SlideShare a Scribd company logo
1 of 45
Download to read offline
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Bring the Power of AI to Your
Amazon Connect Contact Center
Dan Perry
Senior Product Owner
Liberty Mutual
Insurance
B A P 3 2 2
Laura McFarland
Technologist
Liberty Mutual
Insurance
Marc Rudkowski
Principal Consultant
AWS Professional
Services
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Agenda
• Business case
• Demo
• Architecture
• Best practices
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Improving contact centers with artificial
intelligence
A m a z o n
L e x
A m a z o n
T r a n s c r i b e
A m a z o n
C o m p r e h e n d
T R A N S C R I P T
A m a z o n
C o n n e c t
Analytics
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Improving contact centers with artificial
intelligence
A m a z o n
L e x
A m a z o n
T r a n s c r i b e
A m a z o n
C o m p r e h e n d
T R A N S C R I P T
A m a z o n
C o n n e c t
Analytics
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Making the business case
Meets an emerging technology
• Within our US operation, we receive
millions of calls annually across claims
& service call centers
• Some of which are repetitive & direct
• Offering up an opportunity for
automation
• Our customers expect 24/7 access
• No hold time
• Quick resolution of their inquiry
When a customer’s needs
External
Internal
The big bang …
Voice
revolution
Chatbot
evolution
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
= Intents
Building a chatbot roadmap
Conversational complexity
Frequency
Building a data-driven
framework
… from a wide breadth of
resources
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Designing an MVP
Can we build a conversational chatbot that:
1. Interacts with our customers
2. Can answer a subset of claims rental car-related inquiries
3. Touches upon all KPIs needed to address scalability
Business
viability
Does the platform
integrate with our systems
... is it stable, scalable,
secure?
Technical
feasibility
Customer
desirability
Is the forecasted ROI
economically sound?
Do customers want to
engage with the chatbot &
can it embody our
company, our values?
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AWS services
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
A new way of developing the design
GUI
CSS
Home screen
Screen flow
Screen components
VUI
Persona
Introduction sentence
Script Flow
Conversation script
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
VUI designing
Professional call center persona
“Hi there, I can help you with your
rental car today …”
Amazon Lex only able to
misunderstand twice
Intents to handle “Can you repeat that”
After Intent is fulfilled, “What else can I
help you with today”
VUI
Persona
Introduction sentence
Script flow
Conversation script
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
VUI designing Text to speech (TTS) prompts include
punctuation marks to add emphasis or
pauses.
Use SSML (Speech Synthesis Markup
Language) for additional controls over
speech generation. Amazon Polly
console great for learning SSML.
<break time="1s"/> 1 second pause
Initial scripts—reviewed with UX
psychologist.
Held user experience testing session.
VUI
Persona
Introduction sentence
Script flow
Conversation script
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
VUI designing—Script and flows
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
A new way of developing the design
Partnered with AWS Professional Services
to get access to:
Amazon Connect & Amazon Lex expert
VUI designer from VoiceFoundry
UX psychologist
PhD in cognitive and neural sciences
Partnered with AWS in a consultancy
Their responsiveness and fast feedback kept our MVP
project on a fast pace
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Learning and evolving architecture
We had an emerging serverless architecture
AWS Cloud
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Evolving architecture—Top tips
AWS Cloud
Get out of the console early & start
developing AWS CloudFormation
templates
Reporting, alerting, …
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Evolving architecture—Top tips
AWS Cloud
https://aws.amazon.com/about-aws/whats-
new/2018/
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Evolving architecture
Amazon S3 Alarm
CALL
CENTER
software
JSON
JSON
JSON
AWS Cloud
Solid architect pattern
established
ProxyGateway
Logs, Alarms & Reports
Rental Bot FeedbackBot
Lambda Data Gathers
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Call flow and data flow in action
Amazon S3 Alarm
CALL
CENTER
software
JSON
JSON
JSON
AWS Cloud
ProxyGateway
2. New call event sent
4. Data pulled & front loaded into
DynamoDB
6. Amazon Lex accesses caller data
to have intelligence about caller
…
JSON
… … …
JSON
Logs, Alarms & Reports
Rental Bot FeedbackBot
Lambda Data Gathers
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Lex under the hood
Has my rental been
authorized?
According to your claim
file, your rental is
scheduled to begin on 30
March and is approved for
10 days
Are there other rental car
questions I can help you
with today?
Rental authorized intent
Caller’s utterance matches an intent
Fulfillment lambda populates the static
text with caller data & passes it to
Amazon Lex via a PostText
Follow-up prompt to
continue or end call
I see we have a rental car
already set up for you. Do
you want to hear the
details?
Amazon Lex calls the fulfillment lambda
with caller’s session data in the request
Lambda uses the session data to get the
front-loaded caller data from DynamoDBYes
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Lex intents
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Lex intents, sample utterances, and slot usage
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Lex intent and sample utterances testing
Automated utterances tested using Amazon
Lex runtime API PostText
https://docs.aws.amazon.com/lex/
latest/dg/API_runtime_PostText.html
Can send text or SSML
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Lex intent and sample utterances testing
Request
POST /bot/botName/alias/botAlias/user/userId/text HTTP/1.1
Content-type: application/json
{
"inputText": "the utterance text to send",
"requestAttributes": { "string" : "string" },
"sessionAttributes": { "string" : "string" }
}
Response
{
"dialogState": "Fulfilled",
"intentName": "IntentNameUsed",
"message": ”Response message from intent",
...
}
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Lex intent and sample utterances testing
For rental authorization intent
{ "Authorized" },
{ "Authorization" },
{ "Authorized rental" },
{ "Rental authorized" },
{ "Rental authorization" },
{ "Has my rental been authorized" },
{ "Is my rental authorized" },
{ "I need to know if my rental car is authorized" },
{ "I want to know if my rental has been authorized" },
{ "Trying to get my reservation with approved" },
{ "Send an authorization out" },
{ "You guys haven't approved the rental yet" },
...
assertEquals(response.intentName, "Authorized_Rental”)
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Lex intent and sample utterances testing
Automated CI/CD pipeline
Code check in followed by pull request
Static analysis runs—Sonar, Lint, CheckStyle
Built & deployed to AWS dev account
Bamboo job kicks off Java app tests with each
bot’s intents test utterance text
AWS SDK included to call Amazon Lex runtime API
Results pulled into Allure
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Utterance refinement procedure
Used 3,000+ example rental queries from our call center
transcripts to create our utterance test cases
Each utterance test case has a single Amazon Lex intent it
must match to
Advice was to aim for 75% match for MVP
First run of the tests was not good news
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Utterance refinement procedure
But we just gamified utterance testing!
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Utterance refinement procedure
one intent at a time
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Utterance refinement procedure
Before refinement
"sampleUtterances": [
"Has {Rental} been {Authorized}",
"Has my {Rental} been {Authorized}",
"Is my {Rental} {Authorized}
]
After refinement
"sampleUtterances": [
"{Authorized} {Rental}",
"Has {Rental} been {Authorized}",
"Has my {Rental} been {Authorized}",
"Is my {Rental} {Authorized}",
"Send an {Authorized}",
"If {Rental} has been {Authorized}”
]
Enums
"Rental": [
{"value": "rental vehicle"},
{"value": "rental car"},
{"value": "car rental"},
{"value": "vehicle rental"},
{"value": "rented car"},
{"value": "rented vehicle"}
]
"Authorized”: [
{"value": "authorized"},
{"value": "allowed"},
{"value": "approved"},
{"value": "authorize"},
{"value": "approval"},
{"value": "approve"},
{"value": "authorization"}
]
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Caller interactions with Amazon Lex
what i wanna know
is when i rent a car
say for her does my
insurance cover it
do i qualify for a rental
car with my claim
rental set
up
rental car
schedule
rental car
extension
rental
details
how much money do
I have to rent a car
no but thank
you very much
for the
information
that’s all
thank you
very much
can you repeat
that for me
That’s good
thank you
yes
ma’am
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
MVP project timeline
Team—seven + AWS Professional
Services
Continue evolving fast & create new
intent areas
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Rental chatbot results
10-15%Call deflection
Utterance
recognition
Customer
<5%Callbacks
>90%
Call volume
experience
7/10
- “A good experience.”
- “You’re very good
help.”
- “Pleased with my
service.”
Wk1 Wk2 Wk3 Wk4 Wk5 Wk6
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Polyglot programming
Pair programming
Mob code reviewing
The squad
Serverless architecture
Event-driven design
Cloud native
CI/CD pipelines
TDD
Fully automated testing
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Building your next customer self-service voice
experience—Best practices
Building the customer experience
• Pick a use case that allows you to vet some of your key business
requirements, but be pragmatic about complexity
• Customer experience is as important as the technology:
• Delight customers
• Leverage your data and anticipate why they’re calling
• Iterate and validate with real end-user/customers
• Leverage automated testing to improve effectiveness and containment
of your experience
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Building your next customer self-service voice
experience—Best practices
Learn from existing approaches:
• Build a Q&A bot
• Understand how to leverage Lambda with Amazon Lex
• Build an automated AI experience with Amazon Connect and Salesforce
• Build your own text-to-speech applications with Amazon Polly
• Explore and build experiences with Alexa and Alexa for Business
Thank you!
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AWS console—
Amazon Lex
https://aws.amazon.com/blogs/machi
ne-learning/building-better-bots/
Niranjan Hira and Harshal
Pimpalkhute
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
The console—Amazon
Connect
https://aws.amazon.com/blogs/aws/n
ew-amazon-connect-and-amazon-lex-
integration/
Randall Hunt

