EdTech / Language learning - 2023–2025

VocabularBuilder

An iOS app for building your own vocabulary lists - from a film script, a textbook, a song - and testing yourself against them until the words stick.

Role
Design and engineering
Platform
iOS mobile app
Scope
UX research, UI design, AI-powered features
Year
2023–2025
VocabularBuilder home screen showing folders of word lists next to a profile screen with rank and streak progress
The home screen - folders of word lists, one per source - next to the profile screen tracking rank and login streak.

The problem

No fixed course, no fixed vocabulary

This app doesn't teach a set curriculum. Every list is built by the person using it, out of whatever they're already reading or watching - a film script, an economics book, a UX writing book, a song. I started with research into how people actually retain new vocabulary, not just how they look a word up, and that research pointed at the real risk: users add a word once and never come back to it.

The design problem was less "how do we teach vocabulary" and more "how do we get someone to reopen a list they made three weeks ago, and how do we make that list still make sense to them when they do."

Home screen with folders named after their source material, a word list inside the Margin Call film folder, and a swipe-to-delete row
Folders named for their source, a list open inside one of them, and the swipe-to-delete action on a saved word.

Approach

AI to look words up, not to run the lesson

The interface follows iOS guidelines for navigation and interaction, built for small screens with a clear hierarchy between a folder, a list and a test. Working alongside the mobile developers, I designed the AI-assisted word search, the folder structure, and the testing system as one connected flow rather than three separate features bolted together - the AI's job is to speed up adding a word, not to decide what the user should learn.

A vocabulary built from whatever you're already reading. Not from a syllabus.

Marketing composite showing the profile, achievements, testing list and word-search screens of VocabularBuilder
Profile achievements, the folder list ready to start a test, and the AI-assisted word search - the three screens a returning user actually lives in.

Adding a word

Search the dictionary before typing one out

Typing a word into search runs it against a built-in dictionary first: "esoterica," "esotropia" and "esophagus" show up as matches, each with an "add word" action that fills in the definition automatically. A word already sitting in the list is marked "Already in list" instead of being offered again. Only when nothing matches does the app drop the user into a manual form - term and a hand-typed definition - so writing your own definition is the fallback, not the default.

Manual word creation form, AI-assisted search results for a partial word, and an empty search state offering manual creation
The manual entry form, live search results against the built-in dictionary, and the fallback screen when a search turns up nothing.

Process

One loop, from launch to a saved result

  1. Sign in

    App launch branches to sign-up or log-in, both handled through Apple ID or Google.

  2. Add a word

    Search checks the built-in dictionary first; a match fills in the definition, no match falls back to a manual entry.

  3. Organize

    The word lands in a folder - general, or one named for the book, film or song it came from.

  4. Test

    A test pulls from that folder's words in mixed question formats, and the result only saves if the test is finished.

User flow diagram showing sign up or log in, the main folder page, the add-word decision tree checking the dictionary before falling back to manual creation, and the path into a test
The flow behind that loop: a word search checks the folder, then the wider dictionary, before ever asking someone to define it themselves.

Testing

The same folder, several question shapes

Starting a test from a folder - "Margin Call film," 125 words - opens a numbered sequence that doesn't stick to one question type. Some prompts show a definition or a sentence built around the word, with four options to pick from; others drop into a free-text field where the user has to spell the word themselves, with a "skip" if they're stuck. Trying to leave before the last question triggers a confirmation that the result won't be saved - a small piece of friction aimed at the person who's three questions in and about to bail.

Testing screens: folder list with start-test actions, a multiple-choice sentence question, a multiple-choice definition question, a free-text spelling question, and an exit confirmation warning the result will not be saved
Folder list ready to test, a sentence-based multiple-choice question, a definition-based one, a free-text spelling prompt, and the exit warning that the result won't be saved.

Design decisions

Three choices built around coming back

Premium upgrade screen with monthly and annual pricing, profile screen with login streak and achievement progress bars, and settings screen with daily goal and subscription options
The premium paywall - monthly at $4.99, annual at $42 with a 30% saving - next to the profile and settings screens that carry the streak and achievement system.
2
Pricing tiers - monthly and annual
30%
Saved by paying annually instead of monthly

Outcome

A vocabulary that remembers where it came from

What shipped is registration, folder-based word lists, an AI-assisted add flow with a manual fallback, mixed-format testing, and a profile built around streaks and achievements, sitting behind a monthly or annual subscription. Later design passes cut the number of steps to find information, enlarged buttons and controls, added clearer navigation paths and made the text easier to read - changes that came out of testing the app with real users rather than guessing at what would help.