URL, HTML or text input
Audit one public web response or work directly from pasted HTML or plain text without first creating a project or account.
See whether a page gives answer engines clear structure, explicit answers and claims they can check.
A silent screen tour of the shipping Cited app: Citability score overview; Dimensions fixes and detected signals; Full AI readiness report; Private AI apple intelligence; Private answer engine simulation; Pasted article and score.






This website download is a separate direct-distribution build from the Mac App Store edition. It contains no StoreKit purchase flow or subscription screen: every feature is available after the one-time website purchase.
Apple notarized this exact disk image after an automated malware check. It is signed with the publisher's Developer ID and its notarization ticket is stapled to the download, so Gatekeeper can verify it even when your Mac is offline.
How signing, notarization and installation workb0e60a5e05e296fb81cc9d04e974550debf1170f257a1f7ffa36199b5c130b2eA native answer-engine readiness auditor for Mac. Analyze one URL or pasted HTML or text, inspect a five-part deterministic score, entities, claims and prioritized fixes, then copy a complete report or run an optional grounded simulation.
Cited gives AI-search content review a focused native Mac workspace. Enter one public HTTP or HTTPS URL, paste HTML, or paste plain text. For a URL, the app retrieves one raw response; for pasted material, it analyzes exactly what you supply. The deterministic audit then extracts readable content and exposes the title, word count, headings, FAQ patterns, structured-data signals, named entities and checkable claims behind its result.
The 0–100 readiness grade is a disclosed heuristic built from five dimensions: structure and headings, FAQ or question-and-answer coverage, structured data when HTML is available, answer-first writing, and entity and claim coverage. Cited shows each dimension separately, lists detected signals and turns weak areas into prioritized recommendations. The score is designed to make an editorial preflight reviewable; it is not a search ranking model and does not claim access to a search engine's index or citation systems.
A complete Markdown report records the grade, dimension breakdown, detected entities, checkable claims, source details and recommended fixes for handoff. When a supported provider is available, Cited can also produce an explanatory narrative or simulate an answer-engine response from a bounded excerpt of the analyzed source. Those optional results are grounded against the supplied content and checked for citation support before presentation, while the deterministic score remains available without any model.
Optional generation can use Apple Intelligence on supported Macs, a local Ollama or LM Studio service, or a supported cloud provider using an API key stored in the macOS Keychain. The separate website Direct edition is Developer ID-signed and Apple-notarized, permanently unlocks complete reports and simulations after one purchase, and contains no StoreKit subscription flow, account requirement or trial timer.
Audit one public web response or work directly from pasted HTML or plain text without first creating a project or account.
Review structure, FAQ coverage, HTML structured data, answer-first writing, and entity and claim coverage instead of accepting an opaque score.
See headings, detected entities, checkable claims and other content evidence that influenced the grade.
Start with the weakest dimensions and concrete editorial actions rather than a generic request to optimize the page.
Copy a Markdown audit containing source details, grade, dimension scores, detected evidence and prioritized fixes.
Use a supported provider for a narrative or bounded answer-engine simulation with citation-support checks against the analyzed source.
Cited is an editorial readiness preflight, not a search-engine crawler, browser renderer, index monitor, rank tracker, analytics service or guarantee of traffic, indexing, answer inclusion or citations. URL mode retrieves one raw HTTP or HTTPS response and does not follow the site's internal links or execute client-side JavaScript; blocked, login-protected, non-2xx and JavaScript-only pages may fail or expose incomplete content. Fetches time out after 30 seconds and reject responses larger than 5 MB, analysis is capped at 2,000,000 characters, and optional answer-engine simulation uses at most 4,000 characters of context. Scores, entity detection, claim extraction, recommendations and citation-support checks are heuristics and require human factual, technical SEO, editorial and legal review. URL mode contacts the target host, so its server receives the request; choosing a cloud provider sends the relevant analyzed content directly to that provider under its terms.
Website edition purchased once and fully unlocked; the separate App Store edition retains its subscription purchase flow.
Buy & downloadA native AI-search content preflight for Mac. Analyze one URL or pasted HTML or plain text, review a deterministic 0-100 readiness grade across five disclosed dimensions, inspect detected entities and checkable claims, prioritize concrete fixes, and copy a complete Markdown report.
Cited is for content, SEO, AEO and communications teams checking whether a page is structured clearly enough for answer engines and human reviewers. Audit one page for answer-engine readiness, inspect the signals behind the score, and turn the weakest dimensions into a fix-first plan.
Cited requires macOS 14 or later. Supported architecture: Apple silicon and Intel. Check About This Mac before purchasing.
Cited accepts one public HTTP or HTTPS URL, pasted HTML, or pasted plain text. URL mode retrieves one raw response rather than crawling a site or rendering it in a browser; pasted HTML is useful when the public response is blocked or JavaScript-dependent.
No. It is a deterministic content-readiness heuristic across five disclosed dimensions. Cited has no privileged access to search indexes, ranking systems or answer-engine citation decisions, and a high grade cannot promise traffic, visibility, indexing or citations.
No. Extraction, the five-part grade, detected entities and claims, recommendations and the complete report use the deterministic local path. A supported provider is optional for the narrative and answer-engine simulation.
URL fetches have a 30-second timeout and a 5 MB response limit. Analysis is capped at 2,000,000 characters, and optional simulation context is capped at 4,000 characters. Blocked, login-only, non-success or JavaScript-only pages may need pasted content instead.
Yes. The separately built Cited Direct edition permanently enables complete reports and optional simulations and excludes the App Store paywall and StoreKit code. It is a one-time website purchase with no subscription, account or trial timer.
No. The Mac App Store edition can include Apple's in-app purchase system. The website Direct edition is a separately signed build with no StoreKit purchase flow: one website purchase unlocks the complete app with no recurring charge.
The download is the complete app. There is no subscription, no locked tier, no account, and no trial timer — every feature is included.
Choose $10 for one app, $20 for two different apps, or $49 for every published app through Stripe's hosted checkout on this page. Download links are delivered on the confirmation page and by email. Each link is single-use; its exact expiry is shown in your delivery email. Keep the installer. If the link expires or a download fails, contact support@macossoftware.com with your receipt instead of buying again.
Yes. Version 1.0 is signed with a Developer ID certificate, notarized by Apple, and distributed with a stapled notarization ticket. Its published SHA-256 checksum is b0e60a5e05e296fb81cc9d04e974550debf1170f257a1f7ffa36199b5c130b2e.
Cited video tour: source signals and article analysis. Watch the video and read a list of the views it shows before choosing the app.