--- sourceDocument: Australia Conversational Interfaces sourceDocumentLink: https://servicenow-prod.fluidtopics.net/r/de-DE/conversational-interfaces Release : - australia ft:locale : - de-DE ft:publication_title : - Australia Conversational Interfaces ft:clusterId : - convint bundleId : - convint workflow : - Platform --- # Implement NLU in Virtual Agent # Implement NLU in Virtual Agent {#ariaid-title1} * Freigeben Version: Australia * * Aktualisiert 12. März 2026 * * ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 2 Minuten Lesedauer Create and maintain NLU model groups and intents that map to your conversation topics in Virtual Agent. You can create and edit model groups in NLU Workbench or from topics in Virtual Agent Designer. ## Vorbereitungen Activate the plugins for [Glide Virtual Agent](https://servicenow-prod.fluidtopics.net/etu8tyRAVEWVsajjqma~VA "You can activate the Glide Virtual Agent plugin (com.glide.cs.chatbot) if you have the admin role. This plugin automatically activates other necessary plugins if they are not already active.") and any [pre-built topics](https://servicenow-prod.fluidtopics.net/yHSF7VmWRKk7ClfkUI5sPA "Prebuilt Virtual Agent conversations (topics), reusable topic blocks, and ServiceNow NLU models are available for the Virtual Agent platform and various business applications, such as Customer Service Management, HR Service Delivery, IT Service Management, and more.") that you want to use. Role required: virtual_agent_admin or admin ## Warum und wann dieser Vorgang ausgeführt wird When authoring conversations for an NLU instance, be aware of the following guidelines: * Verify that you are in the appropriate application scope before you create or update a topic. For example, if you are creating ITSM topics, verify that you are in the ITSM Virtual Agent Conversations scope, and not the scope for the ITSM NLU Model for Virtual Agent Conversations. * Specify the NLU Model and Associated Intent for the topic in the [Topic Properties tab](https://servicenow-prod.fluidtopics.net/bAhqf9TP9nOl1G3NTNJsQA "The Virtual Agent Designer is a diagram tool for creating and managing assets, which are blueprints for conversations between a Virtual Agent and a user. You can design topics that help your users resolve common work issues or guide them through self-service tasks."). If you want to allow topic switching in the conversation session, enable Resume topic flow. Hinweis: A topic can map to only one intent in an NLU model. Once you select an intent for a topic, the intent is no longer available for use in other topics. * Set the NLU entity properties in the property sheet for each [input control](https://servicenow-prod.fluidtopics.net/3AMBmm98Pv8bH~iHZyFfjw "Use the collection of input controls provided by Assistant Designer to prompt and capture information from the user in a conversation.") that you add to the conversation flow. The entity properties identify the entity associated with the node, a switch for allowing text input for the control (prompt), and another switch for confirming the slot-filled entity value that Virtual Agent extracts. {#implement-nlu-va__ul_kgm_zqp_13b} ## Prozedur 1. [View the Virtual Agent General Settings, and change your NLU service provider, if needed.](https://servicenow-prod.fluidtopics.net/mAuz2V8w3sqMvPQN_Pikbw "Configure Natural Language Understanding (NLU) in Virtual Agent to identify the NLU service provider for your instance. You can also specify the languages of NLU models used during conversation design, based on the languages supported by your NLU provider and the ServiceNow AI Platform.") If you're using a different NLU service provider supported by Virtual Agent, configure it as described in one of the following topics: * [IBM Watson Assistant Intent and Entity integration](https://servicenow-prod.fluidtopics.net/fjl1ae1PmJEgoR0ZuMRICg "Use the intents, entities, and utterances defined in IBM Watson Assistant and apply them as an NLU model for your Virtual Agent conversations.") * [Google DialogFlow Essentials (ES) Intent and Entity integration](https://servicenow-prod.fluidtopics.net/us0rGrNoaz0HobII9WShiQ "Use the intents, entities, and utterances defined in Google Dialogflow ES. Apply them as an NLU model for your Virtual Agent conversations.") {#implement-nlu-va__ul_amp_p1x_frb} 2. **Wahlweise:** If you're supporting conversations in other languages, [enable NLU languages in Virtual Agent settings](https://servicenow-prod.fluidtopics.net/8cYB1vr~JS1uJOsPr~Ke1g "If you plan to use language-specific NLU models, you must enable the installed languages in the Supported NLU Languages list. A language is enabled if the Enabled column displays true. English language is enabled by default."). 3. Associate a model group and intent with each Virtual Agent topic in your instance. You can do this in the following ways: * [Add NLU to an existing Virtual Agent keyword topic.](https://servicenow-prod.fluidtopics.net/xC3c_n9Qo9cA~0pshB4k1Q "Create and map an NLU model group and intent for the topic from Assistant Designer.") * Create or map model groups and intents when you [create a new topic](https://servicenow-prod.fluidtopics.net/l7I4pYbsOhW0Uro3rwhTCg "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."). * [Preview](https://servicenow-prod.fluidtopics.net/1X4RszH69N_IRsqhOB3zFA "Use the chat test window to preview, test, and debug Natural Language Understanding (NLU)/Keyword topics.") and test the pre-built ServiceNow topics in Virtual Agent Designer. Determine whether you want to use any of the topics, then [duplicate](https://servicenow-prod.fluidtopics.net/PFQ9~sp9KYQNkIJPDQa_jA "Create a new topic or topic block by copying an existing Virtual Agent topic or topic block and customize it.") them as needed. * [Run Topic Recommendations reports for your instance](https://servicenow-prod.fluidtopics.net/Hv_f9SRcwu9REtnU~1n_kA "Use the Topic Recommendations app to identify pre-built Virtual Agent topics that can be quickly implemented in your organization. Topic Recommendations uses Intent Discovery to analyze data from your organization and to find relevant pre-built topics that your organization can benefit from, and new topics that would be useful to create.") to identify pre-built Virtual Agent topics and intents that you can quickly implement in your organization. {#implement-nlu-va__ul_z1s_3cx_frb} 4. [Test the topic](https://servicenow-prod.fluidtopics.net/1X4RszH69N_IRsqhOB3zFA "Use the chat test window to preview, test, and debug Natural Language Understanding (NLU)/Keyword topics."). 5. When you're ready to deploy a topic, [publish the topic](https://servicenow-prod.fluidtopics.net/PZAZ0IBob2pV5fn5OmI5dw "Deploy an inactive topic or an updated topic to save it and make it available to users on Virtual Agent clients."). ## Ergebnisse The topic state changes to Active.