Intento@HelloIntento
Nov 6
We received a lot of questions and feedback on the 2026 State of Translation Automation, and added an executive summary. Let us know if this is useful. What is still missing? inten.to/state-of-trans…
Executive summary of The State of Translation Automation 2026, 10 points: 1. Translation quality depends on the model and its harness. 2. Translation quality means meeting a set of requirements. 3. More demanding translation requirements often need more complex solutions. 4. Automatic post-editing alone reduces translation errors by just 7%. 5. Quality assessment and targeted repair reduce errors by 54%, but increase costs. 6. Choose the simplest solution that meets your translation requirements. 7. LLM solutions offer lower costs and fewer errors than MT engine solutions. 8. Real-time translation comes with a quality trade-off. 9. The trade-off between quality, cost and speed differs by language. 10. Benchmark results are a starting point for a production solution.
0
0
0
10
Intento@HelloIntento
Oct 30
Our new blog post shows how AI workflows in our latest Trados Enterprise connector handle technical documentation, medical device instructions and marketing copy, with steps explained for each content type. Link in the first reply.
Example Intento workflow for technical documentation and product marketing. In the Trados Enterprise workflow template, the Intento Translate step runs between TM Match and human translation, in paragraph translation mode. Inside it, ten steps: extract glossary terms, mark protected content, swap in placeholders, translate with an MT engine, post-edit with an LLM, check tags and placeholders, retranslate failed segments with a failover LLM, restore tags and fix case, apply language rules, and put protected content back.
1
0
2
26
Intento@HelloIntento
Oct 30
Replying to @HelloIntento
The full post: inten.to/blog/ai-transl…
0
0
0
10
Intento@HelloIntento
Oct 29
Two EU laws apply in 2027. Machinery instructions that go online must stay available for at least 10 years in the languages each EU country requires, and the Cyber Resilience Act adds security guidance to the instructions of connected products. Link in the reply.
Two EU Laws Will Keep Translation Teams Busy After Launch. What changes for manuals, security updates, and translation teams. A circle of twelve EU stars above balanced scales labeled EU Machinery Regulation 2023/1230 and Cyber Resilience Act 2024/2847, surrounded by Latin letters.
1
1
2
35
Intento@HelloIntento
Oct 29
Replying to @HelloIntento
The full post: inten.to/blog/eu-produc…
0
0
0
4
Intento@HelloIntento
Oct 28
Our Trados Enterprise connector has a new release: AI translation workflows now get the full document with every inline tag, can take as long as they need, and run in one of three modes per language pair: segment-accurate, paragraph or subtitles.
inten.to/language-hub-f…
A Trados Enterprise workflow template, English to Spanish, with the Intento and Trados Enterprise logos joined by a connector. Step 1 is Translation Memory Match. Step 2 is Intento Translate, with three modes, Segment-accurate, Paragraph (selected) and Subtitles, an example AI workflow of Translate, LQA and Repair, the note "Waits until the AI workflow is complete", and checks for inline tags, terminology and tone of voice. Step 3 is post-editing and review, or delivery.
0
0
0
20
Intento@HelloIntento
Oct 16
The 2026 State of Translation Automation is live today, and this year it's an interactive website, not a PDF. Choose your translation requirements, a target language and what to optimize for (quality, cost or latency), and see which solutions should work for you.
Card: The State of Translation Automation 2026, Intento annual industry report, previously The State of Machine Translation. 57 AI models and MT engines, 229 different solutions, 10 translation quality requirements, 100 target languages.
1
0
0
29
Intento@HelloIntento
Oct 16
Replying to @HelloIntento
Inside: which solutions meet Basic, Standard and Advanced requirements in each language, how prompts, glossaries, quality checks and repair change quality, cost and speed, and where automated quality assessment is reliable and where the evidence is limited.
1
0
0
17
Intento@HelloIntento
Oct 16
Replying to @HelloIntento
We evaluated 229 different solutions built from 57 AI models and MT engines, translating from English into 100 languages against 10 requirements in three levels of translation quality. The report: inten.to/state-of-trans…
0
0
0
9
Intento@HelloIntento
Oct 10
After you specify your requirements, the next problem is making automatic translation meet them. For each language we use a solution complexity ladder: start with the simplest solution, often the fastest and cheapest, and add complexity and context until it meets them.
Card: solution complexity ladder from the 2026 benchmark, State of Translation Automation 2026, eight levels with the simplest at the bottom. 1, off-the-shelf NMT: an MT model as is. 2, adjusted NMT: native parameters such as glossary and formality. 3, off-the-shelf LLM: an LLM with a translation prompt. 4, adjusted LLM: RAG for dynamic business context. 5, fine-tuned models, NMT and LLM: not in the 2026 benchmark. 6, two-step solution: NMT or LLM, then automatic post-editing. 7, multi-step: translate, LQA gate, bounded repair. 8, multi-agent systems: agents that own different requirements cooperate. Each level adds context and usually costs more to build, run and maintain.