More Related Content

What's hot

Build a Voice-Based Chatbot for Your Amazon Connect Contact Center (BAP401-R1...
Build a Voice-Based Chatbot for Your Amazon Connect Contact Center (BAP401-R1...Build a Voice-Based Chatbot for Your Amazon Connect Contact Center (BAP401-R1...
Build a Voice-Based Chatbot for Your Amazon Connect Contact Center (BAP401-R1...Amazon Web Services
 
Ask an Amazon Redshift Customer Anything (ANT389) - AWS re:Invent 2018
Ask an Amazon Redshift Customer Anything (ANT389) - AWS re:Invent 2018Ask an Amazon Redshift Customer Anything (ANT389) - AWS re:Invent 2018
Ask an Amazon Redshift Customer Anything (ANT389) - AWS re:Invent 2018Amazon Web Services
 
Serverless Architectural Patterns and Best Practices (ARC305-R2) - AWS re:Inv...
Serverless Architectural Patterns and Best Practices (ARC305-R2) - AWS re:Inv...Serverless Architectural Patterns and Best Practices (ARC305-R2) - AWS re:Inv...
Serverless Architectural Patterns and Best Practices (ARC305-R2) - AWS re:Inv...Amazon Web Services
 
Alexa for Device Makers: Create Products with Alexa Built-In Using AVS (ALX30...
Alexa for Device Makers: Create Products with Alexa Built-In Using AVS (ALX30...Alexa for Device Makers: Create Products with Alexa Built-In Using AVS (ALX30...
Alexa for Device Makers: Create Products with Alexa Built-In Using AVS (ALX30...Amazon Web Services
 
Build Your Own Royal Wedding Celebrity Viewing Experience (CTD401) - AWS re:I...
Build Your Own Royal Wedding Celebrity Viewing Experience (CTD401) - AWS re:I...Build Your Own Royal Wedding Celebrity Viewing Experience (CTD401) - AWS re:I...
Build Your Own Royal Wedding Celebrity Viewing Experience (CTD401) - AWS re:I...Amazon Web Services
 
Accelerate ML Training on Amazon SageMaker Using GPU-Based EC2 P3 Instances (...
Accelerate ML Training on Amazon SageMaker Using GPU-Based EC2 P3 Instances (...Accelerate ML Training on Amazon SageMaker Using GPU-Based EC2 P3 Instances (...
Accelerate ML Training on Amazon SageMaker Using GPU-Based EC2 P3 Instances (...Amazon Web Services
 
Lower Costs on Amazon EMR: Auto Scaling, Spot Pricing, & Expert Strategies (A...
Lower Costs on Amazon EMR: Auto Scaling, Spot Pricing, & Expert Strategies (A...Lower Costs on Amazon EMR: Auto Scaling, Spot Pricing, & Expert Strategies (A...
Lower Costs on Amazon EMR: Auto Scaling, Spot Pricing, & Expert Strategies (A...Amazon Web Services
 
Exploiting IoT & Machine Learning to transform Power and Utilities
Exploiting IoT & Machine Learning to transform Power and UtilitiesExploiting IoT & Machine Learning to transform Power and Utilities
Exploiting IoT & Machine Learning to transform Power and UtilitiesAmazon Web Services
 
Dissecting Media Asset Management Architecture and Media Archive TCO (MAE301)...
Dissecting Media Asset Management Architecture and Media Archive TCO (MAE301)...Dissecting Media Asset Management Architecture and Media Archive TCO (MAE301)...
Dissecting Media Asset Management Architecture and Media Archive TCO (MAE301)...Amazon Web Services
 
What's New with Amazon Redshift ft. McDonald's (ANT350-R1) - AWS re:Invent 2018
What's New with Amazon Redshift ft. McDonald's (ANT350-R1) - AWS re:Invent 2018What's New with Amazon Redshift ft. McDonald's (ANT350-R1) - AWS re:Invent 2018
What's New with Amazon Redshift ft. McDonald's (ANT350-R1) - AWS re:Invent 2018Amazon Web Services
 
Accelerate Digital Transformation for Telecom Operators with Cloud-Native Amd...
Accelerate Digital Transformation for Telecom Operators with Cloud-Native Amd...Accelerate Digital Transformation for Telecom Operators with Cloud-Native Amd...
Accelerate Digital Transformation for Telecom Operators with Cloud-Native Amd...Amazon Web Services
 
Computing at the Edge with AWS Greengrass and Amazon FreeRTOS, ft. General El...
Computing at the Edge with AWS Greengrass and Amazon FreeRTOS, ft. General El...Computing at the Edge with AWS Greengrass and Amazon FreeRTOS, ft. General El...
Computing at the Edge with AWS Greengrass and Amazon FreeRTOS, ft. General El...Amazon Web Services
 
Breaking Up the Monolith While Migrating to AWS (GPSTEC320) - AWS re:Invent 2018
Breaking Up the Monolith While Migrating to AWS (GPSTEC320) - AWS re:Invent 2018Breaking Up the Monolith While Migrating to AWS (GPSTEC320) - AWS re:Invent 2018
Breaking Up the Monolith While Migrating to AWS (GPSTEC320) - AWS re:Invent 2018Amazon Web Services
 
Have Your Front End and Monitor It, Too (ANT303) - AWS re:Invent 2018
Have Your Front End and Monitor It, Too (ANT303) - AWS re:Invent 2018Have Your Front End and Monitor It, Too (ANT303) - AWS re:Invent 2018
Have Your Front End and Monitor It, Too (ANT303) - AWS re:Invent 2018Amazon Web Services
 
ALB User Authentication: Identity Management at Scale with Netflix (NET204) -...
ALB User Authentication: Identity Management at Scale with Netflix (NET204) -...ALB User Authentication: Identity Management at Scale with Netflix (NET204) -...
ALB User Authentication: Identity Management at Scale with Netflix (NET204) -...Amazon Web Services
 
Inventory, Track, and Respond to AWS Asset Changes within Seconds at Scale (S...
Inventory, Track, and Respond to AWS Asset Changes within Seconds at Scale (S...Inventory, Track, and Respond to AWS Asset Changes within Seconds at Scale (S...
Inventory, Track, and Respond to AWS Asset Changes within Seconds at Scale (S...Amazon Web Services
 
How Rovio Uses ML to Acquire, Retain, and Monetize Users (GAM304) - AWS re:In...
How Rovio Uses ML to Acquire, Retain, and Monetize Users (GAM304) - AWS re:In...How Rovio Uses ML to Acquire, Retain, and Monetize Users (GAM304) - AWS re:In...
How Rovio Uses ML to Acquire, Retain, and Monetize Users (GAM304) - AWS re:In...Amazon Web Services
 
M&E Leadership Session: The State of the Industry, What's New from AWS for M&...
M&E Leadership Session: The State of the Industry, What's New from AWS for M&...M&E Leadership Session: The State of the Industry, What's New from AWS for M&...
M&E Leadership Session: The State of the Industry, What's New from AWS for M&...Amazon Web Services
 
Set Up a Communications Platform on AWS with AI-Enhanced Services (TLC302) - ...
Set Up a Communications Platform on AWS with AI-Enhanced Services (TLC302) - ...Set Up a Communications Platform on AWS with AI-Enhanced Services (TLC302) - ...
Set Up a Communications Platform on AWS with AI-Enhanced Services (TLC302) - ...Amazon Web Services
 
Deploying Your ONNX Deep Learning with Apache MXNet Model Server (AIM413) - A...
Deploying Your ONNX Deep Learning with Apache MXNet Model Server (AIM413) - A...Deploying Your ONNX Deep Learning with Apache MXNet Model Server (AIM413) - A...
Deploying Your ONNX Deep Learning with Apache MXNet Model Server (AIM413) - A...Amazon Web Services
 

What's hot (20)

Build a Voice-Based Chatbot for Your Amazon Connect Contact Center (BAP401-R1...
Build a Voice-Based Chatbot for Your Amazon Connect Contact Center (BAP401-R1...Build a Voice-Based Chatbot for Your Amazon Connect Contact Center (BAP401-R1...
Build a Voice-Based Chatbot for Your Amazon Connect Contact Center (BAP401-R1...
 
