Discussion: what need for dialogue designer

When building conversational assistants with Rasa, what kind of dialogue designer do you need?

I read some documentation on it, amongst them @juste_petr blog on designing training stories

So I understand when using Rasa, dialogue design involves two phases:

  1. Initial, the basic to get started by creating some happy paths
  2. Evaluating and using real dialogues to further develop the conversational agent

As far as the initial phase concerns, to me dialog design seems to be much like creating a bot with only rules:

  1. You have to decide which happy paths are to be designed
  2. You have to write the dialogues / stories: which turns, intents, actions

And, off-course, you’ll also have to decide on which Rasa technique to use (rules and/or stories). To me, this doesn’t need a converstaional designer.


But when it comes to using real conversations, you’ll need:

  1. An communication and subject matter expert to create stories. Either by interaction with customers (=users of the bot) or by interactive learning.
  2. An expert on analysing the dialogues and creating the training data out of them.
  3. And off-course datascientist (building pipelines, data-analysing) and developer (custom actions, forms, interfaces)

So am I right when I state, there’s little need for a conversational designer who mostly worked on rule-based bots and has little or no experience with Rasa?

I’ve just read this rasa blog on CA-teams.

Si I found a usefull answer!

Thanks @HermanH for bringing this up and solving it yourself :rocket: I’ll mark your comment as solution!

1 Like