You can use the Watson Assistant NLU Connector to connect to IBM Watson Assistant and use the language understanding results from this service to power the NLU of agents within Cognigy.AI.


You'll need the following three credentials to successfully connect to the Watson Assistant service from Cognigy.AI:

  • API Key
  • Skill ID (Workspace ID)
  • Service URL

System Entities - Cognigy Slots

In case you want to use the DATE, NUMBER and DURATION slots of the Cognigy.AI input object you have to add the following Watson Assistant System entities:

  • @sys-date
  • @sys-number
  • @sys-time

For a detailed description see step 2 below.


This section describes the necessary steps for setting up a Watson Assistant NLU Connector.

1. Create a Watson Assistant Service

🔗 In IBM Cloud

Go to IBM Cloud and login or create a new account. After logging in and getting redirected to your Dashboard you should be able to create a new resource by clicking on the Create resource + button.



Scroll down or search for the Watson Assistant service and select it to proceed. 


Once you have completed the creation process, open the settings page of your Watson Assistant Service.

Here you should find the Service URL under the Credentials section. Save this URL for adding to the Cognigy NLU Connector.


Select the Launch Watson Assistant button which leads to the tool for creating new Assistant skills.

2. Create a Skill

Create a new skill by clicking first on the Skills tab in the menu on the left of the screen. Select the Create skill button to add a new Watson Skill.


Please note that the API feature used to connect with Cognigy.AI is not currently available for an Action type skill.


After choosing a skill type, your skill creation is complete and you are now able to add intents and entities to your Watson Assistant skill. 

3. Add the System Entities (optional)

To add the system entities, which enable the possibility to access the DATE, NUMBER and DURATION slots of the input object, you have to click in the skill editor on Entities and then System entities.


Here you should enable:

  • @sys-date
  • @sys-number
  • @sys-time

4. Get the Credentials

Navigate to the skills overview of your Watson Assistant service. Here you should find all of the skills you have created. Now click on the three-dotted button next to the name of the skill which you would like to connect with Cognigy


Select View API Details. Here you can retrieve the following credentials:

  • API Key
  • Skill ID (Workspace ID)


5. Connect the Watson Assistant NLU Connector

🔗 In Cognigy.AI

The last step is to create and configure a Watson Assistant NLU Connector on our Cognigy.AI platform.

In Cognigy.AI, navigate to the NLU connectors menu found under the Build sub-menu in the resources panel. Create a new NLU Connector of type Watson Assistant.


The NLU connector settings will be opened automatically (you can open the settings again by clicking on the NLU connector) where you can find the corresponding fields for the Watson Assistant credentials. Enter the credentials gathered in the earlier steps to connect to the service.


6. Test your NLU Connector

🔗 In Cognigy.AI

Open the interaction panel from the top right of the interface. Select settings, then select the Watson Assistant NLU connector you just created from the NLU Connector dropdown menu. Additionally, enable Expert Mode to get a summary of the intent mapping printed to the chat window.


Now select the chat tab and type a message to your bot that was one of the example sentences you used for intent creation in Watson Assistant. If the connection is successful, you will see an orange box showing the name of the Watson Assistant intent that you configured earlier.


Congratulations, you have successfully connected Watson Assistant as the NLU service for Cognigy.AI!

Deploying your External NLU

Once you have activated an NLU connector, it will become available for use with Endpoints and the Interaction Panel. Visit the Cognigy.AI External NLU documentation page to find out how to deploy your external NLU within the platform.



Please sign in to leave a comment.

Was this article helpful?
0 out of 0 found this helpful