Rebuilding an AI Chatbot Language
Learning Platform
I built an intuitive and guided AI language learning chatbot experience
AcquiLingua's AI tutor holds real conversation in your target language, calibrated to your level. I redesigned the interface into a guided, gamified flow with interactive games.
- Built the Chatbot interface into a guided, progress-oriented experience using Figma and Codex.
- Conducted 4 user tests and synthesized findings to pinpoint interface friction points with the old design.
- Audited 7 competitor AI chatbot and language learning apps to benchmark onboarding and gamification patterns.
- Collaborated closely with engineering and business stakeholders to balance their priorities with user needs.
The interface was confusing and
complicated to users
Many functions built into the app were hard for users to understand, ranging from lesson selection to emoji usage to the buttons on the main chatbot interface. All of it created friction for users and led to fast drop‑off.
Core interactions were complicated to users
Lesson selection, emoji usage, and the buttons on the main chatbot interface were all unclear, causing users to hesitate, misclick, or abandon tasks partway through.
Modernize the UX without losing the emoji niche
Stakeholders wanted the UX improved while keeping emojis as a core product differentiator, plus new SRS-based flashcards and in-between activities to diversify practice.
Chat
Lessons
Speech Settings
VoiceAcquiLingua, a fun and intuitive AI language learning chatbot
AcquiLingua's AI tutor holds adaptive conversations calibrated to your level. I rebuilt the interface around it, adding guided lesson paths, inline correction feedback, and interactivity to make practice more engaging.
AcquiLingua: An AI Tutor That Teaches Like a Person
Real conversation, guided every step
Polly opens with a friendly first message, so new learners start chatting right away instead of facing a blank screen.
A guided sentence-builder turns each new phrase into a hands-on exercise, with instant feedback on every attempt.
Let's see what other competitors are doing
I audited 7 AI language apps — including ChatGPT, Talkpal, Pingo AI, and Duolingo — for onboarding, training, and gamification patterns, plus an internal audit of AcquiLingua to pinpoint friction points.
What users told me
I ran 4 user tests on the existing interface to see where people actually got stuck. Testers struggled to tell whether the AI had corrected their message, weren't sure what the buttons on the main chat screen did, and found the visual design dated compared to other language-learning apps they'd used.
"When it revised my message, I couldn't even see my original message so I don't know what I did wrong."
"I think it could look more modern. This is confusing as to how this would be better than any other language learning chatbot."
"A little antiquated, not a modern website even though there are aspects that are. The landing page doesn't look good and the globe isn't obvious to me that this is where I choose a language."
"Put the settings in the main nav bar so we don't have to go back. I wish there were suggested questions the chatbot asks. I didn't expect it to correct my grammar, and it's a little offensive."
Building a prototype faster than ever before
Key redesign opportunities
I used Figma Make to convert the design into code and then bringing it into Codex to actively work on the product. I had quite a bit of difficulty with technical bugs that were popping up as I was developing features, and also with inconsistent type and spacing across pages. In order to remedy this, I set my design system to fix these issues and have a set of limitations.
How it started
Vocab Collection
VocabularyThe AI was using its own stylization and not properly implementing icons and things such as spacing, centering, and different UX features. Those that were all important to the experience were all construed in different places, and it also didn’t follow the visual design system made from my Figma file.
An AI language learning chatbot that motivates you to learn
The new chatbot now has onboarding, fast response times, chat customization options, and gamification for its users.
Polly opens with a friendly intro message, so new learners start chatting right away instead of facing an empty screen.
Grammar corrections appear as a gentle inline note under Polly’s reply, without breaking the conversation.
Talking speed, tone, and teaching style are all adjustable, so the chatbot can match how each learner wants to be taught.
A guided sentence-building exercise lets users tap word chips into place and get instant feedback before moving on.
Note to self: set rules first
This was my first time building a live product connected to my design, and it felt extremely rewarding to see the redesign come to life. I worked closely with stakeholders throughout the process and learned a lot about aligning their expectations with users' expectations of an AI language learning chatbot.
