This post is a response to a user question: I have an entity called “Insurance” wich has the following values: “Home insurance” “Empresarial insurance” I have too an intent tha i use to ask about de price of the insurances. The training phrases are: “How much cost the home insurance?” “How much cost empresarial insurance” And other phrases like those. The DialogFlow recognize the entities in the training phrases, but home insurance and empresarial insurance are recognized like “Insurance”. I want to know if there a way to distinguish the different values of the entity and use this entity with the value to make a corresponding response like: If i ask about the empresarial insurance, i wish to asnwer with […]
In one of my articles, I mention using Automated Conversation Testing (ACT) as a way to improve your bot’s reliability. In other words, when you make a change anywhere in your bot, it would be a great help to know that you didn’t accidentally break something else in the bot which was working correctly. REST API The straight forward way (note: I don’t mean easy) to do ACT right now is to use Dialogflow’s REST API. Each time you issue a query to your Dialogflow agent via the REST API, you get back the following information (some fields deleted to make it easier to read): The three fields of interest to us are: intentId (line 11) intentName (line 14) score […]
I recently spent some time watching the Chatbase team’s video on improving chatbots using Chatbase. I will summarize the material in this post. What is UMM? UMM is an acronym which stands for: U – Unsupported requests M – Misunderstood requests M – Missed requests Let us take a look at some examples to show what each of these types of requests are. Intent Mapping For the sake of explanation, let us suppose you can assign a color to each of your intents. So you have red, blue and green intents, and the black color represents the Fallback intent. Unsupported requests Suppose, we get a new user request and it is an orange. We don’t (yet) have any way to […]
I got this question from a reader: Let’s say I have a BlackListWord entity that I use in template mode for capturing sentences with curse words. If I say “f**king” or “f**k you” the bot is gonna catch it. But if I get to say something like “the end of the f**king world” it takes me to the fallback intent. How could I manage to my intent to be triggered by every occurrence of a BlackListWord regardless of the sentence it is in? I don’t see how the official docs could help. I’ve already searched the web but I couldn’t find many discussion threads. Then I thought I’d find something here–as I always do–but I think that this hasn’t been […]
I got a comment recently on my post about intents which don’t match like you might expect. This is an extremely unlikely scenario. But here are some troubleshooting tips. Make sure the input context matches In a previous article, I shared an example of an intent in my SupportBot where people express interest in coaching. The intent definition for the “Coaching” intent looks like this: For this intent to fire, the context must already be set to awaiting_service_choice. If you have a wrong context set, the intent will not fire even if the words are an exact match. Make sure the previous intent was mapped correctly When you set contexts in this fashion, in fact, usually it is quite likely […]
I have deleted obsolete and off topic posts from my site. If you are still interested, you can access this article here.