The Actions that can be defined in order to manage interactions coming through a channel end point (e.g Email Accounts, Chat Websites, and so on) are defined in the Channel Applications list:
The Applications
The Applications will be executed in the Action flow in the order they are placed in the list and may vary according to the channel type.
Application | Description | Parameters |
---|---|---|
Agent | Sends a notification to a specific Agent |
|
AmazonLex | It enables you to use an Amazon Lex voice BOT |
|
Auto Reply | Sends an automatic reply |
|
Close | Closes the interaction |
|
Dialogflow(Deprecated from rel. 2.5.7) | Activates a conversational agent defined on Google Dialogflow (you find an example for the chat in this page: see the next paragraph) |
|
DialogflowV2(Starting from rel. 2.5.7) | Activates a conversational agent defined on Google Dialogflow |
|
Gotoif | Jumps to an action in the flow according to the condition set |
|
GotoP | Jumps to an action in the flow unconditionally |
|
Noop | Writes information in a log file (for debugging purpose) |
|
Queue | Sends a notification to a specific Queue |
|
System | Executes a unix command or script |
|
Tag | Add the selected tag to the interactions |
|
Please consider that:
- Auto Reply cannot be used on Fax channel action flow
Dialogflow (any version) integration is currently available only as a Chat Websites Action (starting with XCALLY Motion Version 2.0.71) and as an Open Channel Action (starting with XCALLY Motion Version 2.3.6). In this context you can, for example, let a chat or an open channel interaction be managed by a Bot (according to Intents, Entities and Fallback Rules defined on Dialogflow) and make your Agent chime in conversation only when needed.
Do you want to know more about Dialogflow integration? click here
Remember to set on Dialogflow the intent "end of conversation", that will be considered as the end of the customer-bot interaction before to end the session or connect the customer to an agent, according to your action flow rules.
The agent will take the bot place from that moment on and open the whole interaction history.
- AmazonLex integration is available as a Chat and Open Channel Action.
- System Application is very useful when you need to:
- get information from a source external to XCALLY Motion (e.g. DB tables, CRM, other)
- provide XCALLY Motion interaction information to external applications
For example: In the following statement, the command field executes a script to verify the message.from (sender) value and inserts the result in the VAR1 variable:
Using Dialogflow to create a ChatBot: an Example
Dialogflow API Keys
First thing to do on Dialogflow is to create an Agent.
After your agent is created you will be able to retrieve the API Keys to be used in the XCALLY Dialogflow application: see the Client access token field on Dialogflow please.
Insert please your Dialogflow Client access token inside the XCALLY Dialogflow application Key field:
Dialogflow Intents
After the agent is created, you can proceed with your Intent creation: basically intents define the expected customer questions (named Training phrases) and related Bot answers (Text responses).