--- sourceDocument: Brazil Enable AI sourceDocumentLink: https://www.servicenow.com/docs/r/intelligent-experiences Release : - brazil ft:locale : - en-US ft:publication_title : - Brazil Enable AI ft:clusterId : - platai bundleId : - platai workflow : - Platform --- # (Legacy) Natural Language Understanding # (Legacy) Natural Language Understanding {#ariaid-title1} Release version: Brazil Updated September 10, 2026 ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 4 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 (Legacy) Natural Language Understanding ServiceNow® Natural Language Understanding (NLU) provides tools to enable the system to comprehend and respond to human-expressed intents by analyzing natural language input. Users can input example utterances to help the system learn word meanings and context, allowing it to infer user or system actions. Starting with the Brazil release, this legacy NLU feature is being prepared for future deprecation; it will no longer be activated on new instances but will continue to be supported for existing users. Show full answer Show less ## Key Concepts and Terminology * **Intent:** The action or goal a user wants to achieve, such as requesting access. * **Utterance:** A natural language example representing an intent, like a chat message or incident description; these examples train the system to recognize intents. * **Entity:** Context or object related to an intent, such as a laptop or priority level. * **System Entity:** Predefined entities like date, time, or location that are reusable across models. * **User Defined Entity:** Custom entities created from user utterances to tailor recognition. * **Common Entity:** Frequently used contexts extracted by predefined models, e.g., currency or people. * **Vocabulary:** Defines or overrides word meanings, enabling synonym mappings such as linking "MS" to "Microsoft." * **NLU Model:** A collection of utterances, intents, and entities used to infer meaning in new inputs. ServiceNow provides pre-built models (e.g., ITSM), and users can create custom models. ## NLU Workbench The NLU Workbench is a development environment where administrators (with the `nluadmin` role) create, train, test, and publish NLU models iteratively. These models enable ServiceNow applications to interpret natural language inputs by analyzing intents and entities. ## NLU Inference Service This service uses trained NLU models to predict intents and entities from user utterances, converting natural language into machine-understandable formats like APIs and parameters. It supports intelligent system actions based on user input. ## NLU Model Integration Other ServiceNow applications, notably Virtual Agent, consume NLU model outputs. For example, Virtual Agent Designer can be configured to use NLU models to improve chatbot understanding of user conversations, enhancing automation and user interaction. ## Getting Started and Support * **Explore:** Learn foundational NLU concepts and features. * **Use:** Create, test, translate, and publish your NLU models effectively. * **Integrate:** Virtual Agent administrators can update NLU models from within Virtual Agent Designer for seamless integration. * **Reference:** Utilize multilingual models and apply them across various applications. * **Troubleshoot and Support:** Access the Virtual Agent \& NLU community, Known Error Portal, and ServiceNow Customer Service for assistance. ServiceNow® Natural Language Understanding (NLU) provides an NLU Workbench and an NLU inference service that you can use to enable the system to learn and respond to human-expressed intent. By entering natural language examples into the system, you help it understand word meanings and contexts so it can infer user or system actions. ## Overview of Natural Language Understanding {#nlu-landing__section_jhx_jch_czb} Starting with the Brazil release, Natural Language Understanding is being prepared for future deprecation. It will be hidden and no longer activated on new instances but will continue to be supported. For details, see the [Deprecation Process \[KB0867184\]](https://support.servicenow.com/kb_view.do?sysparm_article=KB0867184) article in the Now Support Knowledge Base. For an overview of Natural Language Understanding, see [(Legacy) Exploring Natural Language Understanding](https://www.servicenow.com/docs/qmk7cFiP53zVVcgzHLQ53w "ServiceNow Natural Language Understanding (NLU) provides an NLU Workbench and an NLU inference service that you can use to enable the system to learn and respond to human-expressed intent. By entering natural language examples into the system, you help it understand word meanings and contexts so it can infer user or system actions."). ## NLU terminology {#nlu-landing__section_gzy_5wc_lhb} In NLU parlance, these terms identify the key language components the system uses to classify, parse, and otherwise process natural language content. Intent : Something a user wants to do or what you want your application to handle, such as