Comment by mohaps

the basic difference in approach was to switch the earlier approach of

if (conditionA && conditionB && !conditionC) cache_it()

to

hey look, an item with featureset X is cacheable while one with featureset Y is not.

This reflects in the API which is just two calls predict() and feedback()

this simplifies the integration code and is easily debuggable even in the face of changes.