Virtual Agent is a platform for
providing user assistance through conversations within a messaging interface. Use ServiceNow®
Virtual Agent to design and build
automated conversations that help your users quickly obtain information, make decisions,
and perform common work tasks.
Watch this eight-minute video for an introduction to the Virtual Agent platform.
Listen to this 21-minute podcast to hear about Natural Language Understanding in Virtual Agent and related features introduced
in the New York release.
The Virtual Agent
platform includes the following components:
- Virtual Agent conversational (client)
- With Virtual Agent, your users interact with a
virtual or live agent through various messaging services. You can configure the web-based
Virtual Agent client available for Service Portal and Apple iOS and Google
Android environments. And your users can use the Virtual Agent interface for third-party
enterprise messaging applications when you install the ServiceNow messaging integration for Slack, Microsoft Teams, and Workplace by
Facebook. You can also configure the Virtual Agent interface for Facebook Messenger, a consumer messaging
- Virtual Agent Designer
Use Virtual Agent Designer to
develop, test, and deploy automated conversations that assist your users with common issues
or self-service tasks. Virtual Agent Designer is a graphic tool
for building the dialog flows of conversations, called topics. A topic defines the dialog
exchanged between a virtual agent and a user to accomplish a specific goal or resolve an
issue. Use Virtual Agent Designer to
develop, test, and deploy conversations that assist your users with common issues or
You can build conversations that are based on keywords that your users enter. Or, you can
apply Natural Language Understanding (NLU) models, which enables your virtual agent to
understand, process, and respond to what users are saying during a conversation.
Predefined topics are available for Customer Service Management (CSM), HR Service Delivery,
and IT Service Management.
- Live agent support
- Give users the option to switch to a human agent for assistance during bot conversations.
Virtual Agent integrates with live chat
to offer a seamless transfer from a virtual agent to a live agent. Your users can request a
live agent transfer at any time during a virtual agent conversation. You can also initiate a
live agent transfer through custom conversation flows that you build.
Implementing a virtual agent to handle common requests and tasks enables your users to get
immediate help, day or night. Providing your virtual agent on channels familiar to your users,
such as third-party messaging apps, offers a convenient way for them to get work done quickly. A
virtual agent can also offer personalized customer experiences by applying and remembering user
information during the conversation.
Typical Tier 2 support tasks that virtual agents can perform include:
- Answering FAQs
- Providing tutorial ("how to") information
- Querying or updating records, for example to get status on cases or incidents
- Gathering data, such as attachments, for the live agent
- Performing diagnostics
- Resolving multi-step problems
Automating these support tasks with a virtual agent frees your support agents to focus on
more complex user issues and enables you to scale your support organization accordingly.
Conversational user interface
The Virtual Agent conversational
interface captures an automated messaging session between the virtual agent and user. The web
client interface uses the Service Portal web widget, which you can configure for custom service
portals. The widget is available in the CSM, HR Service Delivery, and ITSM Service Portals.
A simple conversation typically includes the following elements:
- Default welcome message from the virtual agent, followed by the first
prompt for the conversation. The initial prompt asks the user to type a question or to choose
from a list of available topics.
- User response to the first prompt. In this example, the user chooses the topic for checking
an IT ticket.
- Series of prompts, acknowledgements, and responses exchanged between the virtual agent and
the user until the users reach their goals or complete their tasks. You can use different rich
controls in bot prompts, for example, choice lists with buttons or a carousel of images to
select an item.
- Closing message to end the conversation.
When your users start a conversation with the bot, they can enter a request or see a list of
everything that the bot can help with. If they choose to see everything, the chat window
displays all topics available to the user. Your users can use the search box to filter the list