Smarter Serverless Chatbots

Building a simple chatbot is simple - building a great one takes a lot more work. Serverless technology and AI services have put very powerful tools into any developer’s hands, but the ease of using them can make us forget some very basic things - and not even spot some more complex ones.

So, set aside that chatbot you created with that 30min online tutorial. Let me walk you through the journey of designing and building a smarter chatbot using the learnings from my own experiences and mistakes building a digital assistant chatbot.

Transcript

1. Smarter Serverless Chatbots Gillian Armstrong
2. 2 Liberty Information Technology Gillian Armstrong @virtualgill Technologist, Cognitive Technologies Liberty IT / Workgrid Software
3. Our chatbot is built on AWS with Amazon Lex, but all the tips are applicable to all platforms Disclaimer Not all Chatbots use Artificial Intelligence, but today we’re only going to talk about those that use Natural Language Understanding Gillian Armstrong @virtualgill
4. Gillian Armstrong @virtualgill
5. Utterance What the user said Entities Variables like names, places, dates or times Intents What the user means Fulfilment What action to take Response Natural Language Processing Natural Language Understanding Text to Speech Automatic Speech Recognition Gillian Armstrong @virtualgill
6. Gillian Armstrong @virtualgill
7. Gillian Armstrong @virtualgill
8. Gillian Armstrong @virtualgill
9. So what is needed for a smarter chatbot? Gillian Armstrong @virtualgill
10. Get the right Use Case 1 Gillian Armstrong @virtualgill
11. Quick Easy Commands Tell me the weather Turn on the lights! Gillian Armstrong @virtualgill
12. Large Lookups and Lists Tell me all the deals of the day Gillian Armstrong @virtualgill
13. Simple Data Collection I’d like a black coffee What size? Large Gillian Armstrong @virtualgill
14. Simple FAQs What time are you open at? Your chatbot can handle the simple questions so you have more time, it can talk to everyone at once, and it never needs to sleep Gillian Armstrong @virtualgill
15. Anything that is easier to do without a chatbot How do users do this right now? me reminding you not to just build a chatbot without considering other options Sketch from @malweene Gillian Armstrong @virtualgill
16. Why did we build a Chatbot? We work in a large Fortune 100 Company, this means lots of big legacy internal systems and information in lots of different places. We wanted to provide “one place to go” where you could ask your question just the same as you would to a colleague or the help desk…and get an answer, or even some get tasks done for you. Gillian Armstrong @virtualgill
17. Gillian Armstrong @virtualgill
18. https://www.workgrid.com
19. Get your NLU training model right 2 Gillian Armstrong @virtualgill
20. Chatbots aren’t magic (although I wish they were) Gillian Armstrong @virtualgill
21. Gillian Armstrong @virtualgill
22. ORDER COFFEE Intent Utterance ORDER JUICE ORDER SHAKE Gillian Armstrong @virtualgill
23. ORDER COFFEE Intent Utterance ORDER JUICE ORDER SHAKE Fulfillment Gillian Armstrong @virtualgill
24. Intent Utterance I’d like a coffee Please may I have coffee One coffee I’ll take a coffee I want to order a coffee Get me a coffee, thanks I would like to order a juice I’ll take a juice Get me a juice Juice please I want a juice Get me a shake I am going to order a shake One shake please I’ll have a shake My order is a shake Gillian Armstrong @virtualgill
25. Gillian Armstrong @virtualgill
26. Gillian Armstrong @virtualgill
27. Intent Utterance I’d like a coffee Please may I have coffee One coffee I’ll take a coffee I want to order a coffee Get me a coffee, thanks I would like to order a juice I’ll take a juice Get me a juice Juice please I want a juice Get me a shake I am going to order a shake One shake please I’ll have a shake My order is a shake Gillian Armstrong @virtualgill
28. Gillian Armstrong @virtualgill
29. CAT DOG ZEBRA Gillian Armstrong @virtualgill
30. Intent Utterance I’d like a coffee Please may I have coffee One coffee I’ll take a coffee I want to order a coffee Get me a coffee, thanks I would like to order a juice I’ll take a juice Get me a juice Juice please I want a juice Get me a shake I am going to order a shake One shake please I’ll have a shake My order is a shake Gillian Armstrong @virtualgill
