Applied machine learning & IoT studio

Quiet intelligence,
built for the real world.

An applied machine learning and IoT studio. We build systems that measure something real, run where the work happens, and keep their claims small enough to verify.

4
Products
2
Deployments
Deployed with
  • Onnesha Cricket ClubAthlete Intelligence workspace
  • Prime Bank Cricket ClubAthlete Intelligence workspace
In the fieldLive
S/01

Agri Remedy

AI crop-disease scanning

Turns a drone video or a few phone photos into a field-by-field crop-disease check, with plain-language treatment advice in English and Bangla.

96%
rice model accuracy
9
diseases detected
7
crops covered
Questions

Answers, up front.

Read all
Do you deploy on premise?
Yes, and it is usually the default. Inference runs on the device or on hardware you control, so footage and records do not leave your network unless you ask them to.
How does an engagement start?
As a scoped pilot: one question, one dataset, one environment, a fixed fee and a success metric agreed before we begin. You get a working system and a written result — including if the result is that it does not work.
Who owns the model and the code?
You do. Weights, training code and deployment scripts are handed over at the end of a build engagement.
Do you work in languages other than English?
Yes. Agri Remedy ships advice in both English and Bangla, and we treat local-language output as part of the product rather than a translation pass at the end.

Have something you need measured?

Tell us what the system has to prove and where it has to run. We will tell you honestly whether we are the right studio for it.