Ask an Amazon Redshift Customer Anything (ANT389) - AWS re:Invent 2018
Ask an Amazon Redshift Customer Anything (ANT389) - AWS re:Invent 2018Ask an Amazon Redshift Customer Anything (ANT389) - AWS re:Invent 2018
Ask an Amazon Redshift Customer Anything (ANT389) - AWS re:Invent 2018
 
Serverless Architectural Patterns and Best Practices (ARC305-R2) - AWS re:Inv...
Serverless Architectural Patterns and Best Practices (ARC305-R2) - AWS re:Inv...Serverless Architectural Patterns and Best Practices (ARC305-R2) - AWS re:Inv...
Serverless Architectural Patterns and Best Practices (ARC305-R2) - AWS re:Inv...
 
Alexa for Device Makers: Create Products with Alexa Built-In Using AVS (ALX30...
Alexa for Device Makers: Create Products with Alexa Built-In Using AVS (ALX30...Alexa for Device Makers: Create Products with Alexa Built-In Using AVS (ALX30...
Alexa for Device Makers: Create Products with Alexa Built-In Using AVS (ALX30...
 
Build Your Own Royal Wedding Celebrity Viewing Experience (CTD401) - AWS re:I...
Build Your Own Royal Wedding Celebrity Viewing Experience (CTD401) - AWS re:I...Build Your Own Royal Wedding Celebrity Viewing Experience (CTD401) - AWS re:I...
Build Your Own Royal Wedding Celebrity Viewing Experience (CTD401) - AWS re:I...
 
Accelerate ML Training on Amazon SageMaker Using GPU-Based EC2 P3 Instances (...
Accelerate ML Training on Amazon SageMaker Using GPU-Based EC2 P3 Instances (...Accelerate ML Training on Amazon SageMaker Using GPU-Based EC2 P3 Instances (...
Accelerate ML Training on Amazon SageMaker Using GPU-Based EC2 P3 Instances (...
 
Lower Costs on Amazon EMR: Auto Scaling, Spot Pricing, & Expert Strategies (A...
Lower Costs on Amazon EMR: Auto Scaling, Spot Pricing, & Expert Strategies (A...Lower Costs on Amazon EMR: Auto Scaling, Spot Pricing, & Expert Strategies (A...
Lower Costs on Amazon EMR: Auto Scaling, Spot Pricing, & Expert Strategies (A...
 
Exploiting IoT & Machine Learning to transform Power and Utilities
Exploiting IoT & Machine Learning to transform Power and UtilitiesExploiting IoT & Machine Learning to transform Power and Utilities
Exploiting IoT & Machine Learning to transform Power and Utilities
 
Dissecting Media Asset Management Architecture and Media Archive TCO (MAE301)...
Dissecting Media Asset Management Architecture and Media Archive TCO (MAE301)...Dissecting Media Asset Management Architecture and Media Archive TCO (MAE301)...
Dissecting Media Asset Management Architecture and Media Archive TCO (MAE301)...
 
What's New with Amazon Redshift ft. McDonald's (ANT350-R1) - AWS re:Invent 2018
What's New with Amazon Redshift ft. McDonald's (ANT350-R1) - AWS re:Invent 2018What's New with Amazon Redshift ft. McDonald's (ANT350-R1) - AWS re:Invent 2018
What's New with Amazon Redshift ft. McDonald's (ANT350-R1) - AWS re:Invent 2018
 
Accelerate Digital Transformation for Telecom Operators with Cloud-Native Amd...
Accelerate Digital Transformation for Telecom Operators with Cloud-Native Amd...Accelerate Digital Transformation for Telecom Operators with Cloud-Native Amd...
Accelerate Digital Transformation for Telecom Operators with Cloud-Native Amd...
 
Computing at the Edge with AWS Greengrass and Amazon FreeRTOS, ft. General El...
Computing at the Edge with AWS Greengrass and Amazon FreeRTOS, ft. General El...Computing at the Edge with AWS Greengrass and Amazon FreeRTOS, ft. General El...
Computing at the Edge with AWS Greengrass and Amazon FreeRTOS, ft. General El...
 
Breaking Up the Monolith While Migrating to AWS (GPSTEC320) - AWS re:Invent 2018
Breaking Up the Monolith While Migrating to AWS (GPSTEC320) - AWS re:Invent 2018Breaking Up the Monolith While Migrating to AWS (GPSTEC320) - AWS re:Invent 2018
Breaking Up the Monolith While Migrating to AWS (GPSTEC320) - AWS re:Invent 2018
 
Have Your Front End and Monitor It, Too (ANT303) - AWS re:Invent 2018
Have Your Front End and Monitor It, Too (ANT303) - AWS re:Invent 2018Have Your Front End and Monitor It, Too (ANT303) - AWS re:Invent 2018
Have Your Front End and Monitor It, Too (ANT303) - AWS re:Invent 2018
 
ALB User Authentication: Identity Management at Scale with Netflix (NET204) -...
ALB User Authentication: Identity Management at Scale with Netflix (NET204) -...ALB User Authentication: Identity Management at Scale with Netflix (NET204) -...
ALB User Authentication: Identity Management at Scale with Netflix (NET204) -...
 
Inventory, Track, and Respond to AWS Asset Changes within Seconds at Scale (S...
Inventory, Track, and Respond to AWS Asset Changes within Seconds at Scale (S...Inventory, Track, and Respond to AWS Asset Changes within Seconds at Scale (S...
Inventory, Track, and Respond to AWS Asset Changes within Seconds at Scale (S...
 
How Rovio Uses ML to Acquire, Retain, and Monetize Users (GAM304) - AWS re:In...
How Rovio Uses ML to Acquire, Retain, and Monetize Users (GAM304) - AWS re:In...How Rovio Uses ML to Acquire, Retain, and Monetize Users (GAM304) - AWS re:In...
How Rovio Uses ML to Acquire, Retain, and Monetize Users (GAM304) - AWS re:In...
 
