Documentation changelog

What changed in these pages, newest first. This is a changelog for the documentation, not for the product: it records what was written, corrected or retired here.

For whether a generated table is current, read its stamp rather than this page. Every generated reference carries the product commit it was read from, which is a better answer than a date on a changelog entry.

1 October 2026

Content Studio is documented as it ships today. Three pages cover the whole path from topic to live page:

• Writing articles leads with Write: one box, one price per length covering research, outline and writing, and the Customise path through a brief for when you want to shape each step.
• Content Autopilot is a new page. It plans topics from your own queue and your topic clusters, writes on the cadence you choose under a monthly cap, and holds each article for review or publishes it, as you set.
• Publishing articles now covers Shopify blogs beside WordPress, the SEO title and meta description written through your SEO plugin (All in One SEO included, with the RankX AI plugin), one-action approve and publish for staff, the built-in duplicate guard, and updating or unpublishing a live post.

Channel packs now carry an article to other channels, so the Campaigns page was retired and its address leads to writing articles, which covers them.

AI Shopping is documented around the products you monitor. Products monitored explains the three ways to choose them, the nightly refresh against your store, and listing-copy proposals that rewrite a product's description and search fields for your approval. AI Shopping adds the Modules switch and the per-question Shopping Questions screen.

Chat's capability statement was re-derived from the product, adding AI conversions, Bing, Shopify store diagnosis, redirects, schema, SEO coverage, page improvements and article progress. See what Chat can do.

The credit cost reference gained the article prices, page improvements, channel posts, press releases and listing-copy proposals, each confirmed against the live rate catalogue. See credit costs.

Smaller updates across the tree: the Settings map carries Modules, Products Monitored, Shopping Surfaces and the live Content and Alerts tabs; every page about AI visibility states that you choose which of the six assistants each Website and each prompt is asked on; AI Answer Citations draws on every tracked answer that names its sources; and the screen map links AI prompt research and search trends directly.

Agency report links and page builders are documented as they work. An emailed client report links to your own custom hostname once it is verified and live (see white label), and a page built with a block-based builder takes targeted text patches and block edits when you ask for them (see WordPress). Troubleshooting connections covers what to do when Google asks you to reconnect.

Earlier the same day, the MCP server overview gained the questions it answers best, worked prompts and an FAQ; Shopify gained how products are chosen for AI Shopping and the full list of what RankX AI writes to a store; WordPress documents SEO writes through every major SEO plugin with the RankX AI plugin installed; and AI Readiness and the site-signal watch link the free llms.txt Generator.

27 August 2026

Six pages were added for work RankX AI shipped, and four existing pages were updated to match.

Free access after a trial is documented. A trial that ends no longer locks the account: AI Readiness, Brand Book and the Tasks board stay usable, and everything else is paywalled. After the trial is the new page, and it sets out what happens to your data, on which clock: everything irreplaceable is kept, crawled page content and stored audit pages go at seven days, and Google Search Console and Analytics history at thirty. The free trial links to it.

The daily site-signal watch is documented. RankX AI now fetches every Website's robots.txt, llms.txt and homepage once a day, on every account including a lapsed one, and reports a change for the worse on the AI Readiness page. See the site-signal watch.

Answer accuracy has its own page. It covers the check that judges what assistants say about your business against the facts you have published. See answer accuracy for the seven verdicts and why the model never gets to choose one.

The Dashboard and Settings have their own pages. The Dashboard covers the Needs Attention feed and the card chooser; Settings maps all seventeen sections to their three scopes, and Brand Book gets the page it has always warranted, since more of the product reads it than any other screen.

Two updates from the product's code:

• AI Readiness states which evidence is live and which is stored. The site-side checks are fetched on every load; the page-level checks read stored crawl data and carry the date it was read.
• An applied task fix keeps a free undo, reachable from the dashboard and over MCP alike, and Tasks documents the revert beside the apply.

19 August 2026

These docs were written. /docs went from one page to a full set: getting started, concepts, every measurement and action section, the MCP server, the agency track, account and this reference.

The MCP server is documented in full as RankX AI's programmatic interface.

Five reference surfaces are generated from the product. The MCP tool tables, plan limits, the audit issue codes, the AI Readiness checks and credit costs are read from the product itself and stamped with the commit they came from, so each one stays in step with what ships.

Search covers every page. The search dialog on /docs finds any page in this tree.

Machine-readable twins were added. Every page here is now available as clean Markdown by appending .md to its URL or by sending Accept: text/markdown, and /docs/llms.txt indexes the tree. Generated tables render into the Markdown too, so a tool reference fetched as Markdown carries its tools.

Traffic is documented in full, Google Search Console and Google Analytics included, with the four availability states.

Two details were taken straight from the product's code:

• Scheduled checks run at most every seven days while an account is on trial, on every plan and every check family. See check cadence.
• Each plan's audit cadence floor comes from the setting the product itself enforces. See plan limits.

Screenshots

These pages describe each screen in words. Screenshots are added page by page as they are captured, each with its alt text.

How to tell whether a table is current

Every generated reference page carries a line naming the product commit it was read from and the date of that commit. That stamp is the answer, and it is more precise than a changelog entry, because it moves when the data moves rather than when someone remembers to write an entry.

The check that keeps it current runs in the build: if a vendored file is edited by hand, or a tool is added to the product without a line being written for it here, the build fails rather than shipping a stale table.

Where to go next

• Start here, for the whole tree.
• Credit costs and plan limits, the two tables most worth checking the stamp on.

Last updated 1 October 2026