SlideShare a Scribd company logo

Rsqrd AI: Making Conversational AI Work for Everybody

In this talk, Rachael Tatman, Senior Developer Advocate at Rasa, talks about how to continuously bringing humans into the development process to improve conversational AI systems. Presented on 09/29/2020 **These slides are from a talk given at Rsqrd AI. Learn more at rsqrdai.org**

1 of 23
Download to read offline
Making Conversational AI Work for
Everybody: An Intro to Conversation
Driven Development
Dr. Rachael Tatman
Quick About Me
How I got here
About Me
● 2012- 2017: PhD in Linguistics
○ Modelling demographic disparities in Automatic
Speech Recognition
○ FAT* ML
● 2017- 2020: Developer Advocate @ Kaggle (Google)
○ "The home of data science"
○ Machine learning education
○ Live Streaming: Livecoding & Paper Reading
● 2020 - now: Developer Advocate @ Rasa
○ Open source conversational AI framework & free
software for conversation driven development
○ Developer education
○ Video, blogs, tutorials, live streaming, talks :)
Sooo.... why do I choose
to work on chatbots/
conversational AI?
Some false assumptions we tend to make
- Everyone has access to a computer
- Everyone has access to the internet
- Everyone knows how to Google stuff
- Everyone likes visual interfaces
- Everyone has a good/affordable enough
internet connection to load graphics
- Everyone knows how to use a website
- Everyone knows how to use YOUR website
- Everyone can make calls during business
hours
https://answers.microsoft.com/en-us/ie/forum/ie11-iewindows8_1/how-much-data-being-us
ed-when-visiting-a-website/5028b804-3adf-4093-b10a-a058d020b19a
Why conversational AI?
- Most people already know how to have a conversation
- NLP methods are able to handle a lot more variation in
input now
- A focused Conversational AI can help people do tasks
much faster
- Chalmers, a conversational assistant for people experiencing
homelessness, helped people find information 60 times
faster than searching (https://www.amplelabs.co/chalmers/)
Ad

Recommended

How Conversational AI is causing a paradigm shift in eCommerce Customer Service
How Conversational AI is causing a paradigm shift in eCommerce Customer Service How Conversational AI is causing a paradigm shift in eCommerce Customer Service
How Conversational AI is causing a paradigm shift in eCommerce Customer Service Shubham Bagri
 
Swapan Rajdev Keynote at Bots-up Meetup, Bangalore
Swapan Rajdev Keynote at Bots-up Meetup, BangaloreSwapan Rajdev Keynote at Bots-up Meetup, Bangalore
Swapan Rajdev Keynote at Bots-up Meetup, BangaloreShubham Bagri
 
Conversational Artificial Intelligence with Ben Tomlinson and Wayne Thompson
Conversational Artificial Intelligence with Ben Tomlinson and Wayne ThompsonConversational Artificial Intelligence with Ben Tomlinson and Wayne Thompson
Conversational Artificial Intelligence with Ben Tomlinson and Wayne ThompsonDatabricks
 
Ethnobots: Reimagining Chatbots as Ethnographic Research Tools | Rasa Summit ...
Ethnobots: Reimagining Chatbots as Ethnographic Research Tools | Rasa Summit ...Ethnobots: Reimagining Chatbots as Ethnographic Research Tools | Rasa Summit ...
Ethnobots: Reimagining Chatbots as Ethnographic Research Tools | Rasa Summit ...Rasa Technologies
 
2018-10-18 J2 4A - How to empower and support your citizen developers - Tracy...
2018-10-18 J2 4A - How to empower and support your citizen developers - Tracy...2018-10-18 J2 4A - How to empower and support your citizen developers - Tracy...
2018-10-18 J2 4A - How to empower and support your citizen developers - Tracy...Modern Workplace Conference Paris
 
test - Future of Ecommerce: How to Improve the Online Shopping Experience Usi...
test - Future of Ecommerce: How to Improve the Online Shopping Experience Usi...test - Future of Ecommerce: How to Improve the Online Shopping Experience Usi...
test - Future of Ecommerce: How to Improve the Online Shopping Experience Usi...Skyl.ai
 
Better Service Management with Artificial Intelligence
Better Service Management with Artificial IntelligenceBetter Service Management with Artificial Intelligence
Better Service Management with Artificial IntelligenceTOPdesk
 
"Center Out" Business Architecture. Creating a Responsive Omnichannel Custome...
"Center Out" Business Architecture. Creating a Responsive Omnichannel Custome..."Center Out" Business Architecture. Creating a Responsive Omnichannel Custome...
"Center Out" Business Architecture. Creating a Responsive Omnichannel Custome...ELEKS
 

More Related Content

What's hot

20220205 Getting started with power bi
20220205 Getting started with power bi20220205 Getting started with power bi
20220205 Getting started with power biAroh Shukla
 
Chapter Leader playbook
Chapter Leader playbookChapter Leader playbook
Chapter Leader playbookUiPath
 
Webinar - Know Your Customer - Arya (20160526)
Webinar - Know Your Customer - Arya (20160526)Webinar - Know Your Customer - Arya (20160526)
Webinar - Know Your Customer - Arya (20160526)Turi, Inc.
 
Webinar - Fraud Detection - Palombo (20160428)
Webinar - Fraud Detection - Palombo (20160428)Webinar - Fraud Detection - Palombo (20160428)
Webinar - Fraud Detection - Palombo (20160428)Turi, Inc.
 
