Polhus, used Crowdin’s AI and DatoCMS integration to localize their website. 75% of translations were AI-generated and ready for publication, saving $80,000 and hours of work. With AI and human review, they achieved high-quality translations for 1.6 million words in 7 languages. Curious about how they did it? Read the full story in the post.

In November 2024 our team closed 246 tasks from the task manager and completed 398 deployments. This month, we’ve rolled out several new features and improvements aimed at making your work at Crowdin better. You can now tag and manage strings meta information directly from the Screenshots tab, get AI-suggested metadata in the Simple Term Extractor app, and use Backtranslation app to check translation accuracy even when you don't speak the target language. We’ve also introduced an automated screenshot capturing for Web and Mobile, better AI proofreading, enhanced LQA annotations in the LQA app, and more. Let’s explore these updates in detail.

As we've already discussed in our previous post, localizing at the design stage is crucial for companies working for a global audience. In many industries like SaaS, e-commerce, and mobile app development, products frequently need updates. Design-stage localization helps prevent design issues caused by varying text lengths and different language structures. With Crowdin for Figma, automated synchronization between the designers, developers and translators means faster time to market, as well as fewer bugs. Teams can ensure that translations are accurate and fit within the localized design. Want to try it out for yourself? Let's take a look at how everything works. We're not yet diving into the technical details -- you'll find them here. For now, let's give you a high-level overview.

This month, we’re rolling out some powerful updates. From a revamped Context Harvester CLI with a context quality check to new Crowdin Store apps like Language Fallback Configurator and an AI debugging tool. For complex projects, we’ve introduced cross-review approval for tasks and improved savings visualization. Plus, discover multilingual terminology extraction with AI that continuously refines your glossary across languages as your project is translated. One AI model builds a multilingual glossary, while another uses this glossary to pre-translate. In October alone, our customers used over 10 billion AI tokens (11.6 billion, to be exact) when our team closed 517 tasks from the task manager and deployed 475 times. Enjoy checking out the latest features.

Design and development teams working on global products face the challenge of localizing content for different markets while keeping the workflow smooth and efficient. Here's where Crowdin, a Figma translation plugin, comes into play. It empowers designers to work hand-in-hand with translators, smoothly integrating localization into the design and development process – no need to wait until a translator gets back to you. With the ability to send texts for translation directly from Figma and review translations in context, Crowdin for Figma makes localized design faster, more accurate, and less prone to errors.

Lightning fast, continuous localization. Decent quality. Super affordable. All automated with no humans in the loop. This guide shows you how to build a multilingual product on autopilot using Crowdin. The workflow is tech stack agnostic and suitable for web, mobile and desktop applications, as well as their documentation and marketing materials. Best of all, AI translations would be contextual. The AI will have all the information it needs to produce the best possible translations. And in the future, you would still be able to bring in a human linguists to improve translations, if you needed to. Prerequisites: You have an internationalized web or mobile application. This means that all translatable texts from the UI have been extracted into the resource files. The implementation time of this guide is 30 minutes.