
Mariia Ivakhnenko
Co-founder
Co-founder of Transept. Three degrees in English Language and Literature — Kyiv, Ostrava, and a year in Salzburg — and a Ukrainian native who lives most of her writing life in English. Came into AI as a prompt engineer, then product and lifecycle marketing. She writes semi-fictional stories about real people, and keeps circling the question of what gets lost between languages.
9 articles

From Traditional Chinese to Amazon: one author’s first novel in English
Passerby David wrote a science fiction novel in Traditional Chinese, translated it into English with Transept, and published it on Amazon. This is how he did it and what he checked by hand.


The fun facts that weren’t
We make short videos about how languages say everyday things. Every fact has to pass two sources first, and some of the internet’s favourite language facts didn’t.


We love AI. But…
We build with AI every day, and we read what people say about it every day too. Here is where Transept stands on AI, and the four rules our AI works under.



I translated my novel with ChatGPT, Claude, Gemini and Google Translate. Here’s how it went
We translated nine chapters of my novel, 15,000 words, from English into Ukrainian with Google Translate, ChatGPT, Claude, Gemini and Transept, then counted every name that changed spelling, every dropped line and every friend who suddenly went formal. The chatbots kept names straight in one long conversation and lost them in fresh chats.


No italics, no spaces, no あなた: what Japanese taught us about localization
We localized Transept into Japanese in a day and thought ten earlier languages had prepared us. They hadn’t. Fake italics, a space two style standards disagree on, words that mean something else in Japanese, a katakana name with two spellings, and why our assistant must never sound like an anime heroine.


Can AI detectors spot an AI translation? We tested Pangram and GPTZero
We translated passages of a novel between Ukrainian, English and Chinese with AI and ran them through Pangram and GPTZero. Every sample came back human-written, a plain ChatGPT translation included. Here is why, and why you should still disclose an AI translation.



Ten languages in three days: field notes from localizing an AI translation product
We localized Transept into German, Ukrainian, Chinese, Portuguese, French, Spanish, Czech, Italian, Polish, and Turkish in one long weekend, using machine translation the way we tell our users to use it: with context, terminology decisions, and human post-editing. These are the plural rules, register flips, typography inversions, and hreflang lessons we collected on the way.


Literess as an agent: the editor who remembers your decisions and does the work
Most AI in translation tools is a chatbot bolted on the side. We built Literess as an agent instead — grounded in the same decision-context memory the product runs on, and able to take real actions on your behalf, always with your confirmation.


Welcome to The Journal
Why we started writing here, what you can expect to find, and a small invitation to come back.

