How would you compare it to something like Landr or Ozone for mastering?
The problem I have with the AI mastering is it seems to be a bit clumsy with making the master fit the song. A lot of these tools just have simple buttons like "low, medium high", and seem to default to really squashing the dynamics to achieve maximum loudness. I have worked with both human mastering engineers and AI mastering, and I would say a decent human mastering engineer is noticeably better at feeling out the songs and finding the right balance.
We're focusing more on the mix down part as that's more objective and less subjective and Landr/Ozone already exist so we're not starting off specializing in mastering. With additional time/funding what I'd like to build is the ability to let the user specify a specific reference track and not just an artist for the AI to use as a reference.
To your question though, it's a chatbot so tell it you want your track to sound like eg Polo and Pan, it'll look for ways to enhance it in their style rather than a simple small/medium/large knob. It'll load one of the built-in mastering chains and tweak the settings on those, or if you have a preference, you can tell it that too.