---
sourceDocument: Australia Conversational Interfaces
sourceDocumentLink: https://servicenow-prod.fluidtopics.net/r/pt-BR/conversational-interfaces

 Release :

    - australia

ft:locale :

    - pt-BR

ft:publication_title :

    - Australia Conversational Interfaces

ft:clusterId :

    - convint

bundleId :

    - convint

workflow :

    - Platform


---

# Use system-derived entities in an NLU topic

# Use system-derived entities in an NLU topic {#ariaid-title1}

* Versão de lançamento: Australia
* 
* Atualizado 12 de mar. de 2026
* 
* ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 2 min. de leitura

Associate system-derived entities such as such as date, time, duration, or location
with a node in a topic.

## Antes de Iniciar

Create the Booking Reservations NLU model and system entities
(<kbd class="ph userinput">FromLocation</kbd> and <kbd class="ph userinput">ToLocation</kbd>) as
described in [Create a system-derived
entity](https://www.servicenow.com/docs/access?context=create-system-derived-entity&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US). In this example
procedure, you will create a topic that can slot fill locations that are used in an
utterance.

Role required: virtual_agent_admin or admin

## Procedimento

1. [Create a new topic](https://servicenow-prod.fluidtopics.net/3WNRx~5BPFnCGPdkHMS0yQ "Use Virtual Agent Designer to create and modify Virtual Agent topics (conversations). Build your topic to meet a specific objective or goal, such as fulfilling a user's request or helping a user complete a task.") called <kbd class="ph userinput">Booking Reservations</kbd>.  
   When completing the Properties tab, make sure that you choose the Booking Reservations NLU model that you created in an earlier exercise.
2. Drag a Text bot response component onto the canvas, and then select it.  
   In the properties sheet, fill in the fields.{#use-system-entities-va-topic__table_lgy_yyy_2qb__entry__2}

   | Field | Description |
   |-|-|
   | Node name | Type <kbd class="ph userinput">Intro</kbd>. |
   | Response Message | Type <kbd class="ph userinput">Let's get you booked on a flight</kbd>. |
   [Tabela 1. Response Properties sheet]

   {#use-system-entities-va-topic__table_lgy_yyy_2qb}Figura 1. Intro Text response properties
3. Drag a Text user input component onto the canvas.  
   In the properties sheet, fill in the fields.{#use-system-entities-va-topic__table_p4m_fzy_2qb__entry__2}

   | Field | Description |
   |-|-|
   | Node name | Type <kbd class="ph userinput">Fromwhere</kbd>. |
   | Prompt | Type <kbd class="ph userinput">Where are you departing from?</kbd> |
   | Input format | Select Text. This doesn't restrict the input format. |
   | NLU entity | Select <kbd class="ph userinput">FromLocation</kbd>. This list only shows existing entities, such as system entities or entities that you created for the model. |
   | Do not ask users to confirm recognized entity | Select this option to avoid having Virtual Agent ask the user to confirm the location. |
   | Advanced (optional) ||
   | Topic switching ||
   | Enable NLU to switch topics | Slide this toggle switch to enable topic switching. |
   [Tabela 2. User Input Properties sheet]

   {#use-system-entities-va-topic__table_p4m_fzy_2qb} Figura 2. Fromwhere Text user input response properties
4. Drag another Text user input component onto the canvas.  
   In the properties sheet, fill in the fields.{#use-system-entities-va-topic__table_bh3_y1z_2qb__entry__2}

   | Field | Description |
   |-|-|
   | Node name | Type <kbd class="ph userinput">Towhere</kbd>. |
   | Prompt | Type <kbd class="ph userinput">Where are you heading?</kbd> |
   | Input format | Select Text. This doesn't restrict the input format. |
   | NLU Entity | Select <kbd class="ph userinput">ToLocation</kbd>. This list only shows existing entities, such as system entities or entities that you created for the model. |
   | Do not ask users to confirm recognized entity | Select this option to avoid having Virtual Agent ask the user to confirm the location. |
   | Advanced (optional) ||
   | Topic switching ||
   | Enable NLU to switch topics | Slide this toggle switch to enable topic switching. |
   [ ]

   {#use-system-entities-va-topic__table_bh3_y1z_2qb} Figura 3. Towhere Text user input response properties
5. Drag another Text bot response component onto the canvas, and then select it.  
   In the properties sheet, fill in the fields.{#use-system-entities-va-topic__table_qgj_lcz_2qb__entry__2}

   | Field | Description |
   |-|-|
   | Node name | Type <kbd class="ph userinput">Confirmation</kbd>. |
   | Response Message | Type <kbd class="ph userinput">Great! I have you booked on a flight from [Fromwhere] to [Towhere]. Bon voyage!</kbd> Use dot-walking to replace <kbd class="ph userinput">[Fromwhere]</kbd> and <kbd class="ph userinput">[Towhere]</kbd> with the input variables you created in the previous nodes. |
   [ ]

   {#use-system-entities-va-topic__table_qgj_lcz_2qb} Figura 4. Confirmation text response properties
6. Click Save.

## O que Fazer Depois

Use additional system-derived entities for your Booking a Reservation topic. For example, you can use system-derived entities to capture the dates that the user wants to travel.

For more information about default system entities, see
[NLU system entities](https://servicenow-prod.fluidtopics.net/U~I77ckluPcVuR8KnBDOfg "Use globally defined NLU entities to identify system information that Virtual Agent can extract from the conversation. You can define entities as \"nodeless\" input variables for a topic. These variables can be slot-filled from NLU service provider predictions or provided outside of the scope of the topic.").