Dialogflow stability [closed]

Question

We have a number of chatbot instances we are testing on Dialogflow, some of which are developmental ones and others which are locked down production instances. We do extensive testing to make sure our responses are consistent and correct on a frequent basis.

We've noticed that even on a locked down instance where we aren't changing anything, the intent and entity responses from Dialogflow on an instance can change over time, and in some cases become incorrect.

This suggests that the underlying training algorithm is changing, and that instances are being auto-trained when such changes are released. Does anyone know if this is the case? If so, are there any suggestions about how to maintain a stable instance?

Answer 1

I am in the same situation. We have turned ML off and auto expansion off because when we go into the entities we sometimes get test data being added in there.