... 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 ... ... wait days before it lands, so the CLI splits a job into lingo

... localization engine's Reviews tab runs the analysis in the background, so a run of low scores quietly produces suggestions waiting in the Suggestions tab. Suggestions are also addressable from code through the Localization Engine Suggestions API https://lingo.dev/docs/api/engine-suggestions free-text feedback like the German copy sounds too stiff goes in the same way and returns the same kind of structured suggestion. Also this week: Prompt caching. The stable parts of every translation prompt system prompt, instructions, brand voice ... ... reuse the LLM provider's prompt cache as cache tokens https://lingo.dev

... Lingo.dev GitHub App runs continuous localization on any repository, straight from git. Install it from your organization settings, commit a .lingo/config.json

... glossary item three weeks ago, even if the actor is no longer on the team. Also this week: Organization invites in the MCP server. Adding a teammate or checking pending invites no longer means switching to the dashboard the Lingo.dev MCP now exposes invite creation and listing, so an AI assistant ... ... handle it alongside engine configuration. Recursive globs in i18n.json. The CLI's include and exclude now match files across nested directories, so a single pattern can cover a deep folder tree instead of listing paths by hand. Full changelog: lingo.dev

... engine's  Pipeline  tab, or override per job through `pipelineConfig.rephrase`. Best fit: marketing copy, landing pages, and other surfaces where reading like a native original matters more than staying close to the source phrasing. Full changelog:  lingo.dev/changelog ...

... edit the translation inline and submit. The job resumes with the reviewer's output and continues through the remaining pipeline stages, with the engine's glossary, brand voice, and instructions visible as context. Full changelog:  lingo.dev/changelog ...

... switch it back on. - Usage in every localization response. Each response now includes the model used, the LLM cost, and the localization token cost useful if you're attributing translation cost back to an end user. Full changelog: https://lingo.dev/changelog Comment from Simran Kumar(@simran_kumar): I appreciate this update because I've always preferred keeping my personal projects separate from team or service-related integrations ...

... which  glossary terms ,  instructions , and  brand-voice rules  the engine retrieved plus the glossary review reasoning. Cost-by-model breakdown.  See how much you spent on each model, in tokens and in dollars. Full changelog: lingo.dev/changelog ...

... Credit balance alerts.  Dashboard indicator shows current balance; emails fire at 20% remaining and at $0. ISO 5060 classification visible in   triage .  Each triaged job surfaces the standardized error class alongside the agent's suggestions. Full changelog: lingo.dev/changelog ...

... translation check .  Translates the final output back into the source locale and compares. The agent flags semantic drift by severity and auto-adjusts on major or critical drift. Turn on what you need, leave the rest off. Full changelog: lingo.dev/changelog Comment from Raj Kumar(@new_user___0932026a86e905cf4b2b7f7): I've worked with similar processes, and I think the pre-edit stage often gets overlooked. In my experience, cleaning up the source content early can reduce review time later ...

... drill into any failed locale. The  async localization API  ships jobs in parallel across every target locale, retries on failure, and webhooks back when done now you can watch it happen instead of reconstructing from logs. Full changelog: lingo.dev/changelog ...

... provisioning  is an async API that takes a fresh engine plus a few URLs or content samples and auto-configures the brand voice, glossary, and instructions for you. Multi-step manual engine setup collapses into one call. Full changelog: lingo.dev/changelog ...

... shipped Per-engine   AI Reviewer   assignment.  Attach different reviewers to different engines instead of one set for the org. Organization-level timezone setting.   Reports  display in the timezone you configure for your org. Full changelog: lingo.dev/changelog Comment from Anthony Adams(@anthony_adams_): The reviewer reasoning is probably as valuable as the pass/fail result itself. Knowing why something failed helps teams improve much faster. Comment from Daniel Henry(@daniel_henry4): I like the pass/fail visibility ...

... actual configuration instead of evaluating in a vacuum. Review filters in translation logs.  Filter the  translation logs  by reviewer and score threshold e.g. any reviewer below 80%, or a specific reviewer below a given percentage. Full changelog: lingo.dev/changelog ...

