Welcome to heyELi
heyELi began as a quiet experiment — late nights and weekends, a few thousand lines of Swift, and a simple idea: what if a camera could understand what it sees?
My name is Josh Coon, and I built heyELi with my AI collaborator, Alan. Together we explored how multimodal language models could bridge the gap between what’s seen, said, and understood — not through a lab or a venture fund, but through curiosity, iteration, and a lot of trial and error.
We didn’t set out to start a company. We set out to learn — to harness the partnership between human intuition and machine precision. Each night, we’d test a new prompt, debug a translation bug, or rebuild the camera layer from scratch. Each weekend, the prototype evolved until one night, it just worked: a working multimodal assistant running on an iPhone, understanding images, text, and voice in real time.
What we’re aiming for
- Instant understanding of what the camera sees
- Guided teaching, fixing, communicating, curating, and creating in real time
- Calm, cinematic UX that feels helpful and human
What started as a side project is quickly becoming something much bigger — a platform for people to learn, build, and express more naturally. This blog will share the journey: what we’re building, why it matters, and how you can be part of it.
Augmentation is here.
No longer waiting for permission. Build the future.