In my article about learning Dialogflow, I wrote down my suggested syllabus as well as learning path. Syllabus There are two parts to that syllabus – the first part is suitable for both non-programmers and programmers, while the second part (Webhooks and REST API v2) are meant for programmers. Common Courses for both programmers and non-programmers Dialogflow Building Blocks Dialogflow Blackholes Dialogflow Conversation Design Dialogflow Flowcharts Courses for programmers Dialogflow Webhooks Dialogflow REST API v2 Till May 31st 2020, I am making all the common courses free-to-watch ( not to be confused with free-to-buy [1] ) Free-to-watch courses Here are the links to the courses which are free to watch: Dialogflow Building Blocks Dialogflow Blackholes * Dialogflow Conversation Design Dialogflow […]
All my mini-courses are free this week
All my mini-courses are free for this week (till end of day April 17th 2020). Note that these are free to watch, but not free to enroll. That is, you will still see a price for the course. However, all the lessons are free to watch. For example, here is what the “Intro to NLU” course curriculum looked like before I made it free. Notice that only one lesson is marked as Preview, the rest are disabled and the button text says “Start”. Now, you can watch all of them (all are marked Preview): Each of these mini-courses are self-contained and go into a lot of detail on a very narrow Dialogflow topic. While a full (regular) course will cover […]
Reader Question: Is there a feedback mechanism to like and dislike a Dialogflow response?
I got this question in the comments recently: is there any feedback mechanism in dialogflow? I mean to like or unlike the bot’s response as in facebook messenger? While there isn’t any simple way to do this from the end UI of your chatbot (which I suppose is the question), you can use the Training tab in Dialogflow to do effectively the same thing. Here are the steps 1 Click on the Training link on the left pane 2 Add your feedback Click on one of the conversations. You will see a popup window. You can provide your feedback within that popup window. Disagree with the matching? Change the intent which was matched. Or you can assign the phrase to […]
Using Collect.chat for preNLU bots
In a previous article, I talked about why it would be a good option to use a rules-based, conditional logic bot as a “pre NLU” bot before you build out your actual NLU-based website chatbot. A good option for this is Collect.chat. I tried out the Collect.Chat service for a month (I chose the Standard plan – $49/month so I could experience the entire set of features) and I really liked it. There are also other similar services, and while I haven’t compared them all, I have very little hesitation in recommending Collect.chat for creating your preNLU bot. Note: the link above is an affiliate link, but I am recommending the service because I believe it is best-in-class for the […]
Reader Question: How to get some sample training data for Dialogflow?
Recently I got this question via my chatbot: How to get some sample training data for Dialogflow? This is actually an important question. The article below assumes you are building an FAQ style bot. If you are building a different kind of bot, please leave a comment below and I will write a different article based on your use case. Now, the obvious first thing is to ask: what does your chatbot replace? Is it acting as the first step for your customer support? Then just look at the existing customer conversation logs. If you don’t store them in a structured way, just analyze it manually. Sometimes it isn’t possible to do that, because you are trying to create something […]
Reader Question: Do you really need to add more training phrases?
I got this question via my blog comments: I think the reader brings up some very interesting questions. But the issue may not actually be due to “too few training phrases”. Here is a step by step process you can use to answer these kind of questions: 1 Avoid features which make your bot hard to analyze I provide a list of these “better to avoid” features in this article. 2 Identify the candidate intents As you are about to type out a message to your bot, make a list of the intents which are candidates at that step. (Tip: Don’t have too many candidates) 3 Identify the target and surplus intents Minimize the surplus intents, and identify the target […]
Reader question: Automating Dialogflow training
I received this question from a reader: I need to add a lot of utterances (phrases) similar to how actual customers will interact with the BOT e.g. I am looking for fitting rooms, I am looking of blue jeans, I am looking for shoes etc. The issue I ran into was while trying to bulk upload these, the entities and intents were not always recognized and needed manual mapping. That’s where I wanted to clarify on how can I make it less human intensive. The reader is asking: can we automatically write a bunch of intents for the CSV to ZIP generator tool and also have it identify the entities? Dialogflow annotation First, we need to understand how Dialogflow’s annotation […]