Alexa, the voice service that powers Amazon Echo and Amazon Fire TV, provides a set of built-in abilities, or skills, that enable customers to interact with devices in a more intuitive way using voice. Application developers are also able to create custom applications and skills that can be published in the Alexa App Store for consumers to use. Some examples of these today include Uber, Spotify and Domino’s Pizza.This session will advise on why voice is a relevant additional user engagement model for businesses, what a good VUI (Voice User Interface) sounds like, and also demonstrate how simple it is to build custom Alexa applications by utilising the hosted Alexa Voice service and the AWS cloud.
4. We also recently launched
Fire TV with Alexa integrated
directly into the device.
Simplifying everyday actions
with voice on new and familiar
devices.
& FIRE TVMEET ECHO
The First
Alexa
Endpoints
The Echo is the first and best-known
endpoint of the Alexa Ecosystem…
The Echo was built to make life
easier and more enjoyable.
5. We’ve received over 36,000
customer reviews in the first
12 months alone. Ratings
clock in at 4.5 stars. And
there has been no shortage
of love…
“Amazon’s Echo might
be the most important
product in years”
“I admit, I may have said
‘I love you’ to Alexa on
more than one occasion”
“The real genius of the
Amazon Echo isn't simply
what it can do now, but what it
might lead to…”
Accolades
roll in…
A Perfect 10
WHAT ARE PEOPLE SAYING?
6. Create Great Content:
ASK is how you connect
to your consumer
THE ALEXA ECOSYSTEM
Supported by two powerful frameworks
ALEXA
VOICE
SERVICE
Unparalleled Distribution:
AVS allows your content
to be everywhere
Lives In The Cloud
Automated Speech
Recognition (ASR)
Natural Language
Understanding (NLU)
Always Learning
ALEXA
SKILLS
KIT
7. Register a device
View and manage actions
Link third-party accounts
View lists
Enable skills
And much more
THE ALEXA COMPANION APP
9. CONVERSATION IS THE MOST NATURAL WAY TO ENGAGE
WITH YOUR PRODUCTS
VOICE RELEASES THE FRICTION OF TRADITIONAL
TECHNOLOGY INTERACTION
USERS CAN NOW INTERACT WITH YOUR PRODUCT IN A MORE
INTIMATE WAY
12. UNDER THE HOOD OF ASK
A closer look at how the Alexa Skills Kit process
a request and returns an appropriate response
You Pass Back a Textual or
Audio Response
You Pass Back a
Graphical Response
Alexa Identifies Skill & Recognizes
Intent Through ASR & NLU
Alexa Sends
Customer Intent
To Your Service
Your Service
Processes
Request
User Makes a
Request
Audio Stream Is
Sent Up To Alexa
Respond to Intent
Through Text & VisualAlexa Converts Text-to-Speech
Renders Graphical Component
22. HOSTING YOUR SKILLS
Skills live in the cloud, and are hosted in one of two places:
AWS Lambda
or
An internet accessible HTTPS endpoint with a trusted
certificate
23. INTENTS AND SLOTS
You define interactions for your voice app through
intent schemas
Each intent consists of two fields. The intent field gives
the name of the intent. The slots field lists the slots
associated with that intent.
Slots can also included types such as LITERAL,
NUMBER, DATE, etc.
intent schemas are uploaded to your skill in the
Amazon Developer Portal
{
"intents": [
{
"intent": "tflinfo",
"slots": [
{
"name": "LINENAME",
"type": "LINENAMES"
}
]
}
]
}
24. CUSTOM SLOTS
Custom Slots increase the accuracy of Alexa when
identifying an argument within an intent.
They are created as a line separated list of values
It is recommended to have as many possible slots as
possible.
There are some built in slots for things such as
US.State and US.FirstName
bakerloo
central
circle
district
hammersmith and city
jubilee
metropolitan
northern
piccadilly
victoria
waterloo and city
london overground
tfl rail
DLR
25. SAMPLE UTTERANCES
The mappings between intents and the typical utterances
that invoke those intents are provided in a tab-separated text
document of sample utterances.
