Expand to New Locales

Max PrilutskiyCEO & Co-Founder1 min read

Add a target language to an existing engine with model chain, brand voice, and rules configured in one conversation.

The workflow#

"Add Brazilian Portuguese to our engine. Use Claude Sonnet as primary, GPT-4.1 as fallback. Informal tone, 'você' not 'tu'. And make sure our product name 'Acme Hub' stays untranslated."

What happens:

  1. The assistant reads the engine's current configuration to understand the pattern
  2. Creates the model chain for en → pt-BR with ranked fallback
  3. Adds a brand voice profile specifying informal register with 'você'
  4. Adds a glossary entry marking "Acme Hub" as non-translatable
  5. If the engine is limited to specific target locales, adds pt-BR to them

What gets configured per locale#

ComponentWhat to specify
Model chainPrimary model + fallback(s) for the locale pair
Brand voiceRegister (formal/informal), pronoun choice, tone
RulesLocale-specific rules (punctuation, spacing, formatting)
Glossary extensionsTerms that need locale-specific localizations or protection

Common patterns#

Locale variants#

"Add pt-BR. Copy the model chain from pt-PT but change the brand voice to informal."

The assistant reuses the existing Portuguese configuration as a starting point, adjusting only what differs for Brazil.

CJK languages#

"Add Japanese. Use Claude Sonnet — it handles Japanese well. Brand voice: polite-formal (keigo for user-facing, plain form for developer docs). Add rules for honorific consistency."

Languages with complex register systems benefit from explicit brand voice and rule configuration.

Right-to-left languages#

"Add Arabic. Same model chain as other languages. Add a rule about mixed LTR/RTL content handling in UI strings."

The assistant configures the locale and adds RTL-specific rules.

After extending#

Once the locale is live:

  • Localize representative content through the localization API or the CLI
  • Review the output against the new rules
  • Watch AI Reviewer results on early requests in the dashboard