1
0
0
39
Intento@HelloIntento
Oct 10
Replying to @HelloIntento
One level above are two-step workflows, usually NMT with an APE step for the context NMT can't handle, or an LLM with an extra step against hallucinations. Multi-step comes next: in the benchmark, a translation step, an LQA gate and a bounded repair of the LQA findings.
1
0
0
25
Intento@HelloIntento
Oct 10
Replying to @HelloIntento
When requirements don't fit into a single prompt or need complex trade-offs, we use multi-agent systems, where AI agents that each own a set of requirements cooperate. We used them for gender neutrality. On Oct 13 we publish what each level takes in price and latency.
0
0
0
15
Intento@HelloIntento
Oct 9
Automating translation now means building a solution that meets your requirements, instead of choosing the "less wrong" off-the-shelf model. Building the harness around the models is iterative, every iteration needs evals, and one black-box 0–1 score can't do that job.
Card: 10 translation requirements from the 2026 benchmark, State of Translation Automation 2026, in three levels. Basic, for any company in this market: 1, general translation quality, MQM-based LQA minus the subjective requirements. Standard, for every company, with its own rules: 2, terminology, 3, tone of voice, 4, tags, 5, Unicode character integrity, 6, locale conventions, 7, HTML entities, 8, valid JSON, 9, spacing at tag boundaries. Advanced, for some companies and use cases: 10, gender neutrality.
1
0
0
17
Intento@HelloIntento
Oct 9
Replying to @HelloIntento
In the 2026 State of Translation Automation we evaluate against 10 requirements in three levels, as we do for clients. Basic: general translation quality, MQM-based LQA minus subjective requirements. Standard: terminology, tags, formality, formatting, Unicode.
1
0
0
11
Intento@HelloIntento
Oct 9
Replying to @HelloIntento
Advanced requirements like gender neutrality may drive a translation away from the most accurate and fluent one, so the LQA has to understand which MQM violations they make necessary. On Oct 13 we publish what each level takes in price, latency and harness complexity.
0
0
0
9
Intento@HelloIntento
Oct 7
In 2018 there were 18 MT vendors to choose a model from. Today 105 vendors of MT and LLMs supply the building blocks of a translation solution, and in the 2026 State of Translation Automation we benchmark 57 models from 37 of them. We publish the report on 13 October.
2018: choose the less wrong model. 2026: build a solution that meets your requirements. 18 MT vendors in 2018, 105 vendors of MT and LLMs in 2026.
1
0
0
13
Intento@HelloIntento
Oct 7
Replying to @HelloIntento
Both vendor landscapes and the full list of models, from Konstantin Savenkov: linkedin.com/feed/update/ur…
0
0
0
8
Intento@HelloIntento
Oct 6
Our new Genesys app translates chat and email, and it can check a reply for offensive or harmful content before the support agent sends it.
inten.to/language-hub-f…
A customer writes in French, “Ma commande n’est pas arrivée”, and the support agent reads “My order hasn’t arrived”. The support agent replies “It ships tomorrow”, and the customer reads “Elle sera expédiée demain”. Between them, a card with the Genesys and Intento logos, and checks for terminology, tone of voice, content safety, and email plus chat.
0
1
4
68
Intento@HelloIntento
Sep 21
1/ After the study of what people said about the localization job at LocWorld55, we went through what employers do, the open in-house positions and the people they appointed over the summer. The full analysis and the list of positions that are still open are in this thread.
Localization jobs in Q3 2026. AI labs are hiring, linguists in demand, 22 open director-level positions. 619 open positions, 308 recent appointments, 22 director-level seats. A donut of 927 new localization jobs by role type: translators and linguists 36%, management 20%, program and project 19%, engineering and i18n 7%, media production 6%, quality and LQA 4%, AI, MT and data 2%, other 6%.
1
0
1
44
Intento@HelloIntento
Sep 21
Replying to @HelloIntento
3/ Four in ten appointees came from outside localization.
Most director seats went to insiders.
Engineering is one record in fifteen.
Europe has the largest share of the jobs.
One posting in four is remote.
1
0
0
14
Intento@HelloIntento
Sep 21
Replying to @HelloIntento
4/ Ten common claims about localization careers checked against 619 open positions at 435 companies, 22 director-level, and 308 appointments: inten.to/blog/localizat…
The 610 open positions with links: docs.google.com/spreadsheets/d…
0
0
0
18
Load more