CXone Mpower Autopilot is a full-service, data-driven intelligent virtual agent
A software application that handles customer interactions in place of a live human agent.. It handles voice Any channel, contact, or skill associated with Digital Experience. The full conversation with an agent through a channel. For example, an interaction can be a voice call, email, chat, or social media conversation. in the place of live agents. Autopilot virtual agents understand human language and respond to contacts naturally. They can switch topics, understand context, and answer questions with human-level comprehension. Autopilot virtual agents can fully resolve issues via self-service, limiting escalations to live agents.
Autopilot virtual agents use CXone Mpower XO artificial intelligence (AI). XO comes equipped with over 30 years of interaction data. Autopilot uses that data, along with your organization's interaction data, to build conversation flows. These flows include lists of possible utterances What a contact says or types. and appropriate responses. Using AI, Autopilot virtual agents continue to learn from interactions to improve and add to these flows.
Autopilot virtual agents can also:
-
Identify tasks agents may need to perform to resolve a contact's issue.
-
Identify back-end tasks that Autopilot itself can do, such as fetching a contact's data.
-
Proactively send messages to contacts based on their identified needs and interests. Watch this demo video
for an example of this feature.
Autopilot Knowledge is different from Autopilot. Autopilot Knowledge is an agent assist application that provides a CXone Mpower Bot Builder bot access to CXone Mpower Expert knowledge bases A website that stores troubleshooting articles..
You can use CXone Mpower Recording to record Autopilot voice interactions.
Edward Ferrars is speaking with Autopilot, the virtual agent for Classics, Inc. He tells Autopilot he wants to pay the balance from his latest book order. Autopilot begins the conversation flow for payments. It fetches his billing information and finds two credit cards. It asks Edward which one he wants to use. He answers "Credit Card A," but then changes his mind and says, "Actually, use Credit Card B". Autopilot changes the credit card selection.
Edward then asks for help changing his password. Autopilot switches to the conversation flow for that intent.
Autopilot remembers Edward's first intent The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish was payment. It switches back to that conversation flow. It asks Edward if he'd like to remove Credit Card A from his billing information. He answers "Yes," and Autopilot removes it.
How Virtual Agents Work
The beginning of the conversation is different for voice and text virtual agents:
-
The person interacting with an agent, IVR, or bot in your contact center. Automated phone menu that allows callers to interact through voice commands, key inputs, or both, to obtain information, route an inbound voice call, or both. menu. Once the conversation with the virtual agent begins, the contact's utterances What a contact says or types. are transcribed Also called STT, this process converts spoken language to text. into text so the virtual agent can analyze them. The virtual agent's responses are converted to synthesized speech using a text-to-speech Allows users to enter recorded prompts as text and use a computer-generated voice to speak the content. service before being sent to the contact. Transcription and speech synthesis can happen in CXone Mpower or, in some cases, in the provider's platform.
-
A way for contacts to interact with agents or bots. A channel can be voice, email, chat, social media, and so on. you use. For example, it might be located on your website or the contact could start the conversation from the location of a third-party service, such as Apple Messages for Business. The contact's utterances are already in text format, so they don't need to be transcribed. They're passed on directly to the virtual agent.
After the conversation has started, the virtual agent analyzes the contact's utterances to understand the purpose or meaning behind what a person says. This is known as the contact's intent. When the intent is identified, the virtual agent sends an appropriate response to the contact. The method of sending a response depends on whether it's a text or a voice virtual agent:
- Voice: Protocol used for signaling and controlling multimedia communication sessions such as voice and video calls. backchannel method of connection.
- Text:
At the end of the conversation, the virtual agent sends a signal to the Studio 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.
Once the conversation is complete, post-interaction tasks can be performed, such as recording information in a CRM Third-party systems that manage such things as contacts, sales information, support details, and case histories..
Prerequisites
Before setting up Autopilot, you must have:
- An account with Omilia or Amelia.
- A fully configured and trained Omilia or Amelia voice
- A voice A way for contacts to interact with agents or bots. A channel can be voice, email, chat, social media, and so on. set up and configured in CXone Mpower.
