Build a ChatBot in 10 minutes!

Use serverless technology such as AWS Lambda to build a chatbot with AWS Lex

Transcript

1. Build a ChatBot in 10 Minutes!
   Serverless Summit 2017, Bangalore
   @dwmkerr
   #inserverless
   Dave Kerr
   Senior Expert, McKinsey & Company
   

   View Slide

2. …or… chatbot jugaad!
   @dwmkerr
   #inserverless
   

   View Slide

3. Thank-you to the organisers and sponsors!
   

   View Slide

4. Who am I?
   @dwmkerr
   #inserverless
   

   View Slide

5. I am a technology consultant.
   @dwmkerr
   #inserverless
   

   View Slide

6. View Slide

7. Which is closer to this…
   @dwmkerr
   #inserverless
   

   View Slide

8. View Slide

9. What am I going to talk about?
   @dwmkerr
   #inserverless
   

   View Slide

10. Chatbots!
    @dwmkerr
    #inserverless
    Perfect for serverless technology. Today is about fun, not ROI!
    

    View Slide

11. …I’ve got to come clean about
    something…
    @dwmkerr
    #inserverless
    

    View Slide

12. …I know almost nothing about
    chatbots!
    @dwmkerr
    #inserverless
    

    View Slide

13. Lawrence Hunt, Selin Lanzafame, Dave Kerr
    

    View Slide

14. Introducing Lex
    @dwmkerr
    #inserverless
    

    View Slide

15. “Amazon Lex is an AWS service for building conversational interfaces for any applications using
    voice and text. With Amazon Lex, the same conversational engine that powers Amazon Alexa
    is now available to any developer, enabling you to build sophisticated, natural language
    chatbots into your new and existing applications. Amazon Lex provides the deep functionality
    and flexibility of natural language understanding (NLU) and automatic speech recognition
    (ASR) so you can build highly engaging user experiences with lifelike, conversational
    interactions, and create new categories of products.”
    @dwmkerr
    #inserverless
    

    View Slide

16. Say what?
    @dwmkerr
    #inserverless
    

    View Slide

17. Let’s see it in action!
    @dwmkerr
    #inserverless
    

    View Slide

18. Demo 1: Get a boring-bot running
    https://github.com/dwmkerr/lex-starter-kit
    refs/heads/demo1
    @dwmkerr
    #inserverless
    

    View Slide

19. We setup the project with make setup
    @dwmkerr
    #inserverless
    

    View Slide

20. We can deploy lex models with make deploy
    

    View Slide

21. Here’s how our conversation looks so far
    @dwmkerr
    #inserverless
    

    View Slide

22. Getting Input
    @dwmkerr
    #inserverless
    

    View Slide

23. Most conversations need input!
    @dwmkerr
    #inserverless
    

    View Slide

24. Demo 2: Getting Input with Slots
    https://github.com/dwmkerr/lex-starter-kit
    refs/heads/demo2
    @dwmkerr
    #inserverless
    

    View Slide

25. We configure the environment with make config
    

    View Slide

26. We can deploy lex models with make deploy
    

    View Slide

27. Our conversation flow is now more complete
    

    View Slide

28. Cool kids use the shell for
    everything
    github.com/dwmkerr/effective-shell
    @dwmkerr
    #inserverless
    

    View Slide

29. Intermission: Using lex-chat
    https://github.com/dwmkerr/lex-chat
    @dwmkerr
    #inserverless
    

    View Slide

30. Using sessions to manage
    conversation state
    @dwmkerr
    #inserverless
    

    View Slide

31. Sometimes we have state which
    we build up over a conversation…
    @dwmkerr
    #inserverless
    

    View Slide

32. Demo 3: Sessions
    https://github.com/dwmkerr/lex-starter-kit
    refs/heads/demo3
    @dwmkerr
    #inserverless
    

    View Slide

33. Use the session to persist conversation state
    between intents
    

    View Slide

34. This gets complex! When do you
    clear a session?
    At least you save time on the
    scripting J
    @dwmkerr
    #inserverless
    

    View Slide

35. Bootstrap your bots, and join in
    for the next set of features!
    github.com/dwmkerr/lex-starter-kit
    github.com/dwmkerr/lex-chat
    @dwmkerr
    #inserverless
    

    View Slide

36. Thanks!
    @dwmkerr
    dwmkerr.com
    github.com/dwmkerr
    linkedin.com/in/dwmkerr
    

    View Slide

37. Appendices
    @dwmkerr
    #inserverless
    

    View Slide

38. Tips and Tricks
    • Question marks in intent utterances will break Lex!
    • Train with realistic data
    • Complicated or very variable slots are very hard to work with (e.g.
    sentences), consider using cards
    • Encrypt sensitive environment variables such as keys when using
    lambda functions
    @dwmkerr
    #inserverless
    

    View Slide