Hurry Up, Join The Webinar Only Few Seats Remaining...

Hurry Up, Join The Webinar Only Few Seats Remaining...

Let Us Tell You A Story of A Bot Which Transformed The Company.

ServiceNow? 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.

Components

The Virtual Agent platform includes the following components:

Virtual Agent conversational (client) interface

With Virtual Agent, your users interact with a virtual or live agent through various messaging services. You can configure the web-based chat client available for Service Portal and Apple iOS and Google Android environments. Your users can interact with a virtual agent through the Now Mobile app, as well as through the ServiceNow integrations for third-party enterprise messaging applications: Slack, Microsoft Teams, and Workplace by Facebook. You can also configure the Virtual Agent interface for Facebook Messenger, a consumer messaging application.

In addition to the clients supported by Virtual Agent, you can create conversational custom chat integrations with other chat providers. These custom chat integrations enable your end users to engage with ServiceNow Virtual Agent and live agents through other chat channels.

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.

In addition to topics, you can also build reusable topic components, such as topic blocks that perform certain functions or custom controls (user interface objects), for use in your conversations.

You can build conversations that are based on keywords that your users enter. Or, you can apply Natural Language Understanding (NLU) models, which enable your virtual agent to understand, process, and respond to what users are saying during a conversation.

Predefined topics and topic blocks 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.

Virtual Agent versions

The Virtual Agent platform is available as a professional subscription or in a limited version that is automatically included with the Now Platform?:

  • Virtual Agent (professional) — Provides all the core functionality needed to create and deploy virtual agent conversations to your Virtual Agent clients. Includes support for Natural Language Understanding (NLU) in Virtual Agent conversations.
  • Virtual Agent Lite — Provides a limited version of Virtual Agent for ITSM standard customers. Used with ITSM Virtual Agent Conversation Topics Lite, which offers three prebuilt conversations for common IT support requests. These keyword-based conversations run in the web chat client and also in Virtual Agent messaging integrations for Slack, Microsoft Teams, Workplace by Facebook, and Facebook Messenger.

Benefits

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, acknowledgments, 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.

Conversation options

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 of topics.

Manage the conversation

The conversational interface offers your users several options to manage the conversation. Users can stop the current conversation and start a new one, or contact support to access a live agent for immediate assistance.

Live agent transfer

When users transfer to a live agent, the chat window header changes to indicate that they are now interacting with a live agent. The attachment and send icons are available in the chat window for uploading an image, text, or PDF file and sending it to the agent.

Working with file attachments during live chat

During live chat, users can attach a file of any type (for example an image, text, or PDF file) and send it to the agent. The system automatically performs a virus scan on the file attachment. If the scan is successful, the file is sent to the agent.

  • If the scan fails, a message informs the user that the scan did not pass so that the user can correct the file and then upload the file again.
  • If the upload and virus scan process times out (the upload takes too long), a message tells the user that the file couldn't be processed and to try the file upload again.

Note: All chat clients support file attachment uploads, except for the mobile chat client.

New message alerts

Your users automatically receive audio and visual alerts when they receive a message from a live agent or virtual agent.

  • The visual indicator displays the number of messages received, next to the chat icon in the Service Portal window. When the user opens the chat, the indicator number closes.
  • The default sound notification uses the sn_va_web_client_alert.mp3 audio file.
  • You can change the sound that requesters hear by uploading your own audio file. For details, see Manage audio files.
  • To turn off the audio notification for your instance, use the system parameter sysparm_disable_audio_notifications=true. For example: https://<your-instance name>.service-now.com/nav_to.do?sysparm_disable_audio_notifications=true

Natural Language Understanding in Virtual Agent

Apply Natural Language Understanding (NLU) models that enable your virtual agent to understand user statements in automated conversations. An NLU model provides information that your virtual agent uses to determine what users want to do and to extract relevant values from their input. With NLU, your virtual agent can offer a more natural and engaging conversational experience.

Virtual Agent Lite

Virtual Agent Lite is a limited version of Virtual Agent available to ITSM standard customers. To use Virtual Agent Lite, you must also install ITSM Virtual Agent Conversation Topics Lite, which provides three predefined conversations for common IT support requests. These keyword-based conversations run in the web chat client and also in the Virtual Agent messaging integrations for Slack, Microsoft Teams, Workplace by Facebook, and Facebook Messenger.

Implementing Virtual Agent

To implement Virtual Agent, complete these initial configuration and setup steps.

Transferring Virtual Agent conversations to a live agent

Manage live chat support, including the chat support interface used when a Virtual Agent conversation is transferred to a live agent.

Virtual Agent Designer

The Virtual Agent Designer is a diagram tool for creating and managing topics, which are blueprints for conversations between a virtual agent and user. You can design topics that help your users resolve common work issues or guide them through self-service tasks.

Virtual Agent interaction records

Each time a Virtual Agent conversation occurs, an interaction record captures the entire conversation as a chat record type in the Interaction [interaction] table. The record maps to an entire conversation and includes all topic elements used in the conversation, as well as live agent transfers.

Virtual Agent conversation states

Virtual Agent conversations move through different states.

Closing idle Virtual Agent conversations

By default, Virtual Agent conversations that are abandoned by requesters remain open or "idle" until they are automatically closed by a daily scheduled job, Time Out Abandoned VA Conversations. This job runs at 1:00 AM each day.

Domain separation and Virtual Agent

Information related to domain separation and the Virtual Agent application. Domain separation enables you to separate data, processes, and administrative tasks into logical groupings called domains. You can then control several aspects of this separation, including which users can see and access data.

Virtual Agent scripts

If you are an admin or Virtual Agent admin, you can use scripts to customize the behavior of Virtual Agent topics.

Virtual Agent localization

Use the Translated Text [sys_translated_text] and Message [sys_ui_message] tables to provide translations for Virtual Agent topics and accommodate users who speak different languages.

Analytics and Reporting Solutions for Virtual Agent

Analytics and Reporting Solutions contain preconfigured dashboards. These dashboards contain actionable data visualizations that help you improve your business processes and practices.

Conversational custom chat integrations

You can use a custom chat integrations framework of scriptable APIs to bring the ServiceNow? Virtual Agent to any conversational interface. These APIs provide the conversational custom chat integrations that you need to make the connections.

Conversational SMS Integration with Twilio

Host Virtual Agent conversations on Twilio SMS.

Conversational Integration with WhatsApp (powered by Twilio)

Engage with requesters including customer contacts and consumers who prefer the WhatsApp messaging app to chat with an agent.

Conversational Integration with LINE

Engage with requesters including customer contacts and consumers who prefer the LINE messaging app to chat with an agent.

ServiceNow Virtual Agent API

Use the Virtual Agent API app through the ServiceNow? Store to integrate any conversational channel or a bot ecosystem with ServiceNow? Virtual Agent and/or Live Agent. This API is built on the conversational custom chat integration framework provided with Virtual Agent in the Paris release.








要查看或添加评论,请登录

社区洞察

其他会员也浏览了