---
sourceDocument: Australia Enable AI
sourceDocumentLink: https://servicenow-prod.fluidtopics.net/r/pt-BR/intelligent-experiences

 Release :

    - australia

ft:locale :

    - pt-BR

ft:publication_title :

    - Australia Enable AI

ft:clusterId :

    - platai

bundleId :

    - platai

workflow :

    - Platform


---

# Import an NLU intent

# Import an NLU intent {#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

As you create intents for your Natural Language Understanding (NLU) model, you can also import and reuse intents from other models in the same application scope. Reusing intents saves time when building new models.

## Antes de Iniciar

* Make sure that the NLU Workbench plugin, NLU Workbench - Core plugin, and Predictive Intelligence plugin are all installed and activated on your instance.
* You can import intents for Virtual Agent and AI Search models.
* Verify that the application scope of your source model and target model are the same.
* Role required: nlu_editor, nlu_admin, or admin
{#import-nlu-intent__ul_shl_vvs_tgb}

## Por Que e Quando Desempenhar Esta Tarefa

When you import an intent, the following associated items are also imported:

* training utterances, with their entity annotations
* entities
{#import-nlu-intent__ul_ont_zm4_lwb}  
The following items are not included when importing an intent:

* test utterances in the default test set
* regular and pattern vocabulary

{#import-nlu-intent__ul_hqt_jn4_lwb}  
Nota:  
You cannot import intents in the following situations:

* When the model already has an intent with the same name as the intent you are trying to import.
* When the model already has an entity with the same name but different attributes as what you are trying to import.
{#import-nlu-intent__ul_sj4_ndn_lwb}

In this example scenario, you are building the content of your NLU model and you want to enhance the model by reusing intents from another model.

## Procedimento

1. Ensure that you are in the target application scope, and navigate to AllNLU WorkbenchModels.  
   The Virtual Agent tab opens by default.
2. Select the tab for your model's application, then select the name of the model you want to add an intent to.
3. In the model overview page, find the Build and train your model phase and select View phase.
4. In the Intents tab, select Import intents.  
   The Import intents screen appears, showing a list of NLU models from which you can select intents to import.
5. Locate the intents you want to import, and select their check boxes.  

   In this scenario, you select the OpenITTicket intent in the ITSM NLU Model for Virtual Agent Conversations model.
6. Select Import.  
   Result: The #OpenITTticket intent appears in the intents list of your target model. By importing this particular intent, you have added 29 additional training utterances to
   your model.

## O que Fazer Depois

Review the annotations of the newly imported training utterances. Add vocabulary annotation if needed.

Train your model to save your updates. For issues with intents, see [Resolve intent issues](https://servicenow-prod.fluidtopics.net/JFx2D84nrbHFV~Zmkkdvag "Use the issue cards to identify intents that have conflicts, need reviewing, or need more utterances. Resolving intent issues ensures the intents in your Natural Language Understanding (NLU) models work properly.").

If there are any secondary language models associated to your target model, consider importing and translating the new content. See [Import primary model content to a secondary model](https://servicenow-prod.fluidtopics.net/lu2EKpM9gbcj1bnB3JqT1Q "When content in your primary NLU model is updated, you can import the updates directly to secondary models.").

For information about prebuilt Virtual Agent models that you can import from, see [Reusing intents from prebuilt NLU models](https://servicenow-prod.fluidtopics.net/7ZSoCibZK6qGiUA1yWdYaQ "Reuse Natural Language Understanding (NLU) intents by importing them from a prebuilt NLU model to other models. Reusing intents saves time when building your models.").