@HelloIntento

Enabling global companies to translate 20x more on the same budget, making their customer and employee experience instantly multilingual

 San Francisco, CA
inten.to
Joined March 2016
  • Tweets646
  • Following32
  • Followers262
370Media
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.

ALT 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
21
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
13
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-translatio…

The State of Translation Automation 2026 — Intento

See which AI translation solutions meet quality requirements in each language, and compare the models, workflows, cost and speed needed to get there.

inten.to
8
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.

ALT 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
39
more replies
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
25
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.
15
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.

ALT 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
17
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
11
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.
9
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.

ALT 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
13
Both vendor landscapes and the full list of models, from Konstantin Savenkov: linkedin.com/feed/update/urn…

Translation Automation Solutions from 105 Vendors Compared | Konstantin Savenkov posted on the...

In 2018, automating translation was about choosing the "less wrong" NMT model for your content and language pair, and there were 18 vendors to choose from. Today it's about building a comprehensive...

linkedin.com
8
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-for-ge…
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.

ALT 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.

1
4
57
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%.

ALT 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
1
44
more replies
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
14
4/ Ten common claims about localization careers checked against 619 open positions at 435 companies, 22 director-level, and 308 appointments: inten.to/blog/localization-j… The 610 open positions with links: docs.google.com/spreadsheets…

Localization jobs in Q3 2026: AI labs are hiring, linguists in demand, 22 open director-level...

Ten claims about localization careers checked against 619 open in-house positions at 435 companies and 308 recent appointments, with the open positions as a spreadsheet.

inten.to
18
We've published Intento Translation Portal for ServiceNow in the ServiceNow Store. Your employees can translate text and documents in 650+ languages inside the Service Portal, with AI checks against company translation requirements. Launch details below.
Intento Translation Portal for ServiceNow: on-demand text and file translation inside the Service Portal, under company translation rules

ALT Intento Translation Portal for ServiceNow: on-demand text and file translation inside the Service Portal, under company translation rules

1
1
23
Read more on the Intento blog: inten.to/blog/translation-po…

A translation portal for ServiceNow puts shadow translation under company rules

A translation portal for ServiceNow brings employee text and file translation into the Service Portal, with company rules and a central audit log.

inten.to
8
A translation can break the rules in your brief and still outscore the correct version on COMET. On locale formatting that happens 36 to 47% of the time, in all four languages. On gender neutrality in German and Spanish, more often than not.
Cover: A good score is not a good fit — a customizable framework for requirements-based LQA. Daria Sinitsyna, Lead AI Engineer at Intento, with the AMTA Québec City 2026 logo.

ALT Cover: A good score is not a good fit — a customizable framework for requirements-based LQA. Daria Sinitsyna, Lead AI Engineer at Intento, with the AMTA Québec City 2026 logo.

1
18
The full study, and what to check instead of a general quality score: inten.to/blog/requirements-b…

A good score is not a good fit: requirements-based LQA

We scored 84,000 machine translations with COMET and with requirement checks. About half the time, COMET ranks a violation above a correct translation.

inten.to
8
Load more