Why Dialogflow CX is a good learning tool for “No Code” Prompt Engineering

If you would like to learn Prompt Engineering without writing any code, I think the Generative features of Dialogflow CX can be very helpful.

Here are some reasons:

Non-programmer friendly

Dialogflow CX includes a visual conversation flow builder, which is built on top of a well defined framework for specifying intents, entities and other NLU concepts.

So it is very friendly for non-programmers.

Practical

Once you start building the Cognitive Training chatbot using Dialogflow CX, it is usually quite easy to update the conversation flow without asking for help from a programmer.

This makes it a practical choice to actually study what is going on – you can see what happens “under the hood” without having to learn programming

Comes with a lot of batteries included

You can also do simple A/B testing of your prompts and use the conversation history to see which prompt is doing a better job of achieving your task or goal.

Since these are features which were already a part of Dialogflow CX this means you get a lot of “batteries included” which can help you learn this subject.

Bonus: You can also learn about the limitations of Generative AI

As a bonus, you can also learn about the limitations of not just Generators in Dialogflow CX, but generative AI as a whole.

One of my big concerns right now is that people are using Generative AI for use cases where it does not make sense.

And the answer to this is not to find a better Large Language Model, but to ask if your task even needs an LLM. Once you do that, you will notice that we already have perfectly functional tools like Dialogflow CX (and other bot frameworks) for implementing those same types of chatbots. The founders of spaCy call this LLM Maximalism – when all you have is an LLM, everything looks like a prompt! 🙂

When you learn the limitations of Generative AI you are also learning about alternate ways (in fact, better ways) to complete your task.

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