Kveck
Tired of AI that thinks every idea you have is a good one?
The models are trained to be liked. They answer confidently about things they do not know, and they almost never say no. We build the layer around them: it decides what the model gets to see, checks what it writes, and leaves the decision to a human.
In pilot
An AI advisor on your own material.
It reads only the sources you have approved, numbers and source references are checked against the source before anyone sees the answer, and when it cannot find the answer it is instructed to say so rather than guess. We are testing the advisor in CanWeApply and exploring a few collaborations on organisations' own material. Scope and conditions are agreed before testing starts.
Let us have a coffee.
We answer ourselves. If we are not right for you, we will say so in the first conversation.