在 Lyft 使用 AI 扩展本地化

For years, Lyft’s localization infrastructure relied exclusively on human translation. While this model usually ensured excellent quality, it was bound by multi-day turnarounds and costs that scaled linearly with every new language. For the few languages Lyft initially supported (Spanish, Portuguese, and French), these limits were acceptable.

多年来，Lyft 的本地化基础设施完全依赖人工翻译。虽然这种模式通常确保了优秀质量，但它受限于多日周转时间，并且成本随着每种新语言线性扩展。对于 Lyft 最初支持的少数语言（Spanish、Portuguese 和 French），这些限制是可以接受的。

However, Lyft’s expansion goals quickly outpaced what traditional workflows could support. Lyft’s recent Québec launch required compliance with Bill 96 (legislation mandating French-first user experiences) which demanded faster turnaround than multi-day cycles allowed. Simultaneously, the Lyft Urban Solutions (“LUS”: Bikes & Scooters) division sought to expand into European markets, requiring six new languages. The business need had changed as we now needed to move faster without sacrificing quality.

然而，Lyft 的扩张目标很快超过了传统工作流程所能支持的范围。Lyft 最近在 Québec 的推出需要遵守 Bill 96（要求用户体验以法语为先的立法），这要求比多日周期更快的周转时间。同时，Lyft Urban Solutions（“LUS”：自行车和滑板车）部门寻求扩展到欧洲市场，需要六种新语言。业务需求已经改变，我们现在需要更快地推进，同时不牺牲质量。

This post explores how we re-architected Lyft’s Translation Pipeline to leverage AI alongside linguist oversight and ultimately unlock new market launches. We will walk through context injection, decoupling content generation from evaluation, implementing guardrails, and treating prompts as version-controlled production code. The new pipeline reduces translation latency from days to minutes while maintaining the fidelity required for legal compliance and brand integrity.

这篇文章探讨了我们如何重新架构 Lyft 的 Translation Pipeline，以利用 AI 结合语言学家监督，最终解锁新市场发布。我们将逐步介绍上下文注入、将内容生成与评估解耦、实施护栏，以及将提示视为版本控制的生产代码。新管道将翻译延迟从几天减少到几分钟，同时保持法律合规和品牌完整性所需的保真度。

Note: We will walk through our batch translation pipeline — used for 99% of app and web content — which targets a 30-minute SLA for 95% of translations. We also support real-time translation (e.g., ride chat) which...