MQ Flow: heating and ventilation that learns each room
The AI HVAC system we build with our partner Mifimi: a physics model of comfort, learning per room, and the cheapest levers first. Now going into a faculty building in Belgrade.
Cases
Proof, documented.
We're a young studio, and we won't pretend otherwise. These are the projects we can show, written up honestly, including one that did not work. As client projects close, and clients agree to be named, they appear here as case studies with verified numbers. How we build is documented separately, on work notes.
Quince AI is incredibly professional and responsive to both stated and unstated needs, presenting solutions that have the potential to make a big difference in both resource efficiency and behavior.
Cases
Method and regulation notes now live on their own page: read the work notes →
Sorting used textiles with AI, NIR, and a recycling framework
A circular economy project with Wargön Innovation, funded by Vinnova: image recognition and near infrared spectroscopy fused into an automated sorting process that sorts toward real buyer demand.
Building Qonverge, our AI talent matching platform
How we built an AI talent matching platform for consulting firms and recruiters, now in production at Itmotive and Braha IT. What we built, what we ruled out, and where we stopped the AI.
ReQloth: the AI textile marketplace we built, and the market that vanished
We launched an app that valued used clothes from a photo and matched them to local buyers. Then a regulation reshaped the market. What the technology proved, and what we misread.
Our standard
What a case study
What a case study
must contain.
A project earns a place on this page only when it can carry a name and a number. Every case study we publish follows the same four-part structure, and until a project can be told that way, it stays a work note.
Every case study answers
- Problem: the business question the client actually needed answered, and the constraints around it.
- Approach: what we built, what we ruled out, and why.
- Deployed result: the system running in production, on infrastructure the client controls.
- Verified metric: the number that mattered, measured against production data.
The rules we publish by
- Every case study names the client, with their written permission, or not at all.
- Every number is verified in production before it appears here. No projections dressed as results.
- No anonymised logos, no invented statistics, no testimonials we wrote ourselves.
- Until a project meets this bar, it's published as a work note: method, not marketing.
Start the conversation
Be the first name on this page.
The fastest route to a case study is a project that works. Tell us the problem and the constraints, and we'll say honestly whether machine learning fits.