Introducing the new Lingo.dev CLI. Every lingo push runs your localization engine's full configured pipeline server-side – the same pipeline the Async Localization API runs when you submit from code.
Every push wraps the core translate step with whatever stages your engine has enabled: pre-localization AI edit to clean typos in the source before they reach any locale, the core localization step with your glossary, brand voice, and instructions, post-localization human review by your team or an external provider, post-localization AI review to reconcile a reviewer's edits back to the engine config, rephrase for natural copy for marketing surfaces, and a back-translation check for semantic drift. Content translated from code and content translated from lingo push go through the same stages, in the same order, with the same engine config.
A run that includes a human-review stage can wait days before it lands, so the CLI splits a job into lingo push and lingo pull – pull re-attaches to the most recent push and downloads outputs from any machine, including after the original terminal was closed.