M&E Leadership Session: The State of the Industry, What's New from AWS for M&...
M&E Leadership Session: The State of the Industry, What's New from AWS for M&...M&E Leadership Session: The State of the Industry, What's New from AWS for M&...
M&E Leadership Session: The State of the Industry, What's New from AWS for M&...
 
Set Up a Communications Platform on AWS with AI-Enhanced Services (TLC302) - ...
Set Up a Communications Platform on AWS with AI-Enhanced Services (TLC302) - ...Set Up a Communications Platform on AWS with AI-Enhanced Services (TLC302) - ...
Set Up a Communications Platform on AWS with AI-Enhanced Services (TLC302) - ...
 
Deploying Your ONNX Deep Learning with Apache MXNet Model Server (AIM413) - A...
Deploying Your ONNX Deep Learning with Apache MXNet Model Server (AIM413) - A...Deploying Your ONNX Deep Learning with Apache MXNet Model Server (AIM413) - A...
Deploying Your ONNX Deep Learning with Apache MXNet Model Server (AIM413) - A...
 

Similar to To check the details of your rental car reservation, please say: "I want to check my rental car reservation details".i want to check my rental car reservation details

AI Powered Conversational Interfaces
AI Powered Conversational InterfacesAI Powered Conversational Interfaces
AI Powered Conversational InterfacesAmazon Web Services
 
ai mlLeverage Data and AI/ML to Drive New Experiences and Make Better Decisions
ai mlLeverage Data and AI/ML to Drive New Experiences and Make Better Decisionsai mlLeverage Data and AI/ML to Drive New Experiences and Make Better Decisions
ai mlLeverage Data and AI/ML to Drive New Experiences and Make Better DecisionsAmazon Web Services
 
AWS Webinar - Learn how and why to build conversational chatbots
AWS Webinar - Learn how and why to build conversational chatbots AWS Webinar - Learn how and why to build conversational chatbots
AWS Webinar - Learn how and why to build conversational chatbots Amazon Web Services
 
AWS Webinar Series | Using Virtual Reality to bring your ChatBot to life
AWS Webinar Series | Using Virtual Reality to bring your ChatBot to life AWS Webinar Series | Using Virtual Reality to bring your ChatBot to life
AWS Webinar Series | Using Virtual Reality to bring your ChatBot to life Amazon Web Services
 
Optimizing Healthcare Call Centers with Natural Language Understanding (HLC30...
Optimizing Healthcare Call Centers with Natural Language Understanding (HLC30...Optimizing Healthcare Call Centers with Natural Language Understanding (HLC30...
Optimizing Healthcare Call Centers with Natural Language Understanding (HLC30...Amazon Web Services
 
Intro To AI & ML at Amazon: Collision 2018
Intro To AI & ML at Amazon: Collision 2018Intro To AI & ML at Amazon: Collision 2018
Intro To AI & ML at Amazon: Collision 2018Amazon Web Services
 
Enhance customer experience with Conversational Interfaces
Enhance customer experience with Conversational InterfacesEnhance customer experience with Conversational Interfaces
Enhance customer experience with Conversational InterfacesAmazon Web Services
 
Building the Organization of the Future: Leveraging AI & ML
Building the Organization of the Future: Leveraging AI & ML Building the Organization of the Future: Leveraging AI & ML
Building the Organization of the Future: Leveraging AI & ML Amazon Web Services
 
Best Practices for Safe Deployments on AWS Lambda and Amazon API Gateway (SRV...
Best Practices for Safe Deployments on AWS Lambda and Amazon API Gateway (SRV...Best Practices for Safe Deployments on AWS Lambda and Amazon API Gateway (SRV...
Best Practices for Safe Deployments on AWS Lambda and Amazon API Gateway (SRV...Amazon Web Services
 
DataXDay - Machine learning models at scale with Amazon SageMaker
DataXDay - Machine learning models at scale with Amazon SageMaker DataXDay - Machine learning models at scale with Amazon SageMaker
DataXDay - Machine learning models at scale with Amazon SageMaker DataXDay Conference by Xebia
 
AWS AI state of the union - AWS Cape Town Summit 2018
AWS AI state of the union - AWS Cape Town Summit 2018AWS AI state of the union - AWS Cape Town Summit 2018
AWS AI state of the union - AWS Cape Town Summit 2018Amazon Web Services
 
Moving Large Scale Contact Centers to Amazon Connect (BAP324) - AWS re:Invent...
Moving Large Scale Contact Centers to Amazon Connect (BAP324) - AWS re:Invent...Moving Large Scale Contact Centers to Amazon Connect (BAP324) - AWS re:Invent...
Moving Large Scale Contact Centers to Amazon Connect (BAP324) - AWS re:Invent...Amazon Web Services
 
Building a Customer-Centric Contact Center in a Regulated Environment
Building a Customer-Centric Contact Center in a Regulated EnvironmentBuilding a Customer-Centric Contact Center in a Regulated Environment
Building a Customer-Centric Contact Center in a Regulated EnvironmentAmazon Web Services
 
Life of a Code Change to a Tier 1 Service - AWS Online Tech Talks
Life of a Code Change to a Tier 1 Service - AWS Online Tech TalksLife of a Code Change to a Tier 1 Service - AWS Online Tech Talks
Life of a Code Change to a Tier 1 Service - AWS Online Tech TalksAmazon Web Services
 
Predicting the Future with Amazon SageMaker - AWS Summit Sydney 2018
Predicting the Future with Amazon SageMaker - AWS Summit Sydney 2018Predicting the Future with Amazon SageMaker - AWS Summit Sydney 2018
Predicting the Future with Amazon SageMaker - AWS Summit Sydney 2018Amazon Web Services
 
AI & ML at Amazon: AWS Developer Workshop - Web Summit 2018
AI & ML at Amazon: AWS Developer Workshop - Web Summit 2018AI & ML at Amazon: AWS Developer Workshop - Web Summit 2018
AI & ML at Amazon: AWS Developer Workshop - Web Summit 2018Amazon Web Services
 
