CCAI Vaccine Bot Demo

(Autogenerated transcript)

 Alright, so in this chapter we are going to take a look at how to handle conversation topic changes in Dialogflow CX and for this I am going to take an example of a YouTube video demo which has been posted by the Google Cloud tech channel where they provide a demo for the contact center AI vaccine hotline bot and it's actually supposed to be a demo for the contact center AI technology which is not exactly the same thing that we are using in Dialogflow it's a little different but it's actually a good illustration of a case where the user changes the topic. So let's take a look at the interaction you can go and just search for the phrase CC AI vaccine hotline and I think you should be able to pull up that video if not I will leave a link below this video also and this is how the conversation goes. So the user first asks is the vaccine free and the bot is going to respond with an answer yes it's free then they ask do vaccine contain animal based ingredients and the bot says

 no and then the third question is am I eligible for the COVID vaccine. Now unlike the previous two questions the third one requires that the bot answers it's not like a single conversation turn answer because the bot has to collect some information from the user it's like a decision tree chat bot right. So the bot first asks are you a healthcare worker in the ICU etc etc and the user says no and then it asks are you first responder the user says no then it asks are you either over 65 years old or under 65 with co-morbidities and then the user says no and then it asks we are down to the final question it asks are you an essential worker of any kind when the user says no for that the bot is going to say okay you can take the vaccine in phase 5 okay. Now the user says where can I get the vaccine again they have changed the conversation topic

 one more time and this time the bot has to get a different kind of information from the user it needs to get input from them about their zip code the five digit zip code. Once the user provides that five digit zip code then it's going to say based on this information your closest vaccination location is pharmacy A and so on and when this happens usually there's going to be a database lookup which means that it's usually going to call the webhook of some kind and then the user says is there some other place on location and the bot says yeah the next location where you can get a vaccine would be for my pharmacy B and when the user says actually I prefer a hospital the bot says the nearest hospital where you can get the vaccine is so and so. Finally the user says I want to talk to a representative and then the bot is going to say okay hold on while I transfer you the one thing that I want to notice here or rather I want you to notice here is that after that whatever comes in the demo in the demo video

 is all pure contact center AI technology and that's not of interest to us for this particular course. So what I'm going to do is just stop with this particular just with this conversation over here and you can go and take a look at the full video to get the complete picture if you want and there is a couple of things that I want to mention as we start this chapter the first is that I will have a copy of this video I'm sorry I'll have a copy of this agent blob file which associated with this and you can download it before you watch the other videos in this chapter and the second thing is that these are the way I construct the agent the pages and the transitions and all that that's not the only way that you can do it you can there are some other ways to implement the same ideas and what I would

 say is that once you get a good understanding of the basics which you should be able to by if you have gone through all the previous chapters you should feel free to modify the flow that I have to make it work in the way that you want I think that there's no hard and fast rules about how to design these conversation flows and because Dialogflow CX does provide you with a lot of options in terms of handling pages and states and transition routes and all that there is more than one way where in which we can build this particular part so in the next few lessons I'm going to show you how I have built this part.

About this website

BotFlo1 was created by Aravind Mohanoor as a website which provided training and tools for non-programmers who were2 building Dialogflow chatbots.

This website has now expanded into other topics in Natural Language Processing, including the recent Large Language Models (GPT etc.) with a special focus on helping non-programmers identify and use the right tool for their specific NLP task. 

For example, when not to use GPT

1 BotFlo was previously called MiningBusinessData. That is why you see that name in many videos

2 And still are building Dialogflow chatbots. Dialogflow ES first evolved into Dialogflow CX, and Dialogflow CX itself evolved to add Generative AI features in mid-2023