Bilingual builder · EN / 日本語 · Japan

Why does this problem
still exist?

I build technology — from model to interface — for the people existing systems forgot to design for.

Scarlett Whisnant — software, AI, and the questions people would rather avoid.

01 — who

The person behind the build

I'm not the person who's sure. I'm the person who tries when it matters — even when it looks hopeless — and then I make it mine.

→ Talk to people. Don't assume.
→ Agency shouldn't require a technical background.
→ It's never the user's fault. Fix it.

I moved to Japan at eleven with no Japanese, went through public school entirely in Japanese, and got into a national university the domestic way — no exchange-student lane. I get fluent fast in systems that weren't built for me.

That's the through-line in everything I make: human communication, institutional failure, and AI as a tool for handing people back some agency. I build the model and the interface — and when my understanding deepens, I go back and rebuild my earlier work instead of hiding it.

Off the screen, I run. I started from genuinely terrible — the dreaded PE distance run was my nemesis — and picked it up anyway because it felt impossible. Training through a knee injury toward a 5K now, a marathon eventually. Same move as everything else here: pick the hard thing, start from zero, make it mine.

02 — work

Built, broken, rebuilt

/01

Burnout Predictor

proof — I build AI from model to interface, and rebuild as I learn

A local-first desktop app that reads facial expression from a live camera feed in real time and nudges you to step away when stress reads high. I trained the model, wired the pipeline, and built the GUI. I'm currently rebuilding it in public — I caught a weight-loading bug myself by logging per-frame confidence, and the rebuild is where I prove the growth rather than paper over it.

PythonPyTorchMobileNetV2FER2013OpenCVtkinter
rebuilding in public
GitHub →
/02

Voice-SCaNN

proof — I'd rather rebuild the right thing than polish the wrong one

A generative-AI course-feedback system for my university's faculty. Sixty days, a confident wrong assumption, and one week left when user testing told us we'd solved the surface, not the problem. I pushed the team to pivot to a system that actually surfaces honest feedback for students, professors, and admins. It shipped, earned an official university press release, and a professor is presenting the work at a conference.

Generative AIService designUser researchFigma Make
team · press release
Press release →
/03

AAC Communication App

proof — talk to people; it's never the user's fault

An open-source web app for people with developmental disabilities — customizable cards plus freehand drawing, with text-to-speech. I tested it with autistic users and the results were genuinely mixed: some loved drawing, others said it wasn't for them. That's the point of the project. The honest takeaway I'm carrying forward: listen more before building more.

Next.jsTypeScriptReactWeb Speech API
open source
GitHub →
03 — ask

Ask the site about me

live assistant · answers as Scarlett · AI, so not perfect
Hi — I'm an AI that answers questions about Scarlett's work and the way she thinks. Recruiter, curious, or just poking around? Ask me anything.

This assistant is itself one of the projects — an LLM with a system prompt written in Scarlett's voice.

Let's talk.

Looking for an early-career role where technical depth meets human-facing work. US citizen — no sponsorship needed.

GitHub ↗ LinkedIn · soon Email · soon