SRV317 Creating and Publishing AR and VR Apps with Amazon Sumerian
SRV317 Creating and Publishing AR and VR Apps with Amazon SumerianSRV317 Creating and Publishing AR and VR Apps with Amazon Sumerian
SRV317 Creating and Publishing AR and VR Apps with Amazon SumerianAmazon Web Services
 
Mike Gillespie - Build Intelligent Applications with AWS ML Services (200).pdf
Mike Gillespie - Build Intelligent Applications with AWS ML Services (200).pdfMike Gillespie - Build Intelligent Applications with AWS ML Services (200).pdf
Mike Gillespie - Build Intelligent Applications with AWS ML Services (200).pdfAmazon Web Services
 

Similar to To check the details of your rental car reservation, please say: "I want to check my rental car reservation details".i want to check my rental car reservation details (20)

AI Powered Conversational Interfaces
AI Powered Conversational InterfacesAI Powered Conversational Interfaces
AI Powered Conversational Interfaces
 
Lex and connect
Lex and connectLex and connect
Lex and connect
 
ai mlLeverage Data and AI/ML to Drive New Experiences and Make Better Decisions
ai mlLeverage Data and AI/ML to Drive New Experiences and Make Better Decisionsai mlLeverage Data and AI/ML to Drive New Experiences and Make Better Decisions
ai mlLeverage Data and AI/ML to Drive New Experiences and Make Better Decisions
 
AWS Webinar - Learn how and why to build conversational chatbots
AWS Webinar - Learn how and why to build conversational chatbots AWS Webinar - Learn how and why to build conversational chatbots
AWS Webinar - Learn how and why to build conversational chatbots
 
AWS Webinar Series | Using Virtual Reality to bring your ChatBot to life
AWS Webinar Series | Using Virtual Reality to bring your ChatBot to life AWS Webinar Series | Using Virtual Reality to bring your ChatBot to life
AWS Webinar Series | Using Virtual Reality to bring your ChatBot to life
 
Optimizing Healthcare Call Centers with Natural Language Understanding (HLC30...
Optimizing Healthcare Call Centers with Natural Language Understanding (HLC30...Optimizing Healthcare Call Centers with Natural Language Understanding (HLC30...
Optimizing Healthcare Call Centers with Natural Language Understanding (HLC30...
 
Intro To AI & ML at Amazon: Collision 2018
Intro To AI & ML at Amazon: Collision 2018Intro To AI & ML at Amazon: Collision 2018
Intro To AI & ML at Amazon: Collision 2018
 
Enhance customer experience with Conversational Interfaces
Enhance customer experience with Conversational InterfacesEnhance customer experience with Conversational Interfaces
Enhance customer experience with Conversational Interfaces
 
Building the Organization of the Future: Leveraging AI & ML
Building the Organization of the Future: Leveraging AI & ML Building the Organization of the Future: Leveraging AI & ML
Building the Organization of the Future: Leveraging AI & ML
 
Best Practices for Safe Deployments on AWS Lambda and Amazon API Gateway (SRV...
Best Practices for Safe Deployments on AWS Lambda and Amazon API Gateway (SRV...Best Practices for Safe Deployments on AWS Lambda and Amazon API Gateway (SRV...
Best Practices for Safe Deployments on AWS Lambda and Amazon API Gateway (SRV...
 
DataXDay - Machine learning models at scale with Amazon SageMaker
DataXDay - Machine learning models at scale with Amazon SageMaker DataXDay - Machine learning models at scale with Amazon SageMaker
DataXDay - Machine learning models at scale with Amazon SageMaker
 
AWS AI state of the union - AWS Cape Town Summit 2018
AWS AI state of the union - AWS Cape Town Summit 2018AWS AI state of the union - AWS Cape Town Summit 2018
AWS AI state of the union - AWS Cape Town Summit 2018
 
Moving Large Scale Contact Centers to Amazon Connect (BAP324) - AWS re:Invent...
Moving Large Scale Contact Centers to Amazon Connect (BAP324) - AWS re:Invent...Moving Large Scale Contact Centers to Amazon Connect (BAP324) - AWS re:Invent...
Moving Large Scale Contact Centers to Amazon Connect (BAP324) - AWS re:Invent...
 
Building a Customer-Centric Contact Center in a Regulated Environment
Building a Customer-Centric Contact Center in a Regulated EnvironmentBuilding a Customer-Centric Contact Center in a Regulated Environment
Building a Customer-Centric Contact Center in a Regulated Environment
 
Cheat your Way into the Cloud
Cheat your Way into the CloudCheat your Way into the Cloud
Cheat your Way into the Cloud
 
Life of a Code Change to a Tier 1 Service - AWS Online Tech Talks
Life of a Code Change to a Tier 1 Service - AWS Online Tech TalksLife of a Code Change to a Tier 1 Service - AWS Online Tech Talks
Life of a Code Change to a Tier 1 Service - AWS Online Tech Talks
 
Predicting the Future with Amazon SageMaker - AWS Summit Sydney 2018
Predicting the Future with Amazon SageMaker - AWS Summit Sydney 2018Predicting the Future with Amazon SageMaker - AWS Summit Sydney 2018
Predicting the Future with Amazon SageMaker - AWS Summit Sydney 2018
 
AI & ML at Amazon: AWS Developer Workshop - Web Summit 2018
AI & ML at Amazon: AWS Developer Workshop - Web Summit 2018AI & ML at Amazon: AWS Developer Workshop - Web Summit 2018
AI & ML at Amazon: AWS Developer Workshop - Web Summit 2018
 
SRV317 Creating and Publishing AR and VR Apps with Amazon Sumerian
SRV317 Creating and Publishing AR and VR Apps with Amazon SumerianSRV317 Creating and Publishing AR and VR Apps with Amazon Sumerian
SRV317 Creating and Publishing AR and VR Apps with Amazon Sumerian
 
Mike Gillespie - Build Intelligent Applications with AWS ML Services (200).pdf
Mike Gillespie - Build Intelligent Applications with AWS ML Services (200).pdfMike Gillespie - Build Intelligent Applications with AWS ML Services (200).pdf
Mike Gillespie - Build Intelligent Applications with AWS ML Services (200).pdf
 