... Glossary   CSV upload.  Bulk-import glossary items from CSV with conflict resolution on collision, so re-imports don't duplicate entries. Jira and GitHub now connect over OAuth.  Both integrations switched off API-token setup. Full changelog: lingo.dev/changelog ...

... Lingo.dev  v1.0 introduces  localization engines   stateful translation APIs that you configure once and call from backend code,  MCP , or  CI/CD . Before today, every team that wanted consistent terminology, on-brand tone, and per-locale rules wired it up by hand: a glossary in one repo, brand-voice notes in a Notion doc, prompt scaffolding hard-coded into the app. The engine collapses all of that into a single addressable thing. What ... ... launch Localization engines .  Configure models, brand voice, instructions, and glossaries per locale. LLM models .  Pick the model per locale, with ranked fallback chains for reliability. Brand voices .  Linguistic

... Most people don t have a productivity problem. They have a system problem . Choosing between Notion vs Todoist vs

... TolleCode for VS Code is now live (v0.1.0 Beta) I just released the first beta version of the Tollecode vscode

... strategists who are tired of surface-level advice and want frameworks that actually move rankings, pipeline, and product narrative. Each piece is built from the inside out grounded in real campaign data, semantic SEO, and the kind of linguistic precision that most content shops skip. What you'll find inside: Deep-dives on content strategy for AI and SaaS brands Frameworks for topical authority, intent mapping, and content systems Real case studies including a 250% organic traffic lift from ... ... client work Practical editorial thinking that bridges linguistics

... just exposure, but the degree to which AI treats your brand as a credible source . Share of Voice (SOV): Represents your brand s voice share within AI narratives the probability that AI mentions your brand rather than a competitor when answering a topic-related question. Sentiment: Captures the emotional tone of AI mentions positive, neutral, or negative showing how AI portrays your brand. Together, these four metrics answer the two most fundamental GEO questions: How frequently does AI mention ... ... brand? and In what tone and context is the brand represented? 1.2 Trends and Competitor

... Maybe more. Here's the painful truth: Your site is translated. Your AI visibility isn't. When a German user asks ChatGPT in German about your category, you're invisible. When a French prospect searches Perplexity in French, your competitor shows up. Translation AI visibility. And it's costing you. The Data We tracked 200 SaaS companies with multilingual sites at Rankfender. Market % Visible in Local AI Answers US (English) 64% UK (English) 58% Germany (German) 22% France (French ... ... Founder: B2B SaaS, 8M ARR "We spent 40k translating our site into German and French. Beautiful work. Native speakers. Perfect messaging. Six months later, we checked German AI answers about our category. We weren't there. Not once. Our competitor

... creators of Lingogrind , a small startup we re building to help people learn German and prepare for official exams (Goethe, telc, TestDaF). We noticed that many learners struggle with two things: structured exam preparation consistent practice with real exam-style exercises So we started building Lingogrind

... Rankfender , we've identified clear patterns. Certain content types get cited 3x more often than others. Here are the 7 content types that win AI citations with real examples you can steal. First, the data: Content Type Citation Rate (vs. average) Best For Comparison pages 3.2x higher "X vs

... Minute Audit Step 1: Keyword Selection (5 minutes) Choose 20 keywords to audit: 10 branded keywords: Your company name Your product names Your founder/CEO name Your flagship features 10 non-branded keywords: "[Your category] best tools" "[Your category] alternatives" "How to [solve problem you solve]" "[Your category] vs

... Performance can degrade as pages grow larger and more complex. And critically, the usefulness of a page often depends on the behavior of a community rather than on intentional editorial structure. Qeeebo takes a different path. A Static, Structured Alternative Qeeebo is built as a structured library of questions and answers rather than a collection of ongoing discussions. Each page is designed to deliver a clear answer quickly, without requiring users to scroll through debates, comments, or tangential replies. Instead ... ... changing threads, Qeeebo uses static pages generated ahead of time. These pages are organized around individual questions, grouped by topic, and delivered through a global content delivery network. This architectural choice influences nearly every aspect of the platform. Qeeebo vs