Veronica Prilutskaya

Lingo.dev can now automatically provision your localization engine s context from your website: generate a glossary, translation rules, and a brand voice, then save and attach them to the engine.

When creating an engine in Infrastructure, enter your website. Lingo.dev reads the content and creates the context automatically, ready for you to review and refine. Everything stays editable. Try a representative translation in Playground before using the engine in your integrations.

For an existing engine, select Fill missing context, enter your website, and choose which missing types to generate. Types already attached to the engine are left alone. Existing context isn t replaced.

Bring your own Anthropic, OpenAI, Google, or Mistral AI key for localization. Requests go directly to the provider on your key, and the provider bills you for those tokens.

Open Settings BYOK, add your provider key, and choose that provider s models in your localization engine.

Your key is used for the engine s translation and editing steps. Your integrations keep using its glossary, rules, and brand voice, while Lingo.dev runs the localization infrastructure.

You can now send translations to human review only when they re in a language you select and score below your quality threshold. All others continue without human review.

Keep human review to selected languages

You could already use a quality threshold to send low-scoring translations to human review. Now you can narrow that rule to selected languages within the same localization engine.

For example, when introducing Japanese or working through terminology issues in German, you can send low-scoring translations in those languages to a reviewer. Translations that meet your threshold continue automatically, and your other languages skip human review.