---
sourceDocument: Zurich Conversational Interfaces
sourceDocumentLink: https://www.servicenow.com/docs/r/zurich/conversational-interfaces

 Release :

    - zurich

ft:locale :

    - en-US

ft:publication_title :

    - Zurich Conversational Interfaces

ft:clusterId :

    - convint

bundleId :

    - convint

workflow :

    - Platform


---

# Assistant Designer

# Assistant Designer {#ariaid-title1}

Release version: Zurich  
Updated September 10, 2025  
![](https://www.servicenow.com/docs/portal-asset/ico-clock) 1 minute to read  
Create, configure, manage, and test LLM-based chat and voice assistants within Assistant Designer, a centralized assistant administrator experience.

To access Assistant Designer navigate to AllAssistant Designer.  
Assistant Designer is comprised of three main areas:

1. Assistants: From the Assistants tab, an admin creates, manages, and tests assistants. Voice assistants can't be tested within Assistant Designer at this time. Assistant Designer is only available if you have installed a Now Assist product. Customers who are only using Natural Language Understanding (NLU) can't access Assistant Designer. For more information about configuring chat or voice assistants, see [Configuring assistants overview](https://www.servicenow.com/docs/0bKmXfQyHQhSU1~pEwib6w "Use Assistant Designer to build and optimize large language model (LLM) assistants for your conversational needs. Assistant Designer is a centralized assistant administrator experience that allows you to create and manage both chat and voice assistants.").
2. Asset library: The Asset library tab opens the Virtual Agent Designer home page where you can create NLU/Keyword topics and LLM assets. For more information, see [Getting started with Assistant Designer Asset library](https://www.servicenow.com/docs/9Z0i~KW2SyGISDnGBW6Llg "The Assistant Designer Asset library includes 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.").
3. Analytics: Monitor, evaluate, and optimize the performance of your chat and voice assistants from the Analytics tab. For more information, see [Analyzing assistants](https://www.servicenow.com/docs/EpN8Kq8UfhE_fbQp8Vq52g "Monitor, evaluate, and optimize the performance of your AI-powered assistants from the Analytics tab of the Assistant Designer.").
{#assistant-designer__ol_nqr_bvn_pgc}  
Figure 1. Assistant Designer  
{#assistant-designer__table_f55_ytn_pgc__entry__2}

| Term | Definition |
|-|-|
| Virtual Agent | Virtual Agent provides user assistance through conversations within an intelligent messaging interface. It helps solve ordinary issues and delivers results for common requests, increasing the productivity of agents and technicians. Virtual Agent supports both large language model (LLM) and Natural Language Understanding (NLU) topic discovery. Assistant Designer only supports LLM conversations in Now Assist in Virtual Agent. |
| Assistant | An assistant is the container for the end-to-end administrative configuration for Now Assist in Virtual Agent. It's a Now Assist in Virtual Agent chat or voice conversation. An administrator can create multiple Now Assist in Virtual Agent assistants. By placing assistants in various channels such as a portal, mobile app, Microsoft Teams, and Sidebar discussions, any user benefits from the assistants. |
| Conversational assets | Conversational assets are components that an admin can use to build an LLM conversation. Asset types that are offered are: * Topics * Subflows * Actions * AI agents * Custom skills {#assistant-designer__ul_xht_5wn_pgc} |
| Information sources | Information sources designate what content areas should be included in the assistant for AI Search queries. Currently, the following information source categories are offered: * Knowledge base (KB) articles * External content * Conversational catalog {#assistant-designer__ul_rmh_cxn_pgc} |
[Table 1. Key terminology]

{#assistant-designer__table_f55_ytn_pgc}

*[\>]: and then