Getting started with Virtual Agent Designer
Summarize
Summary of Getting Started with Virtual Agent Designer
The Virtual Agent Designer is a diagram tool that allows ServiceNow customers to create and manage conversational topics for virtual agents. These topics serve as blueprints to assist users in resolving common issues and navigating self-service tasks, utilizing various AI technologies like generative AI and Natural Language Understanding (NLU).
Show less
Key Features
- Topic Creation and Management: Users can design topics with components and logic for conversations, using tools like Now Assist and NLU integration.
- Topics Page: The landing page lists various objects (topics, topic blocks, etc.) with details such as published status, modification time, and category, allowing for easy access and organization.
- Flow Creation: The Flow tab enables users to design conversation flows visually or in a table format, including user inputs and bot responses.
- NLU and Intent Mapping: Users can review and edit utterances, train models, and publish updates directly within the designer.
- Language Support: The Languages tab helps manage translation statuses and mappings for different languages activated in the instance.
- Testing and Debugging: Customers can preview, test, and debug topics to ensure they function as intended before publishing.
Key Outcomes
By utilizing the Virtual Agent Designer, ServiceNow customers can efficiently create and manage conversational interfaces that enhance user experience, improve issue resolution, and streamline self-service tasks. The integration of generative AI and NLU improves the responsiveness and effectiveness of virtual agent interactions, ultimately leading to higher user satisfaction and reduced operational workload.
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 conversations are defined in a topic. When building a topic, there are various components (controls) that you can use to build the logic of a conversation, as well as the responses that the user sees.
Virtual Agent can use either generative AI, Natural Language Understanding (NLU), or keywords to match the user's request with the appropriate conversation or topic. You can use generative AI through Now Assist in Virtual Agent to match the user's request with the desired conversation or topic. Now Assist in Virtual Agent uses large language models (LLMs) and generative AI skills to improve deflection rates and reduce the amount of time-consuming work that Natural Language Understanding (NLU) topic discovery requires. With Now Assist in Virtual Agent, you can test and publish your models from within Virtual Agent Designer.
With keyword topic discovery, the topic author associates keywords with the topic. With NLU topic discovery, the topic author associates the topic with an intent within an NLU model. An intent describes what the user wants to achieve. User utterances are matched with intents to determine the most appropriate topic for the user. Associating a topic with a model and intent is called mapping.
If you're using ServiceNow NLU, then Virtual Agent Designer integrates with NLU Workbench so that you can map topics to new or existing models and intents without leaving the interface. In addition, you can also modify utterances, test, train, and publish your models from within Virtual Agent Designer.
Virtual Agent Designer Topics page
When you open Virtual Agent Designer, the Topics landing page lists the objects in your instance. These objects include topics, topic blocks, custom controls, setup topics, and small talk topics. The Topics page lets you access, create, and edit these objects in Virtual Agent Designer.
You can also test and preview active topics to verify that they work as intended. You can also sort and search for topics. When you have many topics, use the sort filters to quickly organize and find your topics. For more information, see Virtual Agent Designer Topics page.
- Name: Object name. If the object is a topic block or custom control, the icon for the object type is also displayed.
- Published status: Time (minutes, hours, days, or months) that the item was last published and state. The status also indicates if the object is read-only.
Source template: Pre-built topics include the word template in the name. You can duplicate these predefined conversation templates and use them.
- Draft state: If you update a published item but have not yet republished it, the Published status is marked as Draft. This lets you quickly identify the items that are still in progress.
- Modified: Time (minutes, hours, days, or months) that the item was last updated.
- Category: Type of group to which the topic or object belongs.
Topic properties
Use the topic Properties tab to identify a Virtual Agent object and how it is used. The properties you can specify depend on the method of topic discovery used in your instance: LLM, NLU, or keywords. For example, if you enable NLU in the General Settings page, the Properties tab includes fields for identifying the NLU model and intent for the topic. Or if you've enabled Now Assist and are working with an LLM topic, the Properties tab includes fields for what you want the topic to do and which assistant(s) to use.
- Specify the name and type of object, such as topic, topic block, custom control, and so forth).
- Specify the model type, purpose of the topic, and which assistant(s) can run this topic for Now Assist customers.
- Control who uses the topic and what channels it can run in.
- Associate live agent variables with a topic.
- Add keywords to the topic or map the topic to a ServiceNow NLU model and intent.
For more information, see Topic Properties tab.
Topic flow
When you create or update a topic, topic block, or custom control, you build the conversation flow in the Flow tab. In the default view, the flow looks like a diagram. Use the controls for user inputs, bot responses, and utilities to define the flow. The status of the topic and NLU model (if used) appears in the upper-right corner of the window.
The Table View option in Virtual Agent Designer displays the nodes in your conversation flow as a table, rather than as a diagram. Each node is identified in a corresponding row in the table. You can add, change, or delete nodes using these table rows.
For example, instead of dragging and dropping controls onto the canvas, you can select Add new node to insert a node into the appropriate row in the table. When you focus on a particular row (node), the corresponding property sheet for the node displays.
As you create or update your design, you might find it helpful to switch between the diagram view and the Table View using the Table View option. If your conversation contains many nodes, Table View lets you review all the nodes in your conversation quickly. You can use the Search table option to quickly find a particular node or control.
For more information, see Topic Flow tab.
NLU model and intent mappings
- Review and edit utterances and associated entities.
- Train, test, and publish
your NLU model.
Test the topic model with user utterances to see if it triggers the appropriate intent and topic. You can also test entity recognition.
For more information about this tab, see Topic NLU Intent tab.
Topic languages
The Languages tab displays the topic's translation status for languages that have been activated on the instance. If you're using NLU, you can also review the language mappings for that topic.
- View translation status for activated language plugins.
- View and test the topic in a specific language.
- Edit the topic translations.
- Request topic translations in additional languages.
- View or modify NLU language mappings
and entity mapping.
For more information, see NLU model mapping in Virtual Agent Designer.
For more information about this tab, see Topic Languages tab.