Skip to main content

Keep your source content on brand

Goal: flag forbidden, competitor, and off-preferred terms in your source content and rewrite what fails, so what goes to translation (or production) is already on-brand. This is source governance, before any translation. The profile format lives in Voice profile; setting one up takes ten minutes.

The video below walks the whole path on one repository, in one language. A drafted context graph (recipe, voice profile, vocabulary) is reviewed and committed; kapi check --strict runs as a gate over operator documentation, interface strings and a marketing page; the failures are corrected three ways in the source and once as a vocabulary decision the graph keeps, so the next check enforces what the last one passed. No server, no model, no second language.

With a voice profile bound in the project (Project Settings), the Checks view enforces it over everything the project tracks:

  1. Run the checks. Voice vocabulary findings appear alongside hygiene and length, each named by rule, located to a block, with the suggested wording.
  2. Fix at the block. Open the flagged file, correct the wording, re-run; the score climbs as findings clear.
  3. Fix the rule as well as the draft. A recurring off-brand term belongs in the profile: add it as a vocabulary rule under Context → Voice so every later check enforces it.

In a project​

Bind the profile once (defaults.voice.profile_file) and every surface picks it up: the Checks view, the assistant's loop, bare kapi check, and the ship gate's voice gate. When translating, a bound voice is also injected into the translation prompt, so target-language output starts on-brand.

Next​