The problem with having a plugin AI system is that It will be very generic and might not cover the area of interest that you are working on.
Good news is that all pretrained models can be trained specifically for one's use case, but to achieve a good accuracy one will need a lot of data which can either be generated or gathered.
Once the data is in place and selection of pre-trained model has been made, it is just matter of time before you can have a good - great system working for you.
One can keep training the system every time it the system runs into a dead end to make it more robust and aligned to the task at hand.

Let me know if you'd like a detailed orientation on the above approach.

regards,
Deepesh