Irati Hurtado

Linguist in Conversational AI | Language Data Analyst | Conversation Designer

irati-photo.jpg

I’m a designer with a background in linguistics, currently working as a Conversational AI Designer at Replicant. I specialize in creating intuitive, user-centered digital experiences—whether through voice, chat, or content-driven interfaces.

I started out in academia, where I explored the psycholinguistic dynamics that shape human conversation. This foundation deeply informs my current work: translating complex language patterns into practical, human-centered design solutions.

Over the years, I’ve designed digital experiences for sectors like finance, healthcare, retail, and hospitality, and I’ve worked across a range of environments, from early-stage startups to large tech companies. My experience spans conversation design, content design, and product thinking, always with an eye on usability, clarity, and user needs.

As a Spanish–English bilingual and certified translator, I’ve also led multilingual design efforts, especially for the US and LATAM markets, making sure the user experience feels seamless no matter the language.

Outside of work, I enjoy writing blog posts that explore the intersection of language, tech, and design. When I’m not designing or writing, you’ll probably find me cooking, working out, or off exploring a new part of the world.

I’m always happy to connect with other folks in design and tech. Feel free to reach out!

Projects

cover-content-design.jpg
Content Design
cover-conversation-design.jpg
Conversation Design
cover-analytics.jpg
Language Data & Analytics

Latest Posts

Aug 3, 2026

Text is the new interface and not everyone speaks it well

For most of computing history, the interface stood between you and the machine, and good UX meant designing that interface so a user's skill level stopped mattering much. LLMs quietly broke that deal. The interface is now a text box, and "prompt engineering" is mostly just writing well: knowing what you want, saying it clearly, structuring it so someone (or something) can follow your logic, etc. In other words, literacy, in the plain sense of being proficient in reading and writing a language: a decent vocabulary, a feel for sentence structure, the ability to organize ideas logically, comprehension sharp enough to respond well to what you read. Read more

Jul 24, 2026

Human-like isn’t the same as good: Rethinking Conversational AI’s North Star

There's an assumption baked into most conversational AI roadmaps that nobody really questions anymore: more human-like is better. Friendlier persona, more natural turn-taking, more emotional mirroring, all treated as obvious improvements, the same way "more accurate" or "faster" would be. But is that actually true? Or have we been chasing a proxy for quality and calling it the goal itself? Why human-likeness doesn't always work Push a chatbot far enough toward human-like, and something strange happens: it can start working against you. Read more

Jul 10, 2026

Stop blaming the interface: Conversational AI fails in the user’s head first

A lot of conversations with AI products go wrong. But if you dig into why these interactions really fail, you'll often find that the problem isn't in the interface at all, but it's psychological and it starts in the user's head, before they've even typed a word. Everyone walks into a conversation with a chatbot, voice assistant, or AI companion already carrying a set of expectations: about how smart it is, whether it can be trusted, whether it's " Read more
All Posts

Let's get in touch

Feel free to reach out for collaboration, questions, or just to say hi 👋

 

 

Thanks for reaching out! 🙌