Together We Can Make World Smarter with LUIS

 What’s LUIS?

LUIS stands for Language Understanding Intelligent Service, developed by MicrosoftIt is so smart that can take your sentences and interpret it in terms of intentions they convey and even the entities that are included in the sentences.

But, Why LUIS?

AI with LUIS

Few benefits you may find from using LUIS:

  1. Fast – LUIS is designed to enable you to quickly deploy an HTTP endpoint that will take the sentences you send it and interpret them in terms of the intention they convey and the key entities that are present.
  2. Self-Learning & Adopt – After your endpoint has processed a few dozen interactions, LUIS begins active learning. LUIS examines all the utterances that have been sent to it, and calls to your attention the ones that it would like you to label.
  3. Pre-Built Domains – In addition to allowing you to build your own applications, it simplifies your jump-start by providing selected set of ready made languages models that can be directly used in your application.
  4. Multi-Lingual Support – LUIS is a multi-lingual platform and can be trained to understand over 10 different languages.


Let’s Get Started!

  1. Logon to and click Sign In on the top right corner.
    AI with LUIS
  2. Sign in with your Microsoft Account. If you do not have one, learn how to create one with Azure here.
  3. Welcome to LUIS! A platform that we can gets app smarter.
  4. Let’s create a New App.
  5. Enter Your Favourite App Name and Language/Culture. Then click Create.
  6. Click the App Name to train and configure.
  7. For your ease, there are plenty of default templates which can serve your apps’ intentions. However, we learn to create one manually today.

  8. Let’s create an Appointment Personal AI today. To begin, click Create an intent which will tell your app to serve some intentions.
  9. Click Add prebuilt domain intents to add some intentions.

  10. Let’s check all Calendar.Add, Calendar.CheckAvailability, Calendar.Delete, Calendar.Edit and Calendar.Find, then Save.
  11. Now you should see list of intents being added.
  12. Click Entities so we can add some entities that possibly involved in the message.
  13. Check both Calendar.Location and Calendar.Subject. Then Save.
  14. Now, we should add some custom entities, such as Name.
  15. Also, we should also add datetime since it is possibly part of the Calendar message.
  16. Under labelled utterances, we can map part of the message with the custom entities that we created just now, then Save it.
  17. Let’s go to Train & Test and hit Train Application.
  18. It will take little a while to train the app…..
  19. When done, you should now can try out with some messages. However, you may notice the result is not capturing all the entities, such as Name & DateTime.
  20. You may go to Entities -> Suggested utterances. There may be some utterances that may need your help to make it even accurate & smarter! Let’s map Name & datetime, then Save & Re-Train.
  21. Finally, click Publish to bring it to Live!
  22. Let’s copy the endpoint URL and try with some query message with browser/Postman tool.
  23. Paste the link onto address bar of browser/ Postman tool together with your message,
    a: EndPoint we copied from the LUIS.AI portal,
    b: Your possible query message.

  24. The result should be returned in JSON string and telling you about:
    a: The Top Scoring Intention – eg. Calendar.Add
    b: The possible involved Entities – eg. Name, Date, Location

  25. Now you can create an App with Model class and deserializing the JSON data string to further your development!
    Congratulation! You have the AI with LUIS now!
    AI with LUIS


Want an Offline Copy? Download yours today!

Are you interested to know more on how to build Smart AI app?
Let me know down at comment or on my Twitter!

Don’t forget to follow me @
Twitter: @hmheng
More slides @ SlideShare:

You may also like...

1 Response

  1. November 6, 2017

    […] is an AI service that understands your intention and involving entities in what you say or type. We have learnt how to create an LUIS app @ Today, we are going to learn how we can integrate it to our mobile app that we […]

This site uses Akismet to reduce spam. Learn how your comment data is processed.

%d bloggers like this: