With the recent introduction of AWS Tools for Visual Studio Team Services, .NET developers have more ways than ever to easily use AWS services for their .NET applications. In this workshop, we run through building a .NET chatbot as we take advantage of AWS Lambda and Amazon Lex. The best part? You can build and deploy the chatbot directly to AWS without ever leaving Visual Studio.

1. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
AWS re:INVENT
Building a Better .NET Bot with AWS
Services
T a r a W a l k e r
N i c k i l S o m a n n a
W I N 2 0 5
N o v e m b e r 2 8 , 2 0 1 7

2. What to expect from the workshop
 Learn how to create a Amazon Lex ChatBot from AWS
Management Console
 Learn how to create a backend for a Amazon Lex ChatBot with
AWS Lambda
 Learn how to add secure credentials to your Amazon Lex ChatBot
with Amazon Cognito
 Learn how to create a .NET/ASP.NET Core ChatBot solution using
AWS SDK for NET and Visual Studio
 Learn how to deploy a ASP.NET Core ChatBot solution with a
CI/CD pipeline to Amazon EC2 using AWS CodeStar

3. Agenda
• Introduction to Amazon Lex
• Hands-On: Create Your Lex ChatBot
• Introduction to AWS Lambda
• Hands-On: Create Your Lambda function for Lex ChatBot Fulfillment
• Intro to Amazon Cognito
• Hands-On: Create Your Cognito Federated Identity Pool
• Intro to AWS SDK for .NET
• Hands-On: Start Your ASP.NET Core Web ChatBot Solution
• Intro to CI/CD Tools for Deployment: AWS CodeStar
• Hands-On: Use CodeStar to Build & Deploy your ASP.NET ChatBot

4. Prerequisites
• AWS Account
• Visual Studio or Visual Studio Code
• AWS SDK for .NET Toolkit installed
• Basic Linux/Windows Based Environments with .NET
development

5. Introduction to
Amazon Lex
A new service for building
conversational interfaces
using voice and text

6. Text and speech language understanding: powered by the
same technology as Alexa
Enterprise ready: connect to enterprise systems via SaaS
connectors
Versioning and alias support
Build once and deploy to multiple platforms
Designed for builders: efficient and intuitive tools to build
conversations; scales automatically
Amazon Lex - Overview
Continuous learning: monitor and improve your bot

7. Amazon Lex – Multi-platform
Mobile
Messaging
Platforms Web IoT
SDKs: iOS &
Android
Mobile Hub
Facebook, Twilio
SMS and Slack
SDKs: Java, JavaScript,
Python, CLI, .NET, Ruby
on Rails, PHP, Go, & CPP
Integrated with
AWS IoT via AWS
Lambda
Build once and deploy to multiple platforms

8. Amazon Lex – Key Concepts
Utterances
Spoken or typed phrases that
invoke your intent
BookHotel
Intents
An intent performs an action in
response to natural language user input
Slots
Slots are input data required to
fulfill the intent
Fulfillment
Fulfillment mechanism for your
intent

9. Amazon Lex – Example: “Book a hotel”
Book Hotel
NYC
“Book a Hotel in
NYC”
Automatic Speech
Recognition
Hotel Booking
New York City
Natural Language
Understanding
Intent/Slot
Model
UtterancesHotel Booking
City New York City
Check In April 19th
Check Out April 21st
“Your hotel is booked for
April 19th”
Amazon Polly
Confirmation: “Your hotel
is booked for Nov 30th”
“Can I go ahead
with the booking?
a
in

10. Amazon Lex – Slot elicitation
Check In
4/19/2017
City
New York City
I would like to book a hotel
Sure, which city will you
be traveling to?
New York City
What date do you want to
check in?
April 19th

11. Amazon Lex – Dialog management
I would like to book a hotel
Sure, which city will you
be traveling to?
New York City
What date do you want to
check in?
Tomorrow
… And for how many
nights is this for?
City
Simple Declarative Model
Check-In Date
Check-Out Date
Slots
Which city will you be traveling to?
What date do you want to check in?
How many nights is this for?
Prompts
Build Multi-Turn Conversations
Easy Setup in Console

12. Amazon Lex – Customize conversations
I would like to book a hotel
Would you prefer to stay in
Downtown this time as well?
Yes
What date do you want to
check in?
April 19th
Sorry no availability. Would
a different location work?
Personalize conversation
based on user preferences
Validate user input and
re-prompt as necessary

13. Amazon Lex – Error handling
I want to …. {garbled} …..
Sorry can you please
repeat that?
I am having trouble understanding
Can you please say that again?
Sorry I am not able to
assist you at this time
Clarify by requesting user
to repeat
Uses a different
prompt every time
Hang up phrase to end the
conversation

14. Amazon Lex – Conversation context
Slot Values Intents Prompts ConfirmationsSession
Attributes
Slot Value
Slot Value
Conversation
Yes/No
Session
Attributes
Intent
Prompt
Lex maintains context by storing data throughout the conversation
Confirm

