps small businesses turn website traffic into calls, texts, emails, and callback requests from one clean contact panel. Key Features: Click-to-Call – One tap ca
Altify AI is an auto ALT text and AI ALT text plugin for WordPress images. It helps generate descriptive image ALT text for accessibility and image SEO. Use bulk image ALT text tools for your Media Library, generate featured image ALT text automatically, and scale WooCommerce image ALT updates with
The Accepted Payment Methods plugin is a straightforward, lightweight solution that enhances your website by displaying visually appealing icons of the payment methods you accept. This plugin is ideal for a variety of websites, including e-commerce platforms, service-oriented websites, and informati
