Content drafting
Sign in, bring a content brief from the Content Brief Builder, and get a section-by-section draft: every sentence carries its claim state (bound, gap, stance or no-claim), and where it applies a bound or stance sentence is also marked with the layer its evidence came from; the sentences a human must verify list their references in the verify list; a separate model call checks which must-answer questions the draft covers, and a verify list names what a human must still confirm before publishing.
A GenGrowth sign-in and a content brief are required
Bring an explicitly confirmed Content Brief v2/v3, a shared GEO Brief v1.1 or a valid legacy SEO v1 export. The confirmed versions produce Draft v2 sections that cite only allowed competitor or owned-page excerpts and profile facts; PAA is not factual support. Shared GEO briefs keep their own evidence contract and server-side ownership verification.
No saved draft, no scheduled run, no content score, no originality claim, and no credit claim. A section whose evidence references fail validation is reported as failed rather than quietly rewritten, and an unfinished coverage check never shows a question as covered.
This tool does not accept a bare keyword. Without a brief there is nothing for the coverage check to measure against.
Bring a brief from the Content Brief Builder, paste its exported JSON, or upload the .json file.
Confirmed v2/v3, shared GEO v1.1 and historical SEO v1 imports are accepted up to 256 KB. Each version's cross-references and fingerprint are checked before loading.
Confirm the H2/H3 outline and page decision in Content Brief Builder first. The page strictly checks that revision and its fingerprint; incomplete or altered exports are refused, not repaired.
Each writable outline section is a checkbox. Profile facts reach the model only where you allow them: not at all, in the gap-angle section only, or throughout.
Sections are generated with bounded concurrency, timeouts and attempts, following the confirmed H2/H3 and create/update plan. The model marks each sentence's claim state; the server checks its section-scoped page and profile references and reports invalid sections as failed.
With a fresh context, a separate model call reads only the generated sections and the brief's must-answer questions and judges each one covered, partial or not covered. If that call does not complete, coverage is shown as unavailable.
The draft follows the confirmed H2/H3 order. Optional sentence annotations link to observed page units or profile facts; gaps remain visibly unverified. Switching annotations off does not change the verification list or exported prose.
In v2, every question is checked against all successfully generated text, even if its planned section failed or was skipped. Covered, partial and not covered remain separate; a failed check is unavailable, not zero. No score.
Sentences supported by a single observed page, profile-only claims, gaps and stances — each naming its section and references. These checks validate evidence structure, not factual truth.
The screen, the copied Markdown and the exported JSON come from the same result. Any section can be rerun on its own; the whole result is replaced and re-fingerprinted.
Once you enter the published URL, the page and the primary keyword are carried to the checker inside this browser, never through the URL bar.
No. Without a brief there is nothing for the coverage check to measure against, so the page accepts only a Content Brief Builder export.
Confirm a generated v2/v3 brief in Content Brief Builder first. A legacy GEO report is not a shared GEO Brief v1.1; use the current GEO Brief export for that workflow. Altered exports, broken references and unknown schemas are rejected; valid SEO v1 exports remain accepted.
Bound: the sentence cites an allowed observed page excerpt or declared profile fact. Gap: the model found no supporting evidence. Stance: a position in the designated gap-angle section, citing profile facts. No claim: a connective sentence. None is an automatic fact-check.
Confirmed v2/v3 briefs support the language choices in Content Brief Builder, including Chinese, Japanese, Korean and Thai. Prose length is measured in words or characters and excludes headings. Legacy v1 imports keep their original language restrictions.
Neither. It does not publish, write to a CMS or generate images, and the draft lives in your browser tab until you copy or export it. Refresh the page and it is gone.
This page does not show or promise a credit price. Any future price must be defined for this specific tool before the interface claims it.
GenGrowth