<aside>
Rethinking development through an AI-first lens.
Creative AI Orchestration · Human-Centered Prototyping
I explore how AI can become useful, playful, and more human across software, voice, and physical devices. Right now, I use independent experiments and hackathons to turn ideas into working prototypes, directing coding agents and testing the results through a behavioral QA lens.
My background is in psychology and global game launches rather than traditional engineering. I am especially interested in human agency, shared experiences, digital companions, and technology that fits naturally into everyday life.
</aside>
<aside>
Primary Tools and Platforms: ChatGPT · Codex · Claude Code · Cursor · VS Code · Arduino IDE · ESP32 · Raspberry Pi
</aside>
<aside> <img src="/icons/slideshow-play_gray.svg" alt="/icons/slideshow-play_gray.svg" width="40px" />
</aside>
<aside> <img src="/icons/movie-clapboard_gray.svg" alt="/icons/movie-clapboard_gray.svg" width="40px" />
https://youtube.com/shorts/aOwOBazgZFE?feature=share
<aside> <img src="/icons/compose_gray.svg" alt="/icons/compose_gray.svg" width="40px" />
My first real app, built by directing AI through the whole process — design, code, and launch with ChatGPT (I did not know how to use AI IDE yet). I wanted to find out what happens when you treat AI as a team to orchestrate rather than an occasional helper. This is where "AI-native" building first started to click for me. Read the detailed showcase →
Dream Home Vibe: My First Experiment as an AI-Native Orchestrator
</aside>
</aside>
<aside> <img src="/icons/movie-clapboard_gray.svg" alt="/icons/movie-clapboard_gray.svg" width="40px" />
https://youtube.com/shorts/u6rP2D4xVG8?feature=share
<aside> <img src="/icons/compose_gray.svg" alt="/icons/compose_gray.svg" width="40px" />
A voice assistant that works completely offline — you speak, it responds, and nothing leaves your machine. Most voice assistants send what you say to a company's servers, and I was curious whether a fully private one could still feel quick and natural. So I tried building it.
Read the detailed showcase →
Kai Lite: Building a Privacy-First Voice Assistant Through AI Orchestration
</aside>
</aside>
<aside> <img src="/icons/movie-clapboard_gray.svg" alt="/icons/movie-clapboard_gray.svg" width="40px" />
<aside> <img src="/icons/compose_gray.svg" alt="/icons/compose_gray.svg" width="40px" />
Most AI assistants reset the moment you close them. Kai Desktop is my attempt at the opposite—it keeps a long-term memory and reflects on past conversations to adjust how it responds. I also built mechanisms to protect my privacy: the core agent runs entirely on a private home desktop so your personal data never touches the cloud, and I can swap out the local LLM whenever I want. When I need more power, I can intentionally leverage cloud AI via API commands. It's the idea I keep coming back to: an AI that grows alongside you instead of starting over each time. 📄 Read the showcase →
</aside>
</aside>
<aside> <img src="/icons/movie-clapboard_gray.svg" alt="/icons/movie-clapboard_gray.svg" width="40px" />
<aside> <img src="/icons/compose_gray.svg" alt="/icons/compose_gray.svg" width="40px" />
Groundmarker began with a simple problem: an inspector should not have to remember which camera-roll photo belongs to which spot on a hand-drawn sketch. During an inspection, the app lets them draw the site, mark a finding, and take photos directly from that marker—automatically preserving the connection between what was found and where. Once the inspection is complete, Groundmarker turns everything into an organized, client-ready PDF. Built first for crawlspace inspections, it can support any field where visual evidence and precise location need to stay connected from the jobsite to the final report. Groundmarker was also my first time taking part in a hackathon.
📄 Read Groundmarker on Devpost
</aside>
</aside>
<aside> <img src="/icons/movie-clapboard_gray.svg" alt="/icons/movie-clapboard_gray.svg" width="40px" />
https://www.youtube.com/shorts/f1TcxHoT26s
<aside> <img src="/icons/compose_gray.svg" alt="/icons/compose_gray.svg" width="40px" />
Dotchi is a completed, local-first interactive digital pet built around an ESP32 screen. Touching or tilting him changes his eyes, on-screen motion, and little sounds. He notices everyday sounds, while a dedicated music mode turns the energy of music into a falling-star display. After a period without interaction, he can settle into Deep Rest and show a small clock once the time has synced. Radar sensing also lets him notice when someone leaves or returns. From a local settings page on my phone, I can set reminders and change his Wi-Fi connection. The full firmware remains private.
</aside>
</aside>
<aside> <img src="/icons/movie-clapboard_gray.svg" alt="/icons/movie-clapboard_gray.svg" width="40px" />
https://youtu.be/MiqNuhlzTzI?si=JXtKaHnYnlWwUNUp
<aside> <img src="/icons/compose_gray.svg" alt="/icons/compose_gray.svg" width="40px" />
MuseMirror turns a makeup look someone admires into something she can preview, recreate, and make her own. It combines YouCam visualization with a voice-guided mirror experience, structured reflection, and memory that is saved only after the user reviews and approves it. The React and TypeScript PWA completed a full live Android rehearsal with 163 passing tests.
📄 View the Devpost project → MuseMirror on Devpost
</aside>
</aside>
<aside> <img src="/icons/movie-clapboard_gray.svg" alt="/icons/movie-clapboard_gray.svg" width="40px" />
<aside> <img src="/icons/compose_gray.svg" alt="/icons/compose_gray.svg" width="40px" />
Spotlight is an artist-led discovery and learning platform for makeup, hair, and fashion. People can discover an artist's work, experience selected creator-owned looks on their own photo through Perfect-powered interactive Cards, and then choose whether to explore the artist's courses or related products.
The hackathon version has been submitted. Its transformations are real; the artists, courses, products, and commerce shown in the demo are clearly labeled as fictional.
📄 View the Devpost project →
</aside>
</aside>
<aside> <img src="/icons/movie-clapboard_gray.svg" alt="/icons/movie-clapboard_gray.svg" width="40px" />
Absent: Frozen Heart cover art
<aside> <img src="/icons/compose_gray.svg" alt="/icons/compose_gray.svg" width="40px" />
A short browser-based interactive mystery about memory, guilt, friendship, and choice. When everyone else forgets Eva, Michael follows a pink heart hairpin into a frozen world of damaged memories. Players explore three interconnected locations, gather evidence in his journal, and reach one of three endings shaped by the truths they uncover. Made for the Month of Horror: Frozen Heart game jam; playable in a desktop or mobile browser.
🎮 Play Absent: Frozen Heart on itch.io
</aside>
</aside>
<aside> <img src="/icons/light-bulb_gray.svg" alt="/icons/light-bulb_gray.svg" width="40px" />
The Familiar is becoming a small tabletop hamster built around a 3D-printed inner body. Its head will turn from side to side, and its moving hands are being designed to gently hold a person’s hand or finger. Sensors will help it respond with small motions to touch, nearby movement, and sound. I am currently designing the body and exploring how its behaviour might develop.
</aside>
For any inquiry, please email emilylindev [at] gmail [dot] com