31. Intent Utterance I’d like a {DRINK} Please may I have {DRINK} One {DRINK} I’ll take a {DRINK} I want to order a {DRINK} Get me a {DRINK} thanks I would like to order a {DRINK} {DRINK} please I want a {DRINK} Get me a {DRINK} I am going to order a {DRINK} One {DRINK} I’ll have a {DRINK} My order is a {DRINK} Coffee Juice Shake … {DRINK} Entity Gillian Armstrong @virtualgill
32. Intent Utterance I’d like a {DRINK} Please may I have {DRINK} One {DRINK} I’ll take a {DRINK} I want to order a {DRINK} Get me a {DRINK} thanks I would like to order a {DRINK} {DRINK} please I want a {DRINK} Get me a {DRINK} I am going to order a {DRINK} One {DRINK} I’ll have a {DRINK} My order is a {DRINK} Energizer Iron Man Stress Down Veggie Focus Herb Tonic Avo Shake Coffee Shake Choco Shake Uppercut Ginger Shot Espresso Cup of Joe Flat White … {DRINK} Entity Gillian Armstrong @virtualgill
33. You wouldn’t make up training data for other ML – don’t make up your conversational data either. Get it from your users. Gillian Armstrong @virtualgill
34. Remember a chatbot is still an Application, just one with a new Interface 3 Gillian Armstrong @virtualgill
35. Chatbots aren’t magic (although I wish they were) Gillian Armstrong @virtualgill
36. CONTEXT CONVERSATION SESSION CHAT STREAM ANALYTICS NLP + INTENT MAPPING FULFILLMENT … Amazon Lex Amazon VPC AWS Direct Connect AWS Lambda AWS Lambda Amazon DynamoDB Amazon DynamoDB AWS Lambda Amazon CloudWatch Amazon ES IAM Amazon Polly Amazon S3 AWS X-Ray Amazon API Gateway Amazon Athena Amazon S3 Amazon API Gateway THE DIGITAL ASSISTANT BOT PLATFORM ARCHITECTURE
37. CONTEXT CONVERSATION SESSION … AWS Lambda AWS Lambda Amazon DynamoDB Amazon DynamoDB IAM AWS X-Ray Amazon API Gateway THE DIGITAL ASSISTANT BOT PLATFORM ARCHITECTURE
38. CONTEXT CONVERSATION SESSION NLP + INTENT MAPPING … Amazon Lex AWS Lambda AWS Lambda Amazon DynamoDB Amazon DynamoDB IAM Amazon Polly AWS X-Ray Amazon API Gateway THE DIGITAL ASSISTANT BOT PLATFORM ARCHITECTURE
39. CONTEXT CONVERSATION SESSION NLP + INTENT MAPPING FULFILLMENT … Amazon Lex Amazon VPC AWS Direct Connect AWS Lambda AWS Lambda Amazon DynamoDB Amazon DynamoDB AWS Lambda IAM Amazon Polly Amazon S3 AWS X-Ray Amazon API Gateway THE DIGITAL ASSISTANT BOT PLATFORM ARCHITECTURE
40. CONTEXT CONVERSATION SESSION CHAT STREAM ANALYTICS NLP + INTENT MAPPING FULFILLMENT … Amazon Lex Amazon VPC AWS Direct Connect AWS Lambda AWS Lambda Amazon DynamoDB Amazon DynamoDB AWS Lambda Amazon CloudWatch Amazon ES IAM Amazon Polly Amazon S3 AWS X-Ray Amazon API Gateway Amazon Athena Amazon S3 Amazon API Gateway THE DIGITAL ASSISTANT BOT PLATFORM ARCHITECTURE
41. Why Serverless? Gillian Armstrong @virtualgill
42. “Don’t be a serverless hipster” Gillian Armstrong @virtualgill
43. “be a serverless hipster” Gillian Armstrong @virtualgill
44. Serverless means you don’t pay if no-one talks to your bot… Gillian Armstrong @virtualgill
45. Serverless means you don’t pay if no-one talks to your bot… …and lets you scale seamlessly if everyone wants to talk to your bot! Gillian Armstrong @virtualgill
46. Lambdas are quick to develop, isolate small pieces of functionality and allow you to scale different parts of the conversation independently. Gillian Armstrong @virtualgill
47. Being able to change quickly is vital, because you won’t get it right first time. Users will surprise you, you’ll want to keep adding new functionality, and getting natural language understanding to work well takes effort. Gillian Armstrong @virtualgill
48. You can build faster and change faster by using as many managed services as possible. No to servers, yes to services. A chatbot’s power is in its connected services Gillian Armstrong @virtualgill
49. Be careful! Gillian Armstrong @virtualgill
50. It’s important you know the SLA for any APIs you call – how fast do they return? API Lambda function Conversation (especially with Voice) needs to be fast Gillian Armstrong @virtualgill
51. Conversation (especially with Voice) needs to be fast Make sure everything in your architecture scales as well as your lambdas – performance test to verify! API Lambda functions Amazon DynamoDB Gillian Armstrong @virtualgill
52. Monitor, no, seriously, monitor If your chatbot stopped working, would you know? If you have to wait for user complaints you’ve already lost users. Gillian Armstrong @virtualgill
53. Write a great Conversation 4 Gillian Armstrong @virtualgill
54. It’s not poor AI that’s ‘killing’ chatbots – it’s a lack of understanding of good conversational interaction design Gillian Armstrong @virtualgill
55. In a chatbot, Conversation is the Interface Gillian Armstrong @virtualgill
56. Source: http://hosanna1.com/
57. HUMANS TECHNOLOGY HUMAN-COMPUTER INTERACTION psychology emotion mental models mental processing expectation & affordance memory & attention social AI product design copywriting script writing storytelling conversational design voice design personality design creativity imagination language analysis conversational & voice ux data science ML NLP NLU AI cloud services software engineering soundscape design cognitive & socio-linguistics
58. HUMANS TECHNOLOGY HUMAN-COMPUTER INTERACTION psychology emotion mental models mental processing expectation & affordance memory & attention social AI product design copywriting script writing storytelling conversational design voice design personality design creativity imagination language analysis conversational & voice ux data science ML NLP NLU AI cloud services software engineering soundscape design cognitive & socio-linguistics
59. HUMANS TECHNOLOGY HUMAN-COMPUTER INTERACTION psychology emotion mental models mental processing expectation & affordance memory & attention social AI product design copywriting script writing storytelling conversational design voice design personality design creativity imagination language analysis conversational & voice ux data science ML NLP NLU AI cloud services software engineering soundscape design cognitive & socio-linguistics
60. HUMANS TECHNOLOGY HUMAN-COMPUTER INTERACTION psychology emotion mental models mental processing expectation & affordance memory & attention social AI product design copywriting script writing storytelling conversational design voice design personality design creativity imagination language analysis conversational & voice ux data science ML NLP NLU AI cloud services software engineering soundscape design cognitive & socio-linguistics Gillian Armstrong @virtualgill
61. Know how to Analyse and Use Conversational Data 5 Gillian Armstrong @virtualgill
62. Conversational Analytics are vital Is a long conversation better or worse? How critical are returning customers? Work out what metrics you need to track to know how your chatbot is performing. Gillian Armstrong @virtualgill
63. CONTEXT CONVERSATION SESSION CHAT STREAM ANALYTICS NLP + INTENT MAPPING FULFILLMENT … Amazon Lex Amazon VPC AWS Direct Connect AWS Lambda AWS Lambda Amazon DynamoDB Amazon DynamoDB AWS Lambda Amazon CloudWatch Amazon ES IAM Amazon Polly Amazon S3 AWS X-Ray Amazon API Gateway Amazon Athena Amazon S3 Amazon API Gateway THE DIGITAL ASSISTANT BOT PLATFORM ARCHITECTURE
64. CHAT STREAM ANALYTICS Amazon CloudWatch Amazon ES Amazon Athena Amazon S3 Amazon API Gateway THE DIGITAL ASSISTANT BOT PLATFORM ARCHITECTURE
66. Examples of our Analytics Number of users Number of conversations Length of conversations What functionality is being used Where we are getting it right What people want us to add Where we are getting it wrong Gillian Armstrong @virtualgill
67. Getting Feedback is essential. Work to rapidly be able to fix what isn’t working, and add more of what is! You won’t get it right first time – listen to your users, and monitor how well intent recognition is working. Gillian Armstrong @virtualgill
68. Get the right Use Case Get your NLU training model right Remember, it’s still an Application Write a great Conversation Know how to Analyse Conversational Data Have an AWESOME Chatbot Smarter Serverless Chatbot Checklist Gillian Armstrong @virtualgill
69. Got questions? Let’s chat! @virtualgill http://virtualgill.io
70. 70 Liberty Information Technology Gillian Armstrong @virtualgill Technologist, Cognitive Technologies Liberty IT / Workgrid Software