Skip to content
Docs

RankX AI documentation

How RankX AI measures whether AI assistants name your brand, what every number means, and how to drive the whole platform from an AI assistant over MCP.

RankX AI measures whether AI assistants name your brand when someone asks them a buying question, and turns what it finds into a prioritised fix list. It tracks ChatGPT (with Gemini, Claude and Perplexity one switch away), Google AI Overviews, two AI shopping surfaces and ordinary Google positions, from one account.

These docs follow the product's own navigation, so you can read them with the app open beside you. The reference tables are generated from the product's data rather than typed by hand.

Where to start

What does RankX AI measure?

RankX AI measures four kinds of surface, and each is a separate measurement that is never averaged into the others.

  • AI assistant answers. RankX AI asks your tracked prompts on ChatGPT, and on any of Gemini, Claude and Perplexity you switch on, then records whether your brand was named, where it sat, and which sources the answer leaned on. You choose which assistants each Website and each prompt is asked on. See how RankX AI measures visibility.
  • Google AI Overviews. Collected on your tracked keywords by the rank tracker, not by the prompt run. Citations, two kinds explains how this differs from the sources inside an assistant's answer.
  • AI shopping answers. Whether your products are recommended on ChatGPT Shopping and Google AI Mode, and which merchants take the slots. AI Shopping is a module you switch on per Website, and RankX AI switches it on for you when it detects a store. See AI Shopping.
  • Ordinary Google positions, to depth 20, plus Search Console, Analytics and Bing Webmaster Tools once they are connected.

What does RankX AI do with the findings?

RankX AI turns findings into work. It puts them on a Tasks board, scores how readable your site is to AI crawlers with AI Readiness, audits the site, researches keywords and AI prompts, and drafts content against briefs.

Every screen, and where it is documented

The table maps each screen in RankX AI to the page that documents it.

In RankX AIDocumented at
DashboardThe Dashboard: the Needs Attention feed, the cards and which of them you can hide
Chat (the Browse/Chat toggle)Chat: Ask reads and explains, Act proposes changes you approve
Website AuditWebsite Audit
TasksTasks
Visibility OverviewAI Visibility
AI PromptsAI Prompts
AI Chat FeedAI Chat Feed
AI Answer CitationsAI Answer Citations
AI ReadinessAI Readiness, plus answer accuracy and the daily site-signal watch
Shopping OverviewAI Shopping
Shopping QuestionsThe surfaces each shopping prompt is asked on
ProductsProducts monitored
MerchantsMerchants
AdsAds
Rankings OverviewGoogle Results
Rank TrackingRank tracking
AI OverviewsAI Overviews
AI Overview CitationsAI Overview Citations
Traffic OverviewTraffic
Search ConsoleSearch Console
Google AnalyticsGoogle Analytics
Conversions from AIConversions from AI: enquiries, sign-ups and sales from visitors an AI assistant sent
IndexingIndexing
BingBing Webmaster Tools
AI Prompt ResearchAI prompt research
Keyword ResearchKeyword research
Trends ResearchSearch trends
Topic ClustersTopic clusters
Content StudioWriting articles, content briefs, Content Autopilot, quality scores and publishing
Agency AdminRunning an agency
SettingsSettings, and Brand Book, the largest section

How do I drive RankX AI from an AI assistant?

Connect an AI assistant to the RankX AI MCP server and ask for the work in words. The MCP server is a Model Context Protocol endpoint with a documented tool surface, scoped permissions, OAuth 2.1 sign-in and ready-made Agent Skills.

Claude, ChatGPT, Cursor, VS Code and scripts all reach the same tools under the same safeguards. The MCP section documents every tool, its scope and what it costs to call.

Reading these docs as an AI agent

Every docs page is available as clean Markdown: append .md to its URL, or send Accept: text/markdown. The documentation index is at /docs/llms.txt, the curated brand file at /llms.txt, and the full site corpus at /llms-full.txt.

To write an llms.txt file for your own site, the free llms.txt Generator builds one from your sitemap.

Terminology is fixed across these docs. A Website is one site you track, a Client Workspace is one of an agency's clients, AI Overviews is Google's summary above the results, and AI Answer Citations are the domains cited inside an AI assistant's answer.

Questions

Which AI assistants does RankX AI track?

RankX AI asks your tracked prompts on ChatGPT, with Gemini, Claude and Perplexity one switch away, and measures Google AI Overviews separately on your tracked keywords. You choose which assistants each Website and each prompt is checked on. See tracked platforms.

Does RankX AI work for Shopify and WooCommerce stores?

Yes. A Shopify store installs RankX AI from the Shopify App Store and a WooCommerce or other website signs up on the web. Each platform's setup is in integrations.

Do I need a credit card to try RankX AI?

No. The free trial needs no card, and it starts when you finish onboarding rather than at signup. See the free trial.

Where should a new RankX AI user start reading?

Start with the quickstart, then read your first week so the empty screens on day one make sense.

Last updated

Cookie settings

Choose which cookies we can use. You can change this at any time from “Cookie settings” in the footer.

Essential

Security, bot protection and remembering your choice. The site needs them to run, and they do not identify you. Always on.

Google Analytics cookies that tell us which pages are read and which links are followed, so we can improve them. Off until you switch it on.

Tells advertisers when their advert led to your visit. Includes the Meta (Facebook) pixel and the LinkedIn Insight Tag, which set cookies on this domain (LinkedIn also on linkedin.com) and can be told if you later start a trial.

More in the cookie policy and the privacy policy.