Reasons, not just scores
A prediction without its reasons is a guess with a confidence interval. Every output Kaimei produces comes with the inputs that moved it, in the output's own units.
About Kaimei
Models should be able to explain themselves.
Kaimei means to clarify, to elucidate, to reveal through investigation. We build the tools that let teams do exactly that with the machine-learning models they already run.
Why we exist
Accuracy is not accountability.
Machine learning now decides who gets a loan, which claim gets a second look and what a patient is told to watch for. Most of those models are black boxes, judged by an accuracy number and trusted until something goes wrong.
A model can be right for the wrong reasons. Two models can agree on an answer while believing opposite things about the world. A production feed can start sending a field in the wrong units and nothing in a test suite will notice, while every prediction quietly moves.
Kaimei exists so that every one of those models can answer the question the people affected by it are entitled to ask: why? We attach to the models teams already have, in the frameworks they already use, and give every prediction its reasons, every model its anatomy, and every deployment a watch.
解明
解
kai
to untie, to solve
明
mei
bright, clear
kaimei · to clarify, to elucidate, to reveal through investigation
What we believe
Four commitments that shape every feature we ship.
Exact where possible, honest where not
When a model is small enough we enumerate rather than sample, and say so. When we approximate, the method and its limits are part of the response, not a footnote.
Private by design
We never store your model file. Upload shapes only, or keep the model behind your own endpoint, and Kaimei still does its job without your weights leaving home.
Open by default
An Apache-2.0 client, a plain REST API and examples that run end to end in public notebooks. If a capability is described on this site, you can reproduce it yourself.
How we work
A small technical team, one public example, and no claim we cannot show.
01
Everyone builds
Everyone who works on Kaimei writes code and reads the research. The person who answers your issue is usually the person who built the feature.
02
One dataset, every claim
Every capability is exercised on the same public example before we describe it. What the documentation shows is what the product does, with the outputs committed.
03
Part of Qian Capital
Kaimei AI is developed and operated as a platform of Qian Capital, which lets us build infrastructure at the pace infrastructure deserves.
Build this with us.
We are a small team working on a hard, important problem. If that sounds like your kind of work, or you want Kaimei on your models, we would like to hear from you.