(Autogenerated transcript) [00:00:00] Alright, so the first thing that we are going to do is create a decision tree chatbot based on my decision tree chatbot that I already built using ES. So this is what the bot, this is how it works. You can see that it first starts with a prompt which is which programming language is right for your Dialogflow chatbot and it's going to ask the user to, it just asks the user to fill out a set of, not fill out but really like click on buttons which are yes or no answers. And based on that it will give some recommendations. So let me just walk you through what it's doing here. It's going to first ask, are you building an Actions on Google app? And let's just say that the user says yes. So you can see that it says use Node.js since it has the best documentation for Actions on Google bots. So if I were to start over and it's going to come back with that same question now, I'll say no. Then it's going to ask a question, are you a programmer? And let's say that I say yes. [00:01:00] And then it asks, do you know Node.js? And let's say I say yes again. Then it'll say, just keep using Node.js because you're already familiar with it and what's not mentioned here is also that a lot of the documentation for Node.js in general is better than or more well maintained than for the other programming languages in terms of Dialogflow. When it comes to Dialogflow documentation, you will find that the documentation for Node.js is generally superior to the documentation for the other programming languages. All right. So how exactly is this flowchart going to work? I actually have the flowchart right here if we go to the next lesson. And by the way, you can go through this material for free. So you see that this is the decision tree. This is what it's going to look like. It's going to ask about, are you building an actions on Google app? And if the user were to say yes, it's going to say use Node.js. If the user said no, it's going to ask if they are a programmer. [00:02:00] If they say yes, it'll ask if they know Node.js. Suppose they say no, it's then asking, do you know Python? And if they say yes, then you can use Python because after Node.js, that's probably the best supported language in terms of Dialogflow documentation. And then if they say no, it actually says because you can say the top two languages are Node.js and Python, the board recommends that this person learns Node.js and use it. Okay. And then on the other hand, if the user were to say they are not a programmer, it's then going to ask them if they are technical. And if they were to say no, then it's just going to say ask your programmer to choose the language because at that point, you know, the programmer is probably going to make all the choices in terms of the design of your webhook and all that, right? And if they say that they are technical, it's going to ask them if they want to learn the basics of programming. And suppose they do say yes, then it'll recommend that they use Python. [00:03:00] They ask the board, ask them to learn Python first and then use it. And then because it's the easiest language to learn. And if they say no, then it's just going to say ask the programmer to choose what language they want to use for the bot, right? So this is just a flowchart overview of how the decision tree bot works. And as you might remember from my previous material, what you have to do to keep the conversation moving forward is you have to keep setting this await underscore context name as the output context and use it as the input context for the following intent, right? You keep doing this so that you can chain or sequence these intents together. And you can have your Dialogflow ES bot once you have completed this whole thing, right? With CX, actually this all becomes, in a way, this all becomes a lot easier because all you are doing at that point is that you are just going to make sure that you represent [00:04:00] the await underscore something, right? You change this into a state or in the case of CX, they call it a page, right? A page represents a state in Dialogflow CX. So you change this await into a page. And once you have done that, you will be able to, more or less, you should be able to follow this flowchart and get this whole sequence working pretty much in the same way. And that's exactly what I'm going to do in the following video.
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