Features released, improvements shipped, and fixes deployed.
You can now trust that an "add this" recommendation points at a real gap. We measured our own tool against production data, found it was flagging concepts your pages already covered, and fixed it. The false-recommendation rate dropped from 87.6% to zero.
You can now analyze Japanese, Korean, Chinese, Arabic, and other non-Latin-script pages and get a full coverage score and concept map. Writing guidance is held back for now rather than shown at a quality level we cannot stand behind.
You can now trust that a "move this to its own page" recommendation means the idea is ready to carry a page — not just that it exists. The pipeline now checks whether a concept is developed enough before it suggests structural action.
You can now analyze long, content-heavy pages without hitting the "analysis output exceeded the response limit" error that used to fail the whole run partway through. Pages with many concepts, long comparison articles, and reference-heavy explanations now complete normally.
You can now read a controlled study showing that ContentGrapher's gap picks lift AI retrieval by 11 percentage points more than adding the same volume of content to parts the page already covers, on pages with five or more flagged gaps.
You can now read the coverage score against a back catalogue where question depth is actually scored. A system-funded pass graded depth on the large majority of past analyses, the score header says plainly when an analysis still has none, and the Shallow-to-Complete labels are re-anchored so they split pages into even quarters again.
You can now see a fairer coverage score on analyses run before depth scoring existed. Earlier reports were held back by a part of the formula they had no data for, so many scores moved up without any change to your content.
You can now trust that a higher coverage score means deeper, more useful content — not just more of it. The scoring instrument was rebuilt to separate shallow mentions from substantive coverage, giving you a signal that moves when your writing actually improves.
You can now see exactly which concept each writing task addresses at a glance. Hover any dot to see "Clarify: breed popularity" instead of a truncated sentence fragment.
You can now understand why your writing brief is prioritized the way it is — and how real user demand from Google search shapes which gaps ContentGrapher surfaces first.
You can now hover any dot on the priority map to preview the specific writing instruction it represents, and clicking a dot scrolls to and highlights the exact card in the writing agenda — not just the section header.
You can now get in-product guidance on the SERP intent alignment row and AI Overview badge — two signals that connect your structural analysis to the external retrieval environment.
You can now analyze long pages with dense concept coverage and get back a complete report. Previously these analyses failed before producing writing guidance, with no recovery path.
You can now see whether the SERP's dominant retrieval intent matches your page's structure, directly in the analysis header — along with an AIO indicator when Google is serving an AI Overview for your keyword.
You can now share a report directly from the report page. Clicking Share generates a public link and copies it to your clipboard, so you can send the analysis to anyone without requiring them to log in.
URL analysis now starts faster. The scraping phase completes in under 4 seconds on most pages, down from up to 15 seconds, with no change to how you submit URLs or read results.
Requested by Marin Morchev
The cookie consent banner now closes reliably in all browsers, shows visual confirmation when you choose "Essential only", and presents both options with equal visual weight.
The analysis report and shared report pages now display correctly on mobile. The concept integration and coverage matrix panels stack vertically on small screens instead of being forced into side-by-side columns that overflow the viewport.
ContentGrapher now lets you download your analysis as a structured .xlsx file with one sheet per record type, so you can review, share, and process results outside the UI.
Anonymous users are now navigated to /report/[id] after analysis completes, with their device token used to authenticate the page load. The report persists across tab reloads as long as the device token is in localStorage.
Requested by Hannah Swinkin
You can now find your priority content tasks and writing guidance unified in a single Writing Agenda section, alongside a new PRR role badge that identifies pages with a primary retrieval responsibility in your content architecture.
You can now see a dismissible banner prompting you to sign in and save your results when your analysis completes as a logged-out visitor, preventing result loss without blocking access to the report.
Requested by Kaj Kandler
You can now see your content gaps mapped visually on a four-quadrant matrix alongside an accordion grouped by quadrant, replacing the previous flat ImpactMatrix layout. Note: this layout has since been consolidated into the Writing Agenda in a follow-on release.