Each possible phrase is assigned to one of the defined
intents.
tflinfo are there any disruptions on the {LINENAME} line
tflinfo {LINENAME} line
“What is…”
“Are there…”
“Tell me…”
“Give me…”
“Give…”
“Find…”
“Find me…”
26. REQUEST TYPES
LaunchRequest
Maps to onLaunch() and occurs when the users launch the app without
specifying what they want
IntentRequest
Maps to onIntent() and occurs when the user specifies an intent
SessionEndedRequest
Maps to OnSessionEnded() and occurs when the user ends the session
27. AN EXAMPLE REQUEST
If hosting your own service, you will need to handle
POST requests to your service over port 443 and
parse the JSON
With AWS Lambda, the event object that is passed
when invoking your function is equal to the request
JSON
Requests always include a type, requestId, and
timestamp
If an IntentRequest they will include the intent and its
slots
type maps directly to LaunchRequest,
IntentRequest, and SessionEndedRequest
"request": {
"type": "IntentRequest",
"requestId": "string",
"timestamp":"2016-05-13T13:19:25Z",
"intent": {
"name": "tflinfo",
"slots": {
"LINENAME": {
"name": "LINENAME",
"value": "circle"
}
}
},
"locale": "en-US"
}
28. AN EXAMPLE RESPONSE
Your app will need to build a response object that
includes the relevant keys and values.
The Amazon Developer Portal has plenty of examples
to get started.
There are some third party helper products for node.js
such as alexa-app who have simplified this even more.
outputSpeech, card and reprompt are the supported
response objects.
shouldEndSession is a boolean value that determines
wether the conversation is complete or not
You can also store session data in the Alexa Voice
Service. These are in the sessionAttributes object.
{
"version": "1.0",
"response": {
"outputSpeech": {
"type": "SSML",
"ssml": "<speak>There are
currently no delays on the
circle line.</speak>"
},
"shouldEndSession": true
},
"sessionAttributes": {}
}
31. WHERE DO WE START?
The Evolution of a Skill
Traffic Skill Example
Give an estimated time of
arrival from home to work
Traffic Skill Example
Include crashes, construction
and closures on route
Traffic Skill Example
Hand-off from Echo to in mobile
turn-by-turn directions with local
search and recommendations.
RUN
Evolve Over Time
CRAWL
What’s Your Core functionality?
ANALYZE USER FEEDBACK
& OPTIMIZE SKILL
WALK
Expand Capabilities & Features
INNOVATE FOR CUSTOMERS
32. VUI PRINCIPLES
CRAWL, WALK, RUN
Don’t overwhelm your users with features out of the box. This is a new
medium of interaction with your product. Keep it simple and grow from
there.
NATURAL AS POSSIBLE
Try to make your utterances as natural as they possibly can.
SUPPORT MULTIPLE UTTERANCES
Create as many utterances as possible to upload to the portal. There is an
awesome open source project called alexa-utterances that is great at
helping you to do this.
UTILISE THE BUILT IN HELP INTENT
There is an intent called the helpIntent that is invoked for common requests
for help such as “help me” you can handle this in your skill and respond with
useful speech.
33. SOME DO’s & DONT’s of VUI
DONT
I can give you disruption information for the London
Underground
DO
I can give you disruption information for the London
Underground. Tell me the line you would like to check.
34. SOME DO’s & DONT’s of VUI
DONT
I can give you disruption information for the London
Underground
DO
I can give you disruption information for the London
Underground. Tell me the line you would like to check.
DONT
Welcome to TFL
DO
Welcome to the TFL skill. You can get disruption
information by saying a London Underground line
name
35. SOME DO’s & DONT’s of VUI
DONT
I can give you disruption information for the London
Underground
DO
I can give you disruption information for the London
Underground. Tell me the line you would like to check.
DONT
Welcome to TFL
DO
Welcome to the TFL skill. You can get disruption
information by saying a London Underground line
name
DONT
I can give disruption info for all of the London
Underground lines. Which one would you like….
DO
Which line would you like disruption information for?
36. SOME DO’s & DONT’s of VUI
DONT
I can give you disruption information for the London
Underground
DO
I can give you disruption information for the London
Underground. Tell me the line you would like to check.
DONT
Welcome to TFL
DO
Welcome to the TFL skill. You can get disruption
information by saying a London Underground line
name
DONT
I can give disruption info for all of the London
Underground lines. Which one would you like….
DO
Which line would you like disruption information for?
DONT
You would like disruption information for the circle line
right?
DO
There are currently no delays on the circle line
37. THE PLAN
High-Level Framework to
help get you started
We’ve put together a plan to take your
projects from inception to launch
through a honed process that includes
multiple touch-points with the Alexa
team.
1
VOICE EXPERIENCE DESIGN
Establish Strategic & Creative Direction
What’s Your MVP?
Develop User Flows & Scripts
Prepare Utterances & Responses
DEVELOPMENT
Bring the Skill to Life
Initial Skill Submission
Deliver Skill to Amazon For Review
2
TRAINING & CERTIFICATION
Amazon & Developer Testing & Adjustments
Certification & Deployment
3
Start
End
40. The Alexa Fund is a $100M strategic fund. Designed to support the
Alexa ecosystem
14 investments to date
Hardware that benefits from Alexa’s voice interface
Experiences that Deliver new Alexa capabilities
New contributions to the voice technology