20190219 Telling a story with your data and power bi
20190219 Telling a story with your data and power bi20190219 Telling a story with your data and power bi
20190219 Telling a story with your data and power biAroh Shukla
 
Data Science: Good, Bad and Ugly by Irina Kukuyeva
Data Science: Good, Bad and Ugly by Irina KukuyevaData Science: Good, Bad and Ugly by Irina Kukuyeva
Data Science: Good, Bad and Ugly by Irina KukuyevaData Con LA
 
Internship @ WNS
Internship @ WNSInternship @ WNS
Internship @ WNSAtul Sharma
 
How Does RPA Work? | What Is Robotic Process Automation? Edureka
How Does RPA Work? | What Is Robotic Process Automation? EdurekaHow Does RPA Work? | What Is Robotic Process Automation? Edureka
How Does RPA Work? | What Is Robotic Process Automation? EdurekaEdureka!
 
Customer experience and product instructions
Customer experience and product instructionsCustomer experience and product instructions
Customer experience and product instructionsSharon Burton
 
Making the most of your SharePoint – Intranet & Apps
Making the most of your SharePoint – Intranet & AppsMaking the most of your SharePoint – Intranet & Apps
Making the most of your SharePoint – Intranet & AppsAmos Wachanga
 
I Ctrl Algemeen Voor Linked In V3.0 En
I Ctrl Algemeen Voor Linked In V3.0 EnI Ctrl Algemeen Voor Linked In V3.0 En
I Ctrl Algemeen Voor Linked In V3.0 EniCtrl
 
Welcome from Intuit QuickBase Keynote
Welcome from Intuit QuickBase KeynoteWelcome from Intuit QuickBase Keynote
Welcome from Intuit QuickBase KeynoteQuickBase, Inc.
 
You've Got No UI?! (Agile Data Teams)
You've Got No UI?! (Agile Data Teams)You've Got No UI?! (Agile Data Teams)
You've Got No UI?! (Agile Data Teams)Mark Barber
 
Overview MSBizApps & MPP - Cork PBI UG
Overview MSBizApps & MPP - Cork PBI UGOverview MSBizApps & MPP - Cork PBI UG
Overview MSBizApps & MPP - Cork PBI UGClifton Lenne
 
Implementing ChatOps using Microsoft Power Platform - M365 Saturday Ahmedabad...
Implementing ChatOps using Microsoft Power Platform - M365 Saturday Ahmedabad...Implementing ChatOps using Microsoft Power Platform - M365 Saturday Ahmedabad...
Implementing ChatOps using Microsoft Power Platform - M365 Saturday Ahmedabad...Eldert Grootenboer
 

What's hot (20)

Real-Time Analytics: The Future of Big Data in the Agency
Real-Time Analytics: The Future of Big Data in the AgencyReal-Time Analytics: The Future of Big Data in the Agency
Real-Time Analytics: The Future of Big Data in the Agency
 
20220205 Getting started with power bi
20220205 Getting started with power bi20220205 Getting started with power bi
20220205 Getting started with power bi
 
Image annotation for machine learning
Image annotation for machine learningImage annotation for machine learning
Image annotation for machine learning
 
Trending business areas and skills
Trending business areas and  skillsTrending business areas and  skills
Trending business areas and skills
 
Chapter Leader playbook
Chapter Leader playbookChapter Leader playbook
Chapter Leader playbook
 
Webinar - Know Your Customer - Arya (20160526)
Webinar - Know Your Customer - Arya (20160526)Webinar - Know Your Customer - Arya (20160526)
Webinar - Know Your Customer - Arya (20160526)
 
Webinar - Fraud Detection - Palombo (20160428)
Webinar - Fraud Detection - Palombo (20160428)Webinar - Fraud Detection - Palombo (20160428)
Webinar - Fraud Detection - Palombo (20160428)
 
20190219 Telling a story with your data and power bi
20190219 Telling a story with your data and power bi20190219 Telling a story with your data and power bi
20190219 Telling a story with your data and power bi
 
Data Science: Good, Bad and Ugly by Irina Kukuyeva
Data Science: Good, Bad and Ugly by Irina KukuyevaData Science: Good, Bad and Ugly by Irina Kukuyeva
Data Science: Good, Bad and Ugly by Irina Kukuyeva
 
Face of Art Technologies Ltd Company Presentation
Face of Art Technologies Ltd Company PresentationFace of Art Technologies Ltd Company Presentation
Face of Art Technologies Ltd Company Presentation
 
Internship @ WNS
Internship @ WNSInternship @ WNS
Internship @ WNS
 
How Does RPA Work? | What Is Robotic Process Automation? Edureka
How Does RPA Work? | What Is Robotic Process Automation? EdurekaHow Does RPA Work? | What Is Robotic Process Automation? Edureka
How Does RPA Work? | What Is Robotic Process Automation? Edureka
 
Customer experience and product instructions
Customer experience and product instructionsCustomer experience and product instructions
Customer experience and product instructions
 
Making the most of your SharePoint – Intranet & Apps
Making the most of your SharePoint – Intranet & AppsMaking the most of your SharePoint – Intranet & Apps
Making the most of your SharePoint – Intranet & Apps
 
I Ctrl Algemeen Voor Linked In V3.0 En
I Ctrl Algemeen Voor Linked In V3.0 EnI Ctrl Algemeen Voor Linked In V3.0 En
I Ctrl Algemeen Voor Linked In V3.0 En
 
Welcome from Intuit QuickBase Keynote
Welcome from Intuit QuickBase KeynoteWelcome from Intuit QuickBase Keynote
Welcome from Intuit QuickBase Keynote
 
You've Got No UI?! (Agile Data Teams)
You've Got No UI?! (Agile Data Teams)You've Got No UI?! (Agile Data Teams)
You've Got No UI?! (Agile Data Teams)
 
Beyond Intranets -Enabling a Digital Workplace
Beyond Intranets -Enabling a Digital WorkplaceBeyond Intranets -Enabling a Digital Workplace
Beyond Intranets -Enabling a Digital Workplace
 
Overview