THE PREMISE
Music has geometry. We build inside it.
Pythagoras heard it in ratios. Kepler mapped it to planetary motion. Every composer since has been navigating the same underlying space: the relationships between notes, harmonies, rhythms, and arrangements. This determines whether music feels coherent or arbitrary, resolved or suspended, familiar or improvised.
ORIGIN
Where It Started
The Structured Harmony Engine (SHE) began with a long-running fascination: music theory, experimental composition, procedural art, and production tools. This work was forged over nearly two decades building metadata systems, machine learning platforms, and recommendation infrastructure, for industry-leading music and video streaming services. Our unique industry experience made two pressures abundantly clear:
- AI content is piling up on the work of real artists, and teams lack a clean, structured, original ground truth for model training.
- Transparency, primarily related to the use of closed, frontier models, resulted in the inability to manage each decision, and with nuance.
The question became: could a system understand music deeply enough to compose it, mix it coherently, and stay original without drawing on any specific artist's recordings?
Following years of research, we reached a conviction: symbolic music data, music captured as notes and instructions rather than a finished recording, is the best foundation for the media industry's cultural, workflow, and technical needs while protecting artists' rights.
SHE has never been trained by or on third-party audio, generative AI, or LLMs. We own the engine outright, with full control over its mechanics, rather than inheriting or appropriating someone else's work.
THE TEAM
The People Behind It
Built by people who spent years inside music and streaming infrastructure, and left to build the structured, original ground truth it was missing.
Taylor Kirch
Co-Founder & CEO
Taylor Kirch is a product leader and contemporary artist. As SHE's lead product designer and music technologist, she drove the engine from concept to production, designing its architecture and building the taxonomies of genre, instrument, mood, and rhythm.
She brings over a decade of experience at the intersection of music, metadata, and machine intelligence at companies including Netflix and Pandora/SiriusXM. She holds an MS in Information Science from the University of Illinois Urbana-Champaign.
She's a classically trained singer, with years of experience in chamber, choir, a cappella, and opera music.
Tre Tomaszewski
Co-Founder & CTO
Tre Tomaszewski is a researcher and multidisciplinary technologist whose PhD research at the University of Illinois Urbana-Champaign sits at the crossroads of cognitive psychology and AI: information networks, AI-assisted cognition, agent social interaction, and machine cognitive psychology.
Earlier, as a bioinformatics graduate student, he published research on genetic mutation detection in COVID-19 that seeded further work on the same data infrastructure.
Outside academia, he has worked across music and gaming as a designer and programmer. He has experience in original music composition and audio engineering.
SHE is the Structure. Harmony is the Space.