Our use case is similar to a CSAT Survey. In Classic Paths, we presented a series of static questions to the user, and they clicked on the appropriate button (Very Satisfied = 5 through Very Dissatisfied=1).
We need additional features in order to replicate this functionality in Agent Studio:
- “Human in the Loop” Action for Conversational Processes. This Action would always pause the conversational process to solicit an interaction with the user.
- More control over how options are presented to the user
- Show buttons to user for options
Our Conversational Process has 7 “input” slots to capture the user feedback that is gathered over the course of the conversation. Each slot is set to “Always prompt user” with the desired question in the slot description and a resolver strategy with the possible responses. The bot still infers the user input since many of the slots have identical text in the resolver strategy. An explicit Action to ask for user input as part of the Conversational Process would be welcomed.
We show ‘Very Satisfied’ to the user as the first option. The bot always picks this as ‘Option 1’ and allows users to select this option by pressing 1. Very Satisfied is a 5 and our users are familiar with that value due to how ServiceNow records this information. Asking users to select 1 for Very Satisfied is confusing and I do not see a way of preventing this from being shown to the users.
We would like to have control over the presentation for soliciting user input. Along these lines, support for buttons and button labels with emojis would be welcomed.
