I have created a small eBook to explain the differences between Dialogflow and RASA NLU if you are trying to choose one or the other. Note: you can right click on the images below and open in a new tab or window to see a larger, full size picture. Table of Contents Excerpt Buy the eBook You can buy the eBook from Gumroad by clicking on the link below.
Dialogflow vs Lex vs LUIS vs Watson vs Chatfuel
I get this question a lot. “How does Watson compare to Dialogflow?” “What do you think of LUIS?” So I am going to discuss my opinions in this article. Disclaimers The first disclaimer is that I am clearly biased. I actually work with clients to help them out in their Dialogflow projects. At the same time, I am hoping this post starts a discussion amongst people and helps people do some homework before selecting the appropriate framework. The second disclaimer is that I haven’t had time to actually work on bots using the other frameworks, and used my knowledge of Dialogflow to consider what I feel are the important features. Then I watched a bunch of online tutorials to check […]
Dialogflow: Low code or mo’ code?
Some readers have sent me feedback which suggests that they started using Dialogflow thinking it is a really low code tool, only to discover that it is a lot more complex once you go past the toy chatbots. At the same time, I also think that of all the major bot frameworks, Dialogflow provides the best tradeoff in terms power vs ease of use. My definition of a low code bot framework isn’t one which requires the least amount of code, but rather one which gives the best separation of responsibilities between developer, bot copywriter, and the person who asks for the bot to be built. Unfortunately, some features can change Dialogflow from a low code tool to a mo'(re) […]
More reasons why you need a developer for building a Dialogflow chatbot
I have already written an article about how you need a developer for creating a reasonably useful Dialogflow chatbot. In my previous article, I mentioned some high-level reasons why a coder would be very useful when building a Dialogflow bot. In this article, I get more specific. Here are some questions people asked me recently. All of these are normal questions you will face when building a bot. In other words, you will run into at least one of these questions when you create your own bot. How exactly does Dialogflow know what intent to match each request to? This is what someone asked me in the comments section of my YouTube channel. The answer is: only the Google (Dialogflow […]
10 concepts you can learn in Dialogflow without writing code
If you are not a programmer and don’t want to learn coding any time soon, there are still a lot of concepts you can learn about Dialogflow which will be valuable for your team. Here is my list. 1 Intents You can understand what intents are, and get a basic understanding of how they work. 2 Entities Entities give you ways to represent “many values of a given type”. A good example is a city name. 3 Contexts Understanding what contexts are and how they can help is very important for creating multi-turn dialogs in Dialogflow. Unfortunately, there are quite a few online tutorials which just smush everything together in trying to explain contexts, making the topic seem a lot […]
Some things you should know before building your Dialogflow chatbot
My client was feeling a bit upset. His long term programmer-partner was not interested in working on my client’s new proposal which involved chatbots. Why? “Chatbots are overhyped and useless” – according to the programmer-partner. Maybe you are feeling the same way. Here is what I suggested to my client – instead of calling it a chatbot, sell it to your partner as a “NLU powered digital assistant”. After all, that’s just as accurate, and probably a lot less of a loaded term today. The problem with the word chatbot As you can see, I am not a big fan of using the word chatbot, especially when it is used to describe software which doesn’t actually use NLU. At the […]
Exporting your Dialogflow agent to RASA NLU
Recently I had a coaching call with a client where I explained to him why RASA was a poor choice for substituting a Dialogflow bot he was trying to build. I had taken a quick look at RASA a few months back, so I had some idea what you could and couldn’t do in it. After I went and took a closer look, I realized that I was actually overestimating RASA’s capabilities. As it stands now, you will probably want to avoid migrating your Dialogflow agent to RASA because it will not work as well, especially if you used ideas from my site to create a bunch of conversational turns. Why, you ask? Dialogflow has the notion of an explicit […]
Exploring DialogFlow (API.AI)? Here are 6 things you CANNOT do in a DialogFlow chatbot
Let us say you are trying to evaluate what you can and cannot do with Dialogflow. Knowing some of the gotchas beforehand can save you a lot of headache down the road. Quick Note: They are not unsolveable problems. You can get around them by writing code. You cannot get the correct output if your users make spelling errors But look at the positive side! If the chatbots truly take over, all of you will need to learn to spell much better! 🙂 You cannot do simple math logic without writing code While there are bot building frameworks where math logic is possible (of course, each framework has its own set of limitations), you still cannot do simple math such […]
Can your chatbot framework/platform do this?
Recently, I received a comment on my post which talks about whether Dialogflow is open source. The comment linked to an open source chatbot framework, and helped me remember that I have wanted to write a post on this topic for a while now. In my view, it is possible to measure the flexibility and power of a chatbot framework by using it to develop the following types of chatbots. That is, in my view, building out a set of about 7 chatbots is plenty to get a very good idea of the capabilities of a bot framework. Note: Some of the links on this page might point to a paid course of mine. But you don’t have to purchase […]
The three levels of chatbot AI
I recently got a question from a reader who asked if I could help build out a website chatbot similar to a demo bot he linked to. This question made me realize that people refer to everything as a chatbot (which is great as it expands the industry and leads to more innovation in my opinion) but not everyone notice that there are actually three levels of chatbot AI and they all lead to completely different types of bots – in terms of bot intelligence, skills required to develop, maintainability etc. Conditional Logic Bot The first level of chatbot AI is one which doesn’t actually have any AI. It is actually a visual if-this-then-that type of chatbot, and can be […]