... Glossaries, rulesets, and brand voices now live at the organization level and attach to any engine. Build a glossary

... queries that got zero clicks. Those are the useful ones, because they are people who saw us and did not think we were the answer. Here is a live one from a fragrance site I run. We published a glossary entry titled "Eau de Toilette". Here is what people actually typed to reach it: "eau de toilette perfume", "is eau de toilette perfume", "what is eau de toilette spray", "is eau de toilette for men", "edt fragrance", "define edt perfume ...

... edits a translation whether in-house or through an external provider the localization engine compares the change against what it first produced. When the same fix recurs across jobs, or a correction clearly sets a term, it proposes the glossary, instruction, or brand-voice edit behind it. Apply writes the change into the engine, and the next translation runs with the fix in place. Suggestions can now be approved or dismissed in bulk select ...

... rethink the problem. A database schema can tell a model where the data lives. It cannot explain how a business thinks. So we rebuilt QueryPanel around four ways companies can teach the system: database annotations, their own business glossary, trusted SQL examples, and tenant specific context. The real test came while implementing QueryPanel for a customer. New questions kept coming. Each one exposed another gap. We kept developing the product around what happened in their actual environment, rather than ...

... built-in  AI Reviewers  ship: a  glossary reviewer  and an  instructions reviewer . Toggle on the glossary

... triage workflow  reads any Jira ticket about a bad translation, looks at the offending output, and proposes the actual fix in the  engine config : a  glossary item  to add, an  instruction  to tighten, a  model config  to adjust. Review the suggestion, accept or edit it, and the engine is fixed for every future translation not just the one that was reported. Also shipped AI Reviewers   now receive the same context ... ... localizer saw.  Brand voice, instructions, and glossary

... 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's in the launch Localization engines .  Configure models, brand voice, instructions ... ... glossaries

... 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 to engine config. Rephrase rewrites for marketing copy. Back-translation flags semantic drift ... ... machine, including after the original terminal was closed. Full changelog: lingo.dev/changelog Comment from Amir Mehrabi(@amir_mehrabi): This pipeline framing is interesting because localization failures are often not one-off translation mistakes, they re memory problems. A glossary

... Audit logs are now available an append-only record of every state-changing action in your organization. Each change to engines, glossaries, instructions, brand voices, AI reviewers, API keys, members, and roles is captured with the actor, action, target, and request context. The log lives in the dashboard and filters by user, action category, target, and date so you can see exactly who created, updated, or removed a glossary

... Localization Engine Suggestions are concrete edits to a localization engine a glossary entry, an instruction, or a brand-voice change proposed by the platform from its own AI Reviewer verdicts. When reviews on a translation come back low, the platform suggests a specific edit to the localization engine's glossary

... structural metadata rather than translatable content stay verbatim across target locales and bypass the LLM entirely. Logs show the context that produced each translation.  Open any request in the Log tab and you can see exactly which  glossary terms ,  instructions , and  brand-voice rules  the engine retrieved plus the glossary

... async localization API  fans out a single localization request across every target locale in one POST and delivers results via webhook. Source payload in, job IDs out, webhook fires per locale as each finishes. Also shipped Glossary   CSV upload.  Bulk-import glossary

... locale. The async localization pipeline runs rephrase right after the core localization step. An AI agent rewrites the translation preferring local equivalents over literal renderings, keeping placeholders, variables, tags, and formatting exactly as-is, and applying your engine's glossary, brand voice, and instructions the same way the core localization step does. Downstream stages human review, post-edit, back-translation see the rephrased output and continue from there. Toggle it on the engine's  Pipeline  tab, or override ...

... review shows the source next to the AI translation approve it as-is, or 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 ...

... balance dips below the threshold translation CI runs stop failing on empty balances. Also shipped New   Reports   charts: instruction adherence and terminology coverage.  Track over time how often translations follow your configured instructions and apply your glossary terms. 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 ...

... target locale. Post-localization human edit .  Sends the translation to a qualified human translator. The job pauses on a webhook until the edit returns. Post-localization AI review .  Reconciles the human output against the engine's  glossary ,  brand voice , and  instructions . Back-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 ...

... Engine 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 ...

... startups beyond just launch traction. Comment from ctrl-dev(@sazzz): Just launched Prismiq on Product Hunt today, an AI study tool built entirely on Vercel. Turns any YouTube video, PDF or website into summaries, flashcards, quizzes and a glossary. Vercel made the whole deployment side effortless. Excited to see what comes out on the 16th Comment from Brett Axler(@brett_axler): Honestly, Vercel has been the most powerful tool in my app creation journey right alongside Claude. I have tried ...

... 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

... today is a good day to mow the grass, or what kind of forecast makes for a perfect hike. I stopped chasing generic weather traffic and started chasing intent. Then I pushed it further by creating a weather glossary. I built pages around weather terms people search when they are confused, curious, or trying to understand what they are seeing outside. Things like haze, drizzle, humidity, wind chill, and severe weather alerts. Every search became a chance to help someone ...

... alerts that warn you if you're overspending. 4. Master Your Money (Knowledge Hub) Financial independence is complicated we make it simple. Deep Guides: Step-by-step tutorials on Tax Strategies (France/UK/CH) and ETF investing. AI Assistant: A smart glossary that explains jargon like "Safe Withdrawal Rate" instantly. 5. Plan Your Retirement (Decumulation) It s not just about saving; it s about spending safely. Our Retirement Planner simulates your post-work life year-by-year ensuring you never ...

... Comment from Anna Kasumova(@anna_kasumova): @sanskarix  thank you friend. We are live today! Comment from Anna Kasumova(@anna_kasumova): What it does Translates from two source languages at once (e.g. RU + EN any others). Supports your existing glossary so AI uses your preferred terminology. Validates strings (placeholders, variables, punctuation). Manages projects, users, and roles for teams. Runs on any LLM (OpenAI, DeepSeek, etc.) just plug in your API key. Comment from Anna Kasumova(@anna_kasumova): Why it matters ...

... Creative Industries"). Here s the step-by-step pipeline running completely autonomously: 1. Podcast Topic Input (Human Input Node): You provide the topic idea. 2. Research Agent: Scours the web for key trends, statistics, expert opinions, glossary terms, and discussion points relevant to the topic. It generates a comprehensive research report. 3. Scriptwriting Agent: Takes the research report and drafts a full, engaging podcast script, complete with segmented content blocks, intro/outro music cues, and host dialogue. 4. Editor Agent: Acts ...

... essentially the software analysts, and the AI is the developer. Why not send SRS-prompts? Functional requirements (what the software should do) Non-functional requirements (performance, security, database, etc.) Use cases or user stories Constraints and assumptions Glossary of terms Business logic User flows and interactions Comment from Ray luan(@ray_luan): @taniabell  Not yet, hope it will code better Comment from Ray luan(@ray_luan): Great points Gabe! I think curor and Bolt.new are targeting developer as audience ...