Home / DialogFlow / Conversation Design / The explicative approach to Dialogflow development
Conversation Design | DialogFlow

The explicative approach to Dialogflow development

I was trying to explain to a coaching student that my approach to Dialogflow development was somewhat opinionated, and when they asked me to elaborate, I realized it would be good to have some term which will capture my opinions.

I am going to be calling it the Explicative Approach to Dialogflow development [1].

Here is what the word means:

And here is how Wikipedia defines explication

So the word explicative has multiple benefits:

  • it is a single (although somewhat complex) word
  • it captures the essence of the various opinions
  • it is a positive expression – meaning, why wouldn’t you want to “unfold” and “make clear” the meaning of things?
  • plus, it sounds kind of cool 🙂

Here are some examples of why I use this phrase:

I don’t recommend using slot filling because it uses implicit auto-generated contexts.

I don’t recommend follow up intents because the context names are implicitly used to define the hierarchy (for example you cannot change the context name of a followup intent while also preserving the hierarchical structure).

I recommend overriding the default context lifespan of 5 and explicitly specifying it to be 1 because it will make your bot easier to analyze

I recommend using explicit training phrases inside intents rather than implicitly used entities in some situations where you don’t actually need an entity

Do you like the term? Let me know what you think in the comments.

[1] Not to be confused with “Expletive Approach” although I can understand the sentiment 😉

Related Posts

  • Aravind, yes I like the name of your approach! I would even call it the explanatory philosophy of developing chatbots. This is larger, but this is what you actually created 🙂

    • The article doesn’t mention it – using the explicative approach also has an excellent side effect. It also keeps Dialogflow more “low-code”. I will probably explain this in a future article.