Automate actions based on intelligence signals detected by your telephony system. For
example, if your telephony system detects that the customer is unhappy during a support call,
Salesforce Voice can show a Next Best Action recommendation. The recommendation can suggest that
the support rep offer a 20% discount based on the detected signal and their customer loyalty
information.
To trigger an action, build a flow that maps detected signals from the telephony provider to
an action defined in Salesforce. This action can send notifications to a supervisor and a
support rep, show a script, recommend a strategy, or complete any other action to help your
support reps during their conversations. To define actions, use an Einstein Next Best Action
or an auto-launched flow.
Use Next Best Action recommendations to show support reps what to do next based on the
current conversation with the customer. Recommendations are based on intelligence signals
defined in your telephony system. To show recommendations based on an intelligence signal,
first define a rule in your telephony system that identifies each signal. Next, add a trigger
in a Conversation Intelligence rule in Salesforce. Then define the corresponding
recommendation strategy and recommendations in Salesforce. Finally, to show the
recommendations to support reps, add the Next Best Action component to the record page where
the support reps work.
Use auto-launched flows to run small-to-complex business processes and perform quick actions,
such as send an email, create a task, or create an account. These flows execute automatically
in the background based on the conditions that you define in Conversation Intelligence rules
in Salesforce. Conversation Intelligence supports auto-launched flows with no flow
trigger.
Automatically Trigger an Action Based on a Conversation Intelligence Signal Create a rule in Salesforce that triggers an action based on intelligence signals defined in your telephony system. Salesforce Voice offers multiple options for creating rules. Salesforce admins can declaratively set up Conversation Intelligence rules in a user interface. Developers can set up rules in custom components using Toolkit API and custom actions. The declarative method is the easiest way to set up rules. But the Toolkit API method allows you to develop custom rules and signal detection processes. For example, use Toolkit API to detect signals in the call transcript without using your telephony system.
We use three kinds of cookies on our websites: required, functional, and advertising. You can choose whether functional and advertising cookies apply. Click on the different cookie categories to find out more about each category and to change the default settings.
Privacy Statement
Required Cookies
Always Active
Required cookies are necessary for basic website functionality. Some examples include: session cookies needed to transmit the website, authentication cookies, and security cookies.
Functional Cookies
Functional cookies enhance functions, performance, and services on the website. Some examples include: cookies used to analyze site traffic, cookies used for market research, and cookies used to display advertising that is not directed to a particular individual.
Advertising Cookies
Advertising cookies track activity across websites in order to understand a viewer’s interests, and direct them specific marketing. Some examples include: cookies used for remarketing, or interest-based advertising.