granting access. Utterance : A natural language example of a user intent. For example, a text string in an incident's short description, a chat entry, or an email subject line. Utterances are used to build and train intents and should therefore not include several or ambiguous meanings or intents. Entity : The object of, or context for, an action. For example: a laptop, a user role, or a priority level. System entity : These are predefined in an instance and have highly reusable meanings, such as date, time, and location. User defined entity : These are created in the system by users and can be built from words in the utterances they create. Common Entity : A context commonly used and extracted via a pre-defined entity model, such as currency, organization, people, or quantity. Vocabulary : Vocabulary is used to define or overwrite word meanings. For example, you can assign the synonym "Microsoft" to the acronym "MS". NLU Model : A collection of utterance examples and their associated intents and entities that the system uses as a reference to infer intents and entities in a new utterance. The NLU Workbench comes with pre-built NLU models for specific business units, such as an ITSM model. You can also create custom models. ## NLU Workbench {#nlu-landing__section_rzv_vwc_lhb} Use the NLU Workbench to create morphological representations of human language. These models enable you to create intents and entities expressed in natural language utterances. Any ServiceNow application can invoke an NLU model to get an inference of intents and entities in a given utterance. Using the nlu_admin role, you build your models in the NLU Workbench, where you create, train, test, and publish them iteratively. For information on how to build and use an NLU model, see: [Create an NLU model](https://www.servicenow.com/docs/o6_p4E164FJ9ILzYDTa2oQ "Create a Natural Language Understanding (NLU) model from scratch. Start with an empty model to have full control over the model's content."). ## NLU inference service {#nlu-landing__section_xrx_rzl_vhb} Natural Language Understanding provides an NLU inference service that helps the system to understand natural language and drive intelligent actions. This service trains and predicts intents and entities for a given user utterance in your model so that its text translates into machine-understandable formats, such as APIs and parameters. The system uses an inference API to train NLU algorithms by using sample record data to identify intents and entities that are strong candidates for accurate prediction. ## NLU model consumption {#nlu-landing__section_frc_bxc_lhb} Other ServiceNow® applications consume NLU model output, such as Virtual Agent. For example, Virtual Agent administrators can configure a Virtual Agent Designer conversation flow to consume NLU models so that agent chatbots can better understand user statements in the conversation. For more information on how Virtual Agent consumes NLU models, see: [Natural Language Understanding (NLU) topic discovery in Virtual Agent](https://www.servicenow.com/docs/access?context=va-NLU&version=brazil&pubname=brazil-conversational-interfaces&ft:locale=en-US). ## Get started {#nlu-landing__section_khx_jch_czb} |-|-| | [ExploreLearn about NLU concepts and features.](https://www.servicenow.com/docs/qmk7cFiP53zVVcgzHLQ53w "ServiceNow Natural Language Understanding (NLU) provides an NLU Workbench and an NLU inference service that you can use to enable the system to learn and respond to human-expressed intent. By entering natural language examples into the system, you help it understand word meanings and contexts so it can infer user or system actions.") | [UseCreate, test, translate, and publish your NLU models.](https://www.servicenow.com/docs/GhPYjJNI5DiQKKyMTLWjlg "Use NLU models to apply ServiceNow Natural Language Understanding on your instances. Create, manage, test, and publish NLU models with the NLU Workbench.") | | [IntegrateLearn how Virtual Agent administrators can update NLU models from within Virtual Agent Designer.](https://www.servicenow.com/docs/wU5g5JzIkl7PDYib9VSAbw "Virtual Agent administrators can access and update their NLU models from within the Virtual Agent Designer user interface.") | [ReferenceLearn about using models in different languages for use in other applications](https://www.servicenow.com/docs/bqb~Xi9ozV6bK6HtPiX1TQ "The NLU Workbench application provides support for creating NLU models in different languages for use in other applications, such as Virtual Agent.") | [ ] {#nlu-landing__table_lhx_jch_czb} ## Troubleshoot and get help {#nlu-landing__section_qhx_jch_czb} * [Virtual Agent \& NLU community page](https://www.servicenow.com/community/virtual-agent-nlu/ct-p/virtual-agent-natural-language) * [Search the Known Error Portal for known error articles](https://support.servicenow.com/kb?id=kb_article_view&sysparm_article=KB0597477) * [Contact Customer Service and Support](https://support.servicenow.com/now?draw=case) {#nlu-landing__ul_rhx_jch_czb}