W39 Product Update: Localization infrastructure is now in one place
Localization infrastructure is now in one place.
Infrastructure is where you configure localization engines, models, context, pipelines, and everything else that controls how your content gets translated.
Here's what you'll find there:
Localization engines. Create separate localization engines for different kinds of content. Your product UI, help center, and legal content can each have their own setup, models, context, and localization pipeline.
Models. Choose a model for each language pair and set a fallback. If the primary model is unavailable or rate-limited, Lingo.dev moves to the next one instead of failing the request.
Context. Glossaries, rulesets, and brand voices belong to your organization, so you can reuse them across localization engines. When they overlap, they're applied in order: glossary terms first, then rules, then brand voice.
Localization pipelines. Add stages around translation depending on what the content needs: clean up the source, send it for human review, reconcile edits, rephrase the translation, or translate it back to check the meaning. Different localization engines can run different pipelines.
Playground. Compare a localization engine with a bare model on the same text, or run two localization engines side by side to see how different configurations behave.
Logs. Each localization engine now has its own Logs tab. See what it served and which model handled the request, including when it fell back to another model.
Open Infrastructure and give each kind of content its own localization engine.
Replies