More from Amazon Web Services

Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...Amazon Web Services
 
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...Amazon Web Services
 
Esegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS FargateEsegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS FargateAmazon Web Services
 
Costruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWSCostruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWSAmazon Web Services
 
Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot Amazon Web Services
 
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...Amazon Web Services
 
OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...Amazon Web Services
 
Microsoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows WorkloadsMicrosoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows WorkloadsAmazon Web Services
 
Database Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatareDatabase Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatareAmazon Web Services
 
Crea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJSCrea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJSAmazon Web Services
 
API moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e webAPI moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e webAmazon Web Services
 
Database Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatareDatabase Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatareAmazon Web Services
 
Tools for building your MVP on AWS
Tools for building your MVP on AWSTools for building your MVP on AWS
Tools for building your MVP on AWSAmazon Web Services
 
How to Build a Winning Pitch Deck
How to Build a Winning Pitch DeckHow to Build a Winning Pitch Deck
How to Build a Winning Pitch DeckAmazon Web Services
 
Building a web application without servers
Building a web application without serversBuilding a web application without servers
Building a web application without serversAmazon Web Services
 
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...Amazon Web Services
 
Introduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container ServiceIntroduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container ServiceAmazon Web Services
 

More from Amazon Web Services (20)

Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
 
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
 
Esegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS FargateEsegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS Fargate
 
Costruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWSCostruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWS
 
Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot
 
Open banking as a service
Open banking as a serviceOpen banking as a service
Open banking as a service
 
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
 
OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...
 
Microsoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows WorkloadsMicrosoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows Workloads
 
Computer Vision con AWS
Computer Vision con AWSComputer Vision con AWS
Computer Vision con AWS
 
Database Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatareDatabase Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatare
 
Crea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJSCrea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJS
 
API moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e webAPI moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e web
 
Database Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatareDatabase Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatare
 
Tools for building your MVP on AWS
Tools for building your MVP on AWSTools for building your MVP on AWS
Tools for building your MVP on AWS
 
How to Build a Winning Pitch Deck
How to Build a Winning Pitch DeckHow to Build a Winning Pitch Deck
How to Build a Winning Pitch Deck
 
Building a web application without servers
Building a web application without serversBuilding a web application without servers
Building a web application without servers
 
Fundraising Essentials
Fundraising EssentialsFundraising Essentials
Fundraising Essentials
 
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
 
Introduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container ServiceIntroduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container Service
 

To check the details of your rental car reservation, please say: "I want to check my rental car reservation details".i want to check my rental car reservation details

