Why I use the cognitive training chatbot as a case study

Just like Dialogflow CX is a great tool for learning the basics of Prompt Engineering, the Cognitive Training chatbot is a practical use case for the same goal. And combining them will speed up your learning.

If you look at the flow diagram of the Generative AI prompt, you can see that it is possible to combine intent-based question answering with generative question-answering in Dialogflow CX.

All by itself, this might not seem like a big deal.

But if you try to build this flow using the GPT API, you would have to manage the state of the conversation by yourself. And even if you do, the GPT API does not provide a way for you to then analyze the questions and answers in the context of the flow diagram in the same way that Dialogflow CX does.

But even more important: when something goes wrong, you need a way to deterministically handle it (e.g. a predefined Fallback Intent behavior). And building this out using the GPT API would be a bit like reinventing the entire “bot framework” wheel!

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