W26 – New Lingo.dev CLI: `lingo push` runs your engine's full localization pipeline
The new Lingo.dev CLI now runs the localization pipeline – pre-edit, human review, AI review, rephrase, back-translation, each toggled on the engine.
Toggle stages on the engine's Pipeline tab, or override per job through pipelineConfig. Pre-edit cleans typos in the source before they reach any locale. The core localization step applies your glossary, brand voice, and instructions. Human review pauses the run until your team or an external provider signs off. AI review reconciles a reviewer's edits back to engine config. Rephrase rewrites for marketing copy. Back-translation flags semantic drift.
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.
Full changelog: lingo.dev/changelog
Replies
This pipeline framing is interesting because localization failures are often not one-off translation mistakes, they’re memory problems.
A glossary term, tone rule, or product-specific phrase gets decided once, then slowly drifts across releases, teams, and locales. So the hard part is not only catching the error, but preserving the decision that made it an error.
Curious how AI review feedback reconciles back into engine config over time. Can the system distinguish between a one-off reviewer preference and a durable rule the team should carry forward?