  • 1.
  • 2. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Bring the Power of AI to Your Amazon Connect Contact Center Dan Perry Senior Product Owner Liberty Mutual Insurance B A P 3 2 2 Laura McFarland Technologist Liberty Mutual Insurance Marc Rudkowski Principal Consultant AWS Professional Services
  • 3. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Agenda • Business case • Demo • Architecture • Best practices
  • 4. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 5. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Improving contact centers with artificial intelligence A m a z o n L e x A m a z o n T r a n s c r i b e A m a z o n C o m p r e h e n d T R A N S C R I P T A m a z o n C o n n e c t Analytics
  • 6. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Improving contact centers with artificial intelligence A m a z o n L e x A m a z o n T r a n s c r i b e A m a z o n C o m p r e h e n d T R A N S C R I P T A m a z o n C o n n e c t Analytics
  • 7. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 8. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 9. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Making the business case Meets an emerging technology • Within our US operation, we receive millions of calls annually across claims & service call centers • Some of which are repetitive & direct • Offering up an opportunity for automation • Our customers expect 24/7 access • No hold time • Quick resolution of their inquiry When a customer’s needs External Internal The big bang … Voice revolution Chatbot evolution
  • 10. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. = Intents Building a chatbot roadmap Conversational complexity Frequency Building a data-driven framework … from a wide breadth of resources
  • 11. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Designing an MVP Can we build a conversational chatbot that: 1. Interacts with our customers 2. Can answer a subset of claims rental car-related inquiries 3. Touches upon all KPIs needed to address scalability Business viability Does the platform integrate with our systems ... is it stable, scalable, secure? Technical feasibility Customer desirability Is the forecasted ROI economically sound? Do customers want to engage with the chatbot & can it embody our company, our values?
  • 12. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 13. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 14. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. AWS services
  • 15. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. A new way of developing the design GUI CSS Home screen Screen flow Screen components VUI Persona Introduction sentence Script Flow Conversation script
  • 16. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. VUI designing Professional call center persona “Hi there, I can help you with your rental car today …” Amazon Lex only able to misunderstand twice Intents to handle “Can you repeat that” After Intent is fulfilled, “What else can I help you with today” VUI Persona Introduction sentence Script flow Conversation script
  • 17. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. VUI designing Text to speech (TTS) prompts include punctuation marks to add emphasis or pauses. Use SSML (Speech Synthesis Markup Language) for additional controls over speech generation. Amazon Polly console great for learning SSML. <break time="1s"/> 1 second pause Initial scripts—reviewed with UX psychologist. Held user experience testing session. VUI Persona Introduction sentence Script flow Conversation script
  • 18. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. VUI designing—Script and flows
  • 19. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. A new way of developing the design Partnered with AWS Professional Services to get access to: Amazon Connect & Amazon Lex expert VUI designer from VoiceFoundry UX psychologist PhD in cognitive and neural sciences Partnered with AWS in a consultancy Their responsiveness and fast feedback kept our MVP project on a fast pace
  • 20. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Learning and evolving architecture We had an emerging serverless architecture AWS Cloud
  • 21. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Evolving architecture—Top tips AWS Cloud Get out of the console early & start developing AWS CloudFormation templates Reporting, alerting, …
  • 22. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Evolving architecture—Top tips AWS Cloud https://aws.amazon.com/about-aws/whats- new/2018/
  • 23. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Evolving architecture Amazon S3 Alarm CALL CENTER software JSON JSON JSON AWS Cloud Solid architect pattern established ProxyGateway Logs, Alarms & Reports Rental Bot FeedbackBot Lambda Data Gathers
  • 24. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Call flow and data flow in action Amazon S3 Alarm CALL CENTER software JSON JSON JSON AWS Cloud ProxyGateway 2. New call event sent 4. Data pulled & front loaded into DynamoDB 6. Amazon Lex accesses caller data to have intelligence about caller … JSON … … … JSON Logs, Alarms & Reports Rental Bot FeedbackBot Lambda Data Gathers
  • 25. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Lex under the hood Has my rental been authorized? According to your claim file, your rental is scheduled to begin on 30 March and is approved for 10 days Are there other rental car questions I can help you with today? Rental authorized intent Caller’s utterance matches an intent Fulfillment lambda populates the static text with caller data & passes it to Amazon Lex via a PostText Follow-up prompt to continue or end call I see we have a rental car already set up for you. Do you want to hear the details? Amazon Lex calls the fulfillment lambda with caller’s session data in the request Lambda uses the session data to get the front-loaded caller data from DynamoDBYes
  • 26. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Lex intents
  • 27. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Lex intents, sample utterances, and slot usage
  • 28. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Lex intent and sample utterances testing Automated utterances tested using Amazon Lex runtime API PostText https://docs.aws.amazon.com/lex/ latest/dg/API_runtime_PostText.html Can send text or SSML
  • 29. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Lex intent and sample utterances testing Request POST /bot/botName/alias/botAlias/user/userId/text HTTP/1.1 Content-type: application/json { "inputText": "the utterance text to send", "requestAttributes": { "string" : "string" }, "sessionAttributes": { "string" : "string" } } Response { "dialogState": "Fulfilled", "intentName": "IntentNameUsed", "message": ”Response message from intent", ... }
  • 30. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Lex intent and sample utterances testing For rental authorization intent { "Authorized" }, { "Authorization" }, { "Authorized rental" }, { "Rental authorized" }, { "Rental authorization" }, { "Has my rental been authorized" }, { "Is my rental authorized" }, { "I need to know if my rental car is authorized" }, { "I want to know if my rental has been authorized" }, { "Trying to get my reservation with approved" }, { "Send an authorization out" }, { "You guys haven't approved the rental yet" }, ... assertEquals(response.intentName, "Authorized_Rental”)
  • 31. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Lex intent and sample utterances testing Automated CI/CD pipeline Code check in followed by pull request Static analysis runs—Sonar, Lint, CheckStyle Built & deployed to AWS dev account Bamboo job kicks off Java app tests with each bot’s intents test utterance text AWS SDK included to call Amazon Lex runtime API Results pulled into Allure
  • 32. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Utterance refinement procedure Used 3,000+ example rental queries from our call center transcripts to create our utterance test cases Each utterance test case has a single Amazon Lex intent it must match to Advice was to aim for 75% match for MVP First run of the tests was not good news
  • 33. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Utterance refinement procedure But we just gamified utterance testing!
  • 34. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Utterance refinement procedure one intent at a time
  • 35. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Utterance refinement procedure Before refinement "sampleUtterances": [ "Has {Rental} been {Authorized}", "Has my {Rental} been {Authorized}", "Is my {Rental} {Authorized} ] After refinement "sampleUtterances": [ "{Authorized} {Rental}", "Has {Rental} been {Authorized}", "Has my {Rental} been {Authorized}", "Is my {Rental} {Authorized}", "Send an {Authorized}", "If {Rental} has been {Authorized}” ] Enums "Rental": [ {"value": "rental vehicle"}, {"value": "rental car"}, {"value": "car rental"}, {"value": "vehicle rental"}, {"value": "rented car"}, {"value": "rented vehicle"} ] "Authorized”: [ {"value": "authorized"}, {"value": "allowed"}, {"value": "approved"}, {"value": "authorize"}, {"value": "approval"}, {"value": "approve"}, {"value": "authorization"} ]
  • 36. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Caller interactions with Amazon Lex what i wanna know is when i rent a car say for her does my insurance cover it do i qualify for a rental car with my claim rental set up rental car schedule rental car extension rental details how much money do I have to rent a car no but thank you very much for the information that’s all thank you very much can you repeat that for me That’s good thank you yes ma’am
  • 37. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. MVP project timeline Team—seven + AWS Professional Services Continue evolving fast & create new intent areas
  • 38. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Rental chatbot results 10-15%Call deflection Utterance recognition Customer <5%Callbacks >90% Call volume experience 7/10 - “A good experience.” - “You’re very good help.” - “Pleased with my service.” Wk1 Wk2 Wk3 Wk4 Wk5 Wk6
  • 39. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Polyglot programming Pair programming Mob code reviewing The squad Serverless architecture Event-driven design Cloud native CI/CD pipelines TDD Fully automated testing
  • 40. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Building your next customer self-service voice experience—Best practices Building the customer experience • Pick a use case that allows you to vet some of your key business requirements, but be pragmatic about complexity • Customer experience is as important as the technology: • Delight customers • Leverage your data and anticipate why they’re calling • Iterate and validate with real end-user/customers • Leverage automated testing to improve effectiveness and containment of your experience
  • 41. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Building your next customer self-service voice experience—Best practices Learn from existing approaches: • Build a Q&A bot • Understand how to leverage Lambda with Amazon Lex • Build an automated AI experience with Amazon Connect and Salesforce • Build your own text-to-speech applications with Amazon Polly • Explore and build experiences with Alexa and Alexa for Business
  • 42. Thank you! © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 43. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 44. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. AWS console— Amazon Lex https://aws.amazon.com/blogs/machi ne-learning/building-better-bots/ Niranjan Hira and Harshal Pimpalkhute
  • 45. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. The console—Amazon Connect https://aws.amazon.com/blogs/aws/n ew-amazon-connect-and-amazon-lex- integration/ Randall Hunt