Yes, if the user says something like “that’s not right”, “you were wrong”, “your answer was incorrect” or something similar, it will prompt them for a new response which gets emailed to me.
Human: Do you like eggs?
Bot: I don’t know
Human: bad answer
Bot: OK, what should I have said?
Human: I liked fried eggs
Bot: OK, so I should have said, ” I like fried eggs ” in response to you saying, ” do you like eggs “. Is that correct?
Human: yes
Bot: I’ll try to remember that. If you say ” do you like eggs ” to me again, I will remember what you told me.
Human: Do you like eggs?
Bot: I like fried eggs.
They can also do something along these lines:
Human: When I say, “Jump”, you say, “How high”.
Bot: I’ll try to remember that. If you say ” Jump” to me again, I will remember what you told me.
Human: Jump
Bot: How high
If this was a genuine example, I would include this in its responses but most of the time people just teach it rubbish like “Tim is gay. What is Tim” and so I daren’t make this process automatic.