Components of an Integration
Setting up Autopilot requires the following components:
- CXone Mpower: CXone Mpower must have a configured A way for contacts to interact with agents or bots. A channel can be voice, email, chat, social media, and so on. to use with the integration.
- Virtual Agent Hub in CXone Mpower: Virtual Agent Hub holds the configuration information for connecting to your virtual agent A software application that handles customer interactions in place of a live human agent. provider, such as service account credentials. Written form of a voice or digital interaction, if your integration requires this service.
- Studio scripts: You need at least one script that includes a virtual agent Studio action. The action must be configured with the connection information for your virtual agent. The point of contact for the channel you're using with the integration must be configured to use this script.
- Autopilot:
Voice Biometric Authentication
You can use voice biometrics to authenticate contacts The person interacting with an agent, IVR, or bot in your contact center. with
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 intent The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish 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.
If you have Autopilot (Omilia), you can use the Omilia voice biometrics miniapp that's available on the Omilia platform. This option allows you to use Omilia anti-fraud features, such as a blocklist for known fraudulent contacts, and the ability to detect ANI Also known as caller ID. Listed phone number of an incoming voice call. spoofing and the use of recorded voices to try to trick the system.
Autopilot Integration with a Knowledge Base
You can integrate Autopilot with CXone Mpower Expert or any third-party knowledge base (KB). Autopilot can then use information from your KB articles to help answer your contact's questions. Autopilot can provide your contacts with the following from your knowledge base:
-
A response composed of information from one or more KB articles.
-
Links and images within KB articles.
-
Links to full KB articles.
If the contact doesn't find the information helpful, Autopilot forwards their interaction to a live agent.
The integration of Autopilot with a KB must be completed by your implementation team.
Rich Media Support for Text Virtual Agents
If your channel supports it, you can include rich media Elements in digital messaging such as buttons, images, menus, and option pickers. content in the messages. The type of rich media that can be sent differs from channel to channel, as shown in the following table.
| Adaptive Cards | HTML & Markdown Text | Rich Link | Quick Replies | List Picker | Time Picker | Form message | |
|---|---|---|---|---|---|---|---|
| Apple Messages for Business |
|
|
|
|
|
|
|
|
Digital Chat |
|
|
|
|
|
|
|
|
|
|
|
Uses fallback text |
|
|
|
|
| Facebook Messenger |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| Google Business Messages |
|
|
|
|
|
|
|
Supported:
Not Supported:
Learn more about digital channel support for rich media.
When you want to include rich media content in text virtual agent responses, configure it in your virtual agent's management console. It should go in the configuration for each response that will send the rich media.
Rich media content is sent as JSON. When building your rich media JSON, follow the schema for the digital channel you're using. The schemas are different for each channel. Find the JSON for the media content you want to use, then add it to the response message configurations that you create in
Custom Scripting Guidelines
Before integrating a virtual agent The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish, 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.
- Any script-specific requirements for your virtual agent, including:
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.
- Use the TYPING INDICATOR Studio action in your script for text virtual agents. This action adds a visual indicator, such as bouncing dots, to the chat window when the virtual agent is responding. This can help your virtual agent appear more human during the interaction.
- How to complete the script after adding the virtual agent action. You may need to:
- Add initialization snippets as needed to the script using Snippet actions. This is required if you want to customize your virtual agent's behavior.
- Re-configure the action connectors to ensure proper contact flow and correct any potential errors.
- Use the OnReturnControlToScript branch to handle hanging up or ending the interaction. If you use the Default branch to handle hanging up or ending an interaction, your script may not work as intended.
- Complete any additional scripting and test the script.
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 site.
Supported Studio Actions
Use the Textbot Exchange Studio actions in your scripts with Autopilot. If you're setting up a voice virtual agent with Autopilot, contact your CXone Mpower Account Representative for assistance.
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 agent A software application that handles customer interactions in place of a live human agent. turn by turn. It sends each utterance What a contact says or types. to the virtual agent. The virtual agent analyzes the utterance for intent The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish 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.
