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

 Release :

    - brazil

ft:locale :

    - en-US

ft:publication_title :

    - Brazil Conversational Interfaces

ft:clusterId :

    - convint

bundleId :

    - convint

workflow :

    - Platform


---

# LLM topic discovery in Virtual Agent

# LLM topic discovery in Virtual Agent {#ariaid-title1}

Release version: Brazil  
Updated September 10, 2026  
![](https://www.servicenow.com/docs/portal-asset/ico-clock) 2 minutes to read
Summarize  
![AI sparkle icon](https://servicenow.com/docs/portal-asset/ai-sparkle-icon) Summarized using AI  
This content was generated using new OpenAI-powered functionality. Results are provided on an as is basis and are not guaranteed to be accurate or complete.  

## Summary of LLM topic discovery in Virtual Agent

Large language models (LLMs) enhance ServiceNow Virtual Agent by enabling it to process user statements in natural language more effectively than traditional Natural Language Understanding (NLU).
LLM topics simplify setup by eliminating the need for complex models, intents, and keyword mappings.
When ServiceNow Otto for Virtual Agent is enabled, users can create LLM-based topics in Assistant Designer Asset library, allowing Virtual Agent to leverage generative AI for topic discovery and language-related tasks such as text generation.
Show full answer Show less  

## Key Features

* **Topic Discovery:** LLMs identify the best-matching topic based on a plain language description without requiring explicit intents or keywords. If multiple topics match, users receive a list to select from.
* **Entity Extraction:** LLMs automatically extract relevant entities from user input without prior mapping or association with input nodes, streamlining topic configuration.
* **Topic Switching:** Users can switch conversation topics naturally during interactions without restarting or canceling previous requests. Virtual Agent dynamically activates the new topic based on user intent, improving conversational flow. Note that topic switching is supported during queries but not within catalog ordering flows.
* **Small Talk Handling:** LLMs support natural conversation shifts, including casual questions or unrelated topics, by enabling the creation of small talk topics and filters to maintain engagement and context.

## Benefits for ServiceNow Customers

* Speeds up creation, configuration, and deployment of Virtual Agent topics compared to NLU-based approaches.
* Reduces maintenance overhead by removing the need for extensive training and manual intent or entity setup.
* Improves user experience with more fluid and natural conversations that can handle multiple topics and intent changes seamlessly.  
Large language models (LLMs) enable Virtual Agent to process user statements in plain language. Conversations that use LLMs can outperform those conversations that use Natural Language Understanding (NLU), with easier setup.

## How LLMs work in Virtual Agent {#va-llm__section_j24_4c4_lzb}

Watch this video to learn about LLM topics in Assistant Designer Asset library.

When you create a topic in Assistant Designer Asset library, you can select LLM as the model type for your topic whenever ServiceNow Otto for Virtual Agent is turned on. Virtual Agent then uses LLM generative AI to discover topics that match the user's intent.

Unlike NLU topics, LLMs don't require models, intents, or keywords to be linked to the topic. LLMs can discover topics and perform language-related tasks, such as text generation for case summaries and
resolution notes, without months of training on NLU models. Overall, you can create, configure, and deploy LLM topics faster than working with NLU.

With LLMs, Virtual Agent can do the following:  
* Perform topic discovery without needing a singular declared intent in a given topic.
* Find intents without backup keywords as in NLU modeling.
* Extract entity values without prior mapping as in NLU modeling.
* Handle multiple conversation topic switches in a single conversation session.
{#va-llm__ul_ky4_mgm_13b}

For more information about LLMs, see [Large language models on the ServiceNow AI Platform](https://www.servicenow.com/docs/access?context=exploring-large-language-models&version=brazil&pubname=brazil-intelligent-experiences&ft:locale=en-US).

## Topic discovery {#va-llm__section_gh5_wmv_lzb}

With LLM topic discovery, topic authors no longer need to create and maintain complex NLU models and intents with backup keywords. The LLM does all of the heavy lifting for you. The only requirement is a robust, plain
language topic description on the Properties tab in Assistant Designer Asset library. The LLM uses this description to find the best topic match for the user utterance. If there are multiple potential matches, the user will see a list of topics to choose from.

For example, if a user asks Virtual Agent to calculate a ride share fee, the LLM matches the user utterance with an existing topic that can calculate the ride share with a tip.

## Entity extraction {#va-llm__section_fpf_1nv_lzb}

With LLM topics, the LLM has all the information needed to determine if an utterance has the information to fulfill a request. Unlike NLU models, you don't need to associate entities with a user input node or add nodeless NLU entities as input variables to a topic. The LLM simply finds the entity that most closely fits the
user intent.

## Topic switching {#va-llm__section_ow4_xmv_lzb}

Topic switching is faster and easier with LLMs compared to NLU topics. The LLM processes your requests to change intent made in natural language, and activates the appropriate topic.

For example, if you start a conversation by asking for a mobile phone, you don't have to cancel the order first or restart the conversation. Instead, you can ask Virtual Agent to order a laptop instead. Virtual Agent immediately switches from the mobile phone topic to the laptop topic. Topic switching can be done during a query, but not within a catalog ordering flow.

Another example is when a user might ask a casual question or engage in small talk. The question might be unrelated to the original request. You can create small talk topics or set up small talk filters to help the Virtual
Agent match and launch the appropriate conversation for the switched topic. For more information, see [Create a small talk topic](https://www.servicenow.com/docs/Ck7FzF9m2wuOJS0MXMGo6Q "Build small talk topics that let Virtual Agent engage in casual conversation with users. A small talk topic provides a response to a casual question that users might ask during a conversation, such as the time or date. A small talk topic can occur anytime within a conversation session and can be unrelated to the original conversation intent.") and [Configure small talk filters](https://www.servicenow.com/docs/access?context=configure-small-talk-filters&version=brazil&pubname=brazil-intelligent-experiences&ft:locale=en-US).

## Additional resources {#va-llm__section_u3j_1jz_hcc}

* [Exploring Virtual Agent](https://www.servicenow.com/docs/XXIGI8xIqUOTd3pHv690Og "The ServiceNow Virtual Agent platform provides user assistance through conversations within an intelligent messaging interface. Design and build automated conversations that use large language models (LLMs) and AI to improve deflection rates.")
* [Create LLM assistants](https://www.servicenow.com/docs/VqsI_t6wXOqMqvl1ImGmaA "LLM assistants help with large language model (LLM) topic discovery. The ServiceNow Otto for Virtual Agent assistant is the default LLM assistant created during the Conversational Interfaces Assistants guided setup.")
{#va-llm__ul_gkh_by2_3cc}