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

 Release :

    - australia

ft:locale :

    - en-US

ft:publication_title :

    - Australia Conversational Interfaces

ft:clusterId :

    - convint

bundleId :

    - convint

workflow :

    - Platform


---

# Configure IBM Watson Assistant as the NLU provider for Virtual Agent

# Configure IBM Watson Assistant as the NLU provider for Virtual Agent {#ariaid-title1}

* Release version: Australia
* 
* Updated March 12, 2026
* 
* ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 2 minutes to read

Use the intents, entities, and utterances defined in IBM Watson Assistant and apply them as
an NLU model for your Virtual Agent
conversations.

## Before you begin

In IBM Watson Assistant, do the following:

* In your IBM account, create a [Resource Link](https://www.ibm.com/docs/en/opw/8.3.0?topic=links-resource) in the AI (Artificial Intelligence) category. Once you have created the Resource Link, you should see the API key and URL:

* In your workspace, define the intents, entities, and utterances for your NLU model.
* Locate your workspace credentials and copy the workspace Password, which you must provide when setting your credentials during configuration.
{#configure-watson-service-integration__ul_f2t_rs1_13b}

In your ServiceNow instance, make sure that the Glide Virtual Agent plugin (com.glide.cs.chatbot) is activated. This plugin
installs the proxy agent for the IBM Watson Natural Language
Understanding server plugin (com.glide.nlu.ibmwatson.intent.discovery), which is
needed for this integration.

Role required: admin

## About this task

Configuring the IBM Watson Assistant integration involves providing IBM Watson Assistant credentials for authentication. You can set only one NLU service provider for your instance.  
Note:  
If you upgraded from a previous release, the upgrade process automatically retains the IBM Watson Assistant workspace Password that you provided.  
As of the Quebec release, Virtual Agent supports legacy version 1 URLs only:

* Models: `https://<IBM
  HOST>/assistant/api/{{api_version}}/workspaces?version={{published_version}}`
* Intents: `https://<IBM
  HOST>/assistant/api/{{api_version}}/workspaces/{{model_id}}/intents?version={{published_version}}&page_limit=1000`
* Entities: `https://<IBM
  HOST>/assistant/api/{{api_version}}/workspaces/{{model_id}}/entities?version={{published_version}}
  `
* Prediction: `https://<IBM
  HOST>/assistant/api/{{api_version}}/workspaces/{{model_id}}/message?version={{published_version}}`
{#configure-watson-service-integration__ul_sw3_5k5_25b}

## Procedure

1. Set the IBM Watson endpoint in your ServiceNow instance for each of the following HTTP(s) Connections records:  
   * IBM Watson NLU Models
   * IBM Watson NLU Intents
   * IBM Watson NLU Entities
   * IBM Watson NLU Prediction
   {#configure-watson-service-integration__ul_zpy_qnt_25b}
   1. Navigate to All, and then enter <kbd class="ph userinput">http_connection.list</kbd> in the filter.
   2. In the HTTP(s) Connections page, select an IBM Watson entry in the Name column to open the record.  
   3. Edit the URL in the Host and Base path fields to reflect the endpoint in your IBM Watson NLU account.  
   4. Select Update.
   5. Repeat these steps for the remaining IBM Watson records.
   {#configure-watson-service-integration__substeps_axp_tft_25b}
2. Add the IBM Watson NLU API key in your ServiceNow instance for each of the following Basic Auth Credentials records:  
   * IBM Watson NLU Models
   * IBM Watson NLU Intents
   * IBM Watson NLU Entities
   * IBM Watson NLU Prediction
   {#configure-watson-service-integration__ul_vm4_npt_25b}
   1. Navigate to All, and then enter <kbd class="ph userinput">basic_auth_credentials.list</kbd> in the filter.
   2. In the Basic Auth Credentials page, select an IBM Watson entry in the Name column to open the record.
   3. In the Password field, enter the IBM Watson NLU API key.  
   4. Select Update.
   5. Repeat these steps for the remaining IBM Watson records.
   {#configure-watson-service-integration__substeps_ejv_ryf_25b}
3. Make the IBM Watson NLU service active.
   1. Navigate to All, and then enter <kbd class="ph userinput">open_nlu_driver.list</kbd> in the filter.
   2. In the Open NLU Drivers table, locate the IBM Watson Script record and in the Active field, set the value to true.  

      Activating this setting adds IBM Watson - Script active to the list of available NLU services in Virtual Agent settings.
   {#configure-watson-service-integration__substeps_kdv_j22_dnb}
4. To enable NLU in your instance, navigate to Conversational InterfacesSettings, and then do the following:
   1. Click Virtual Agent.
   2. Under Natural Language Understanding (NLU), click View Settings.
   3. Slide the Activate toggle switch to enable Natural Language Understanding.
   4. In the NLU service provider list, select IBM Watson - Script.
   5. If you plan to use language-specific NLU models, enable the languages in the Supported NLU Languages list.  
      A language is enabled if the Enabled column displays true. For more information, see [Enable NLU languages in Virtual Agent settings](https://www.servicenow.com/docs/TrUUW9AP~lj1zf0Cuqu7RA "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.").
   6. Click Save.

   {#configure-watson-service-integration__substeps_sbd_kqb_23b}  
   IBM Watson Assistant is the NLU service provider for your instance.
{#configure-watson-service-integration__steps_v3j_gpy_zhb}

*[\>]: and then