Crowdin リソース

If you have ever managed a localization project with tens of thousands of strings, you know the struggle: finding duplicate keys, locating untranslated strings with specific tags, or fetching clean Translation Memory (TM) segments manually takes hours. While Crowdin provides powerful querying tools like CroQL (Crowdin Query Language) and GraphQL, crafting precise query expressions isn’t always intuitive. What if you could ask an AI coding assistant (like Claude Desktop, Cursor, or GitHub Copilot) to do that for you? In our previous guide on automating i18n context with AI agents, we covered how AI can automatically generate context descriptions for translators. But AI agents can do much more than just enrich JSON files. By combining AI Agents with Crowdin’s open-source croql and graphql agentic skills, you can also turn natural language questions into valid, optimized Crowdin API queries in seconds. Here is how to set it up and leverage it in your automated localization workflows.

Localization is one of those functions that everyone agrees matters right up until it’s time to fund it. Then suddenly it’s a line item to squeeze, a checkbox to tick, a problem to throw AI at and hope for the best. In a recent episode of The Agile Localization Podcast, host Stefan Huyghe sat down with Matt Grotenstein, Vice President of North America at GTE Localize and host of the LocReset podcast, to discuss why the gap between localization strategy and execution remains so wide and why AI isn’t the magic fix executives want it to be.

Manually maintaining localization files and inventing arbitrary keys for every button or title is a big bottleneck for developers. With Lingui, you don't need to write JSON keys manually. Lingui leverages compilation macros to extract text directly from your UI code, while the Crowdin CLI automates the cloud synchronization and translation loop. In this guide, you will learn how to configure a fully automated CLI-driven localization pipeline: from extracting new strings in your terminal to pushing them for translation without leaving your codebase.

What will you do if your marketing team finds a typo in a promo banner or a missing translation string? Let us imagine how you are doing that in a hurry – patch the codebase, run the CI/CD pipeline, and wait for the App Store review team to approve a hotfix. If you are running a fast-moving app, waiting 24-48 hours for a copy change means losing users and missing time-sensitive promos. Standard Flutter localization guides show you how to set up static .arb files, and that’s it. That doesn't cut it for production. This guide walks through implementing a scalable localization architecture in Flutter using Provider and integrating Over-The-Air (OTA) updates for real-time delivery. You will be able to push translation fixes instantly to your users without app store updates.

You have seen the symptoms a hundred times. A product calls the same feature three different things across its UI, help docs, and marketing site. A support article contradicts the onboarding flow. An AI-generated translation cheerfully invents a term that doesn’t exist in any human glossary. Everyone notices the mess, but almost nobody thinks about the discipline that’s supposed to prevent it. That discipline is terminology. And according to Rita Prazeres Gonçalves, terminology expert and founder of The Language Worker, it might be the most critical yet invisible job in the entire localization industry. In a recent conversation on The Agile Localization Podcast with host Stefan Huyghe, Rita made a compelling case for why terminology deserves far more attention, and why the current AI boom might finally be giving it the spotlight it’s needed for decades.