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.

This June, we released Crowdin Dreams, that runs quietly in the background to analyze how your translators edit AI suggestions, then automatically improves glossaries, style guides, and AI prompts without any manual effort. We've also added a new glossary creation skill to Crowdin Copilot, letting you build termbases instantly from URLs or files, while the new Cursor app brings real code context into the Editor sidebar so translators never have to guess what a string actually means. For teams managing AI costs, we've introduced spending limits at the organization and user levels, plus a Logs tab that tracks every AI call for 30 days. Read this article to learn more about this and other updates.

When you manage multiple localization projects or work with always-changing content, keeping track of project health is difficult. Missing glossaries, unattached style guides, or strings without context lead directly to poor translation quality – whether you use human translators or AI. To fix this, we built Advisors. It works as a background analyzer for your localization configurations. It monitors your setup against quality standards and flags missing or under-configured resources before translations even begin.

Short, ambiguous UI strings like "Name", "Post", or "Run" are the biggest problem in localization. Is "Post" a button to publish content or a forum message? Without context, translators and AI models are forced to guess, which leads to broken UI translations and endless QA review cycles. Instead of manually typing out context descriptions for thousands of keys, you can now delegate this entire process to your local AI Agent (like Cursor, Copilot, or Claude Code). By leveraging the new Crowdin CLI context management commands and Crowdin Skills, your AI agent can automatically download your translation keys, analyze your codebase to understand what those keys do, generate precise context descriptions, and push them back to Crowdin. Based on the core workflow introduced in Context Enrichment with AI Agents, this step-by-step guide will show you how to configure and deploy this automated, agent-driven setup directly in your local terminal. <Aside title="Before automating context"> To ensure your short strings, variables, and plurals are properly captured on the AST level and sent to Crowdin via clean PO files, check out our practical guide on how to extract i18n keys and translate them via CLI using LinguiJS. </Aside>

Technical writers have long been the quiet workhorses of the software world, documenting features nobody reads, chasing developers for context, and generally operating in the background. But something interesting is happening. In the localization space, tech writers are stepping into a role nobody quite planned for them: they’re becoming the connective tissue that holds multilingual product experiences together. In a recent episode of The Agile Localization Podcast, host Stefan Huyghe sat down with Ian Cowley, Technical Writer at Salto, who lives at the crossroads of language, technology, and user experience. Based in Spain’s Basque Country and fluent in English, Spanish, and French, Ian brought a grounded, real-world perspective on why the people who write your UI strings might just be the most important players in your localization pipeline.