15. Amazon Lex – Dynamic conversation flow
Conversation
Session
Attributes
Second
Intent
Switch Intents
First Intent
Session
Attributes
Conversation
Chain Intents
Take out
Dine In
Dine In or
Take out?
Anything
else today?
Book a Car

16. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
HANDS-ON
Amazon Lex
Create Your Lex ChatBot
https://s3.amazonaws.com/win205reinvent2017/Lab1.pdf

17. Introduction to
AWS Lambda
A service for serverless compute.
Run code without provisioning
or managing servers..

18. AWS Lambda – Serverless computing
Run code without servers
Pay only for the compute time you consume.
Extend Other AWS Services with Custom Logic:
Triggered by events or called from APIs
• PUT to an Amazon S3 bucket
• Updates to Amazon DynamoDB table
• Call to an Amazon API Gateway endpoint
• Mobile app back-end call
Automated Administration & Automatic Scaling
Makes it easy to:
• Perform real-time data processing
• Build scalable back-end services
• Glue and choreograph systems

19. AWS Lambda – Service Usage
Authoring functions
• Author directly using the console
WYSIWYG editor
• Package code as a .zip and
upload to Lambda or S3
• Plugins for Visual Studio and
Eclipse
• Command line tools
Monitoring and logging
• Built-in metrics for
requests, errors, latency,
and throttles
• Built-in logs in Amazon
CloudWatch Logs
Flexible authorization
• Securely grant access to
resources, including VPCs
• Fine-grained control over
who can call your functions
Flexible use
• Call or send events
• Integrated with other
AWS services
• Build whole serverless
ecosystems

20. AWS Lambda – Programming Model
Bring your own code
• C#, Node.js, Java,
Python
• Bring your own libraries
(even native ones)
Simple resource model
• Select power rating from
128 MB to 1.5 GB
• CPU and network
allocated proportionately
• Reports actual usage
Programming model
• AWS SDK built in
(Python and Node.js)
• Lambda is the
“webserver”
• Use processes, threads,
/tmp, sockets normally
Stateless
• Persist data using Amazon
DynamoDB, S3, or Amazon
ElastiCache
• No affinity to infrastructure
(can’t “log in to the box”)

21. AWS Lambda – Amazon Lex Fulfillment
AWS Lambda
Integration
Return to
Client
User input parsed by Lex to
derive intents and slot values.
Output returned to client
for further processing
Intents and slots passed
to AWS Lambda function
for business logic
implementation

22. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
HANDS-ON
AWS Lambda
Create Your Lambda function for
Lex ChatBot Fulfillment
https://s3.amazonaws.com/win205reinvent2017/Lab2.pdf

23. Introduction to
Amazon Cognito
A service for adding access control,
authentication, data synchronization, and
user sign-up/sign-in quickly and easily to
your apps like mobile & web apps..

24. Manage authenticated
and guest users’
access to your AWS
resources
Federated
Identities
Synchronize user’s data
across devices and
platforms via the cloud
Data
Synchronization
Add sign-up and
sign-in with a fully
managed user
directory
Your User Pool
GuestYour own
auth
Amazon Cognito Identity Amazon Cognito Sync
Amazon Cognito – Identity and Sync
k/v data

25. Sign in with
Facebook
Or
Username
Password
Sign In
Or
Start as a guest
Authenticate via
3rd party Identity
Providers
Amazon Cognito Identity – User Experience
Guest Access
Your User Pool in
Amazon Cognito
Amazon Cognito
Identity provides
temporary credentials
to securely access
Your resources
DynamoDB
S3
Amazon
Lex
AWS
Lambda
IAM

26. Amazon Cognito – Lex & Federated Identities
Cognito User Identities
(Your User Pool.
Social Media,
SAML, or Unauthenticated )
User
Sign-in or Secure
Guest Access1
Returns Access
and ID Tokens
2
Cognito Federated
Identities
(Identity Pool)Get AWS scoped
credentials
3
Access
to AWS Services
4
Amazon
DynamoDB
Amazon
Lex
AWS
Lambda
IAM
IAM

27. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
HANDS-ON
Amazon Cognito
Create Your Cognito
Federated Identity Pool
https://s3.amazonaws.com/win205reinvent2017/Lab3.pdf

28. Introduction to
AWS SDK for .NET
Takes the complexity out of building .NET
applications with AWS Services
by providing .NET APIs

29. AWS SDK and tools for .NET architectureEXECUTION
PLATFORM
AWSSDK
LOW-
LEVEL
SERVICE
APIS
AWS
TOOLS
HIGHER-
LEVEL
UTILITY
APIS
.NET 4.5 .NET CORE PHONE STORE
SERVICE CLIENTS
AMAZON S3
TRANSFER UTILITY
AMAZON DYNAMODB
OBJECT PERSISTENCE
VM IMPORT RESOURCE API
AWS TOOLS FOR
WINDOWS
POWERSHELL
AWS TOOLKIT FOR
VISUAL STUDIO
ASP.NET SESSION
PROVIDER
TRACE LISTENER
…
AWS ENDPOINTS: REST API
.NET 3.5

30. AWS SDK for .NET – AWS Toolkit for Visual Studio
Full integration in Visual Studio

31. AWS SDK .NET – AWS Tools for Visual Studio Team Services
Deployment Tasks
• Elastic Beanstalk
• Lambda
• CodeDeploy
• CloudFormation
General Purpose Tasks
• S3 uploads/downloads
• Invoking Lambda functions
• Send SNS Messages
• AWS PowerShell commands
• AWS CLI commands
AWS Elastic Beanstalk AWS
Lambda
AWS
CloudFormation
Amazon
S3
AWS
CodeDeploy
AWS
CLI
AWS Tools for
Windows PowerShell
Amazon
SNS
AWS CodeCommit

32. AWS SDK .NET Comprehensive and powerful tools
MonitoringConfiguration
AWS Config
Amazon EC2
Run Command
AWS Tools for
Windows PowerShell
Develop and Deploy
Amazon
CloudWatch
AWS
CloudTrail
AWS
OpsWorks
AWS Toolkit for
Visual Studio
.NET SDK AWS CodeDeploy AWS
Cloud
Formation
AWS Elastic
Beanstalk
AWS
X-Ray
AWS Lambda

33. Introduction to
AWS CodeStar & AWS Dev Tools
Set up your entire continuous delivery
toolchain in minutes, allowing you to start
releasing code faster

34. AWS CodeStar
Develop on AWS in minutes:
Set up your entire CI/CD development environment and
programming tools for coding, testing, and deploying
Collaborate securely with your entire team:
Manage team access and membership to projects
Integrated issue tracking and project management:
Integrates Atlassian JIRA Software to easily manage and
monitor issues & activity from CodeStar dashboard
Support for popular programming languages:
Develop applications using language of choice including
C#, Java, JavaScript, PHP, Ruby, and Python
Release code faster:
Set up your entire continuous delivery toolchain in minutes

35. AWS CodeStar – Features
 Project Templates
 Team Access Management
with AWS IAM
 Managed Build Service with
AWS Code Build
 Unified Project Dashboard
using Amazon CloudWatch
monitoring service
 Issue tracking and project
management via integrated
Atlassian JIRA Software
 AWS CodeCommit and
GitHub integration for
Secure Hosted Git
Repository
 Automated App
Deployments with AWS
CodeDeploy and AWS
CloudFormation
 Integration of AWS
CodePipeline for
Automated Continuous
Delivery Pipeline

36. AWS CodeStar – Automated Continuous Delivery
Each CodeStar project creates and configures a
continuous delivery pipeline
Source Build Test Production
Third Party
Tooling
Software Release Steps:
AWS CodeCommit AWS CodeBuild AWS CodeDeploy
AWS CodePipeline

37. AWS CodePipeline
Continuous delivery service for fast and reliable
application updates
Model and visualize your software release process
Builds, tests, and deploys your code every time there is a
code change
Integrates with third-party tools and AWS

38. AWS CodeCommit
Secure, scalable, and managed Git source control
Automatic encryption at rest and in transit
Supports existing tooling
Highly available

39. AWS CodeBuild
Fully managed build service with pay-as-you-
go pricing
Support for compiling source code, running
tests, and building packages
Enables continuous integration and delivery
EC2

40. AWS CodeDeploy
Automates code deployments to any instance
Handles the complexity of updating your applications
Avoid downtime during application deployment
Deploy to Amazon EC2 or on-premises servers, in any
language and on any operating system
Integrates with third-party tools and AWS

41. AWS CloudFormation
Create templates of your infrastructure
CloudFormation provisions AWS resources based on
dependency needs
Version control/replicate/update templates like code
Integrates with development, CI/CD, management tools

42. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
HANDS-ON
AWS CodeStar
Build and Deploy your ASP.NET
ChatBot
https://s3.amazonaws.com/win205reinvent2017/Lab4.pdf

43. Best practices while building a bot
• Understand the conversation flow
• What information do you need from the conversation
• What is the intent/goal of the conversation
• Validate your input
• Handle errors gracefully
• Add clarification prompts if required
• Test, test and more testing
• Understand Metrics after your Bot is deployed in
production

44. Challenge 1 – Create a basic chat bot
• Be creative
• Think of real world problems that you want to solve
with this Chat Bot
• The sample below shows how you can create a basic
chat bot to launch EC2 instances based on the OS and
Instance type
• https://s3.amazonaws.com/wildrydes-
nickil/ChatOps+using+Amazon+Lex.docx
• The Slack part of the sample is not required. Feel free
to transpose the Lambda function from Python to .NET

45. Challenge 2 – Build a CI/CD pipeline using the
ChatBot you created
This .NET sample given below should give you a good
idea on how you can integrate all the pieces together.
https://github.com/awslabs/aws-lex-net-chatbot

46. © 2017, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Thank you!

47. Amazon Lex – A Complete solution
End to End
Speech to Intent
ASR+NLU
integrated into
one API
Dialog Management
Native support &
maintains context
Text to Speech
Amazon Polly
integrated into API
Business Logic
Native integration
with AWS Lambda
Deployment
One click
deployment
Security
Encrypted data in
transit & at rest
Scale
Completely
managed service
Analytics
Monitor and
improve