Skip to main content

Brand scan

Adopting a brand voice from scratch means transcribing rules a team already follows but has rarely written down. Brand scan shortens that first step: it reads a corpus of existing brand material and drafts a brand voice profile and candidate terms, which you review and edit before saving. It is an onboarding aid, not an authority — nothing it produces is enforced until you adopt it through the ordinary brand surfaces.

Brand scan runs before any bring-your-own provider key exists, so it always uses platform AI credits. The credits it spends are reported on the job as it runs.

The flow​

A scan reads the sources you give it, assembles them into one corpus, drafts a voice profile from that corpus, and extracts term candidates — then hands back a draft for review.

Sourcespaste, URL, upload, git reporead sourcesCorpusassembled + source-taggedinferVoice profile drafttone, style, vocabulary, examplesextract termsTerm candidatesterm + definition + domainreturn draftReviewedit, test, then adopt

A scan reads sources into one corpus, infers a voice profile, extracts term candidates, and returns a draft to review. Nothing is saved to the brand until you adopt it.

The scan runs asynchronously. Creating one returns a job id; poll the scan until it reports completed and read the draft it carries. The lifecycle is queued → processing → completed (or failed), and while processing the job reports a progress percentage and a phase label — reading sources, assembling the corpus, drafting the voice, extracting terms.

Sources​

A scan accepts any combination of four source kinds, assembled into a single source-tagged corpus:

  • Paste — brand copy or a style guide pasted directly as text.
  • URL — public web pages the scan fetches and reads as text. URL fetching is restricted to https and refuses private, loopback, and link-local addresses, re-checking on every redirect, so a scan cannot be pointed at internal infrastructure.
  • Upload — documents uploaded ahead of the scan. Uploads are validated against an allowlist of text-bearing formats (Markdown, HTML, plain text, CSV and TSV, DOCX, XLSX, ODF, EPUB, XML, JSON, and YAML) before any bytes are stored; unsupported files are reported back rather than silently dropped. PDF and PowerPoint are not yet supported and are rejected with an explanatory message. Per-file and per-batch size limits apply, and stored uploads are swept after a retention window so a "regenerate" during review can reuse the same files.
  • Git repository — a public https git repository, shallow-cloned; the scan reads its Markdown files.

The corpus is bounded: sources are read up to a total budget, and a scan reports which sources it read and which it skipped, so a corpus that was trimmed to fit is visible rather than silent.

What a scan drafts​

Voice profile​

The scan drafts a voice profile with the same shape a hand-authored one has — tone (personality, formality, emotion, humour), style rules (active voice, sentence length, point of view, contractions, prohibited patterns), vocabulary (preferred, forbidden, and competitor terms), and before/after examples. The draft is named to signal it needs review before it is adopted.

Each inferred section carries evidence: a confidence score and a short note citing what in the corpus supports it. The evidence travels alongside the draft so a reviewer can weigh each section rather than accept the whole profile blindly. It is a review aid, kept separate from the profile itself, so the profile still round-trips through the ordinary profile format.

Term candidates​

Alongside the voice profile, the scan extracts term candidates — terms found in the corpus, each with an optional definition and domain, deduplicated and merged with the profile's preferred terms. These are candidates for the terminology hub, not governed concepts; adopting them is a separate, deliberate step.

Review, then adopt​

A scan never writes to the brand on its own. It produces a draft; adopting it is a deliberate second action, so the separation between curation and governance holds from the very first profile.

Youmanage_brandBrand scanasync jobBrandprofiles + terminologycreate scan from sourcesread → infer → extractspends platform creditsreturn draft + evidencetest edited draft against sample textno AI costadopt: save profile, promote terms

A scan returns a draft you review; adopting it saves a voice profile and promotes term candidates through the ordinary brand surfaces.

While reviewing, you can test a draft against a sample of your own text: the scan scores the sample against the (possibly edited) draft profile using the deterministic vocabulary matcher — no AI call, no credit cost — so you can adjust the draft and see the effect before committing to it.

When the draft is ready, you adopt it through the ordinary surfaces: the edited voice profile is saved as a brand voice profile, and the term candidates are promoted through terminology. The scan itself creates neither — it only hands you a draft to carry forward.

Credits and quota​

Because onboarding happens before a workspace has configured a bring-your-own provider key, a scan always runs on platform AI credits — the same hybrid credits model that governs the rest of the platform's AI operations. A scan is refused up front if the workspace has no spendable credits, and the credits it spends (one credit per token) are metered per phase and reported on the job as tokens_used. On a self-hosted deployment with billing disabled, no credits are deducted.

Under the hood​