Summary
In this chapter, we built a Python client that can interact with Google Dialogflow. Our XAI chatbot can manage alert functions in the output of a machine learning algorithm.
Before implementing our chatbot, the trained machine learning algorithm would produce outputs. The user would have to wait until the ML program was finished and then activate an interactive interface.
An XAI interface, though interesting, might come too late in a decision-making process. Hundreds of automatic decisions may have been made before the user could intervene. Even if the XAI interface provides excellent explanations, bad decisions may have been made. These bad decisions must thus be analyzed, the parameters modified, and the program run again. If the errors were not damaging, then the problem can be solved with some additional configuration. But if the errors were critical, then an XAI interaction before the machine learning program ends is very productive.
Our XAI chatbot addressed...
