Every AI (AWS, Google, and Genesys) have their own good and bad points. I feel trying to build full self-service in these bots is probably harder than it is worth, especially if you don't work in them as much I have. I have come to realization that DialogFlow, Lex and DialogEngine have unique functions and if you keep them specific to the task of NLU intent return, then you will have an easier time creating bots and have expectations met. For instance, if you use the bots within you flow to just gather intent, then you have very simple bots on these platforms that can perform that function and then you can tune and train them for that purpose. If you start having your bot in these platforms talk to back end systems, keeping track of variables, and start processing information, they can become very complicated very quickly.
A better approach is to keep you flow in Architect for all processing, decisions, and tracking and just use these bots for alphanumeric input or determining intent. Now that Genesys Cloud had DialogEngine, there is really no need to go out to Lex or DialogFlow for simple NLU functionality and the tools provided by Genesys are far better than AWS or Google when it comes to training and intent management.
------------------------------
Robert Wakefield-Carl
Avtex Solutions, LLC
Contact Center Innovation Architect
robertwc@avtex.comhttps://www.Avtex.comhttps://RobertWC.Blogspot.com------------------------------
Original Message:
Sent: 08-09-2020 14:49
From: Satish Pallapotu
Subject: Dialogflow and Chat Widget 2.0
Hi Robert,
We are exploring currently whether to perform the Intent Fulfillment in DialogFlow or just use DialogFlow for Intent identification and return to Architect flow. It would be ideal if we can use the DialogFlow for full service but if you are aware of any other learnings apart from the formatting as Lonmark Galido expressed, please share.
------------------------------
Satish Pallapotu
Franklin Templeton Companies, LLC
Original Message:
Sent: 08-09-2020 12:05
From: Robert Wakefield-Carl
Subject: Dialogflow and Chat Widget 2.0
Unfortunately you can only do this with Rich Response Messages, which is not supported in Architect. Best is to just use DialogFlow to look for the intent and return to Genesys Cloud Architect for formatting and responses. Better yet, just use Dialog Engine for something like that.
------------------------------
Robert Wakefield-Carl
Avtex Solutions, LLC
Contact Center Innovation Architect
robertwc@avtex.com
https://www.Avtex.com
https://RobertWC.Blogspot.com
Original Message:
Sent: 08-09-2020 03:56
From: Lonmark Galido
Subject: Dialogflow and Chat Widget 2.0
Hi,
Looking for assistance on how to display line breaks from DialogFlow onto the Genesys chat widget
My response is as per below in dialogflow:
"Hi I'm a chatbot
I'll do my best to help you with your query today
What would you like help with first?"
Attached is the response i get. I've attempted to add html breaks and other tags but with no luck.
Any suggestions?
Widget Display: response
#DigitalChannels
#Integrations
------------------------------
Lon
------------------------------