Salesforce Einstein

Content on this page is for a product or feature in controlled release (CR). If you are not part of the CR group and would like more information, contact your Account Representative.

Salesforce Einstein is a third-party platform that provides chat-based virtual agents. Virtual agents interpret what your contacts type in the chat window and respond appropriately. They do this using technologies such as:

Virtual agents are flexible and can provide a range of functions to suit the needs of your organization. For example, you can design your virtual agent to handle a few simple tasks or to serve as a complex interactive agent.

The Salesforce Einstein platform only supports text virtual agents. However, you can voice-enable your virtual agent in CXone Mpower so it can handle voice interactions. This requires custom scripting and uses text-to-speechClosed and speech-to-textClosed services to convert each turn of the conversation from audio to text and vice-versa. For more information about voice-enabling a text virtual agent, contact your CXone Mpower Account Representative.

Conversation Flow for Text Virtual Agents

Contacts start a conversation using a chat window. The location of the chat window varies depending on the digital channelClosed you use. For example, it might be located on your website or the contact could start the conversation using a third-party service, such as Apple Messages for Business. The contact's utterancesClosed are already in text format, so they don't need to be transcribedClosed. They're passed on directly to the virtual agent.

The virtual agent analyzes the contact's utterances to understand the purpose or meaning behind the words. This is known as the contact's intent. The virtual agent sends an appropriate response as text.Requests and responses are sent via Virtual Agent Hub and the script with each turn. This option allows for customization of the virtual agent'sbehavior from turn to turn.

At the end of the conversation, the virtual agent sends a signal to the script. It can signal that the conversation is complete, or that the contact needs to speak with a live agent. If the conversation is complete, the interaction ends. If a live agent is needed, the script makes the request. The contact is transferred to an agent when one is available.

When the conversation is complete, the script can perform post-interaction tasks, such as recording information in a CRMClosed.

Prerequisites

To use Salesforce Einstein virtual agentsClosed with CXone Mpower, you need:

  • Salesforce account with administrative privileges.
  • A Salesforce Einstein virtual agent configured and trained to provide responses that fulfill your contacts' requests.
  • Postman API (optional).

Components of an Integration

The integration of Salesforce Einstein involves the following components: 

Conversation Transcripts

You can capture the transcript and intent information from all Salesforce Einstein chat conversations. You can use the captured data in any way you want. For example, in cases where an interaction is transferred to a live agent, you could display it for that agent. Another option could be to save it as a permanent record of the conversation. You can choose to capture just the transcript, just the intent information, both, or neither.

If you want to capture this information, you must enable it in the Salesforce Einstein configuration settings in Virtual Agent Hub. You must also configure a Studio script used with your virtual agent. The script must include a action configured to manage the captured data. Captured data is stored temporarily for the life of the contact ID. If you need to save it, you can configure the script to send it to an archive. You are responsible for scrubbing all saved data for PII (Personally Identifiable Information).

Voice Biometric Authentication

You can use voice biometrics to authenticate contactsClosed with an Amazon Lex V1 voice virtual agent. This method uses voiceprints to authenticate contacts over the phone. Every person has a unique voiceprint, just as they have unique fingerprints. It only takes 0.5 to 3 seconds of normal, conversational speech for a voice biometric service to determine if the caller is who they claim to be.

Contacts need to enroll to use voice biometric authentication. As a part of the enrollment process, they must give your organization permission to record their voice and use it for authentication. When you use this method with a virtual agent, you must configure and train your virtual agent to handle this intentClosed during an interaction.

Using voice biometric authentication with a virtual agent requires that you have a voice biometrics provider set up in Voice Biometrics Hub. You must also customize your Studio script to handle the voice biometrics flow.

Custom Scripting Guidelines

Before integrating a virtual agentClosed, you need to know: 

  • Which script you want to add a virtual agent to.
  • The virtual agent Studio action you need to use.

  • Where the Studio actions must be placed in your script flow.
  • The configuration requirements specific to the virtual agent you're using.
  • Provider-specific requirements. Autopilot has no provider-specific requirements. For Autopilot Amelia only, the script has the following requirements: 
    • When nesting JavaScript within the JSON payload in Amelia virtual agents, use single quotes instead of escaping double quotes with a backslash ( \" ).

    • JSON structures must be "contentType": "dfoMessage", where the M in Message is capitalized. It won't work with a lower case m.

  • How to complete the script after adding the virtual agent action. You may need to: 

Ensure that all parameters in the virtual agent actions you add to your script are configured to pass the correct data. The online help pages for the actions cover how to configure each parameter.

Additionally, ensure that you completely configure your virtual agent on the provider side. Verify that it's configured with all possible default messages. This includes error messages or messages indicating an intent has been fulfilled.

You may be able to obtain template scripts for use with virtual agent integrations from CXone Mpower Expert Services. If you need assistance with scripting in Studio, contact your Account Representative, see the Technical Reference Guide section in the online help, or visit the CXone Mpower Community A square with an arrow pointing from the center toward the upper right corner. site.

Supported Action for Text Virtual Agents

You can use the Textbot Exchange action when integrating a Salesforce Einstein text virtual agent.

The TextBot Exchange action is for complex virtual agents or for when you need to customize the virtual agent's behavior from turn to turn. It monitors the conversation between the contact and the virtual agentClosed turn by turn. It sends each utteranceClosed to the virtual agent. The virtual agent analyzes the utterance for intentClosed and context and determines which response to give. TextBot Exchange passes the response to the contact. When the conversation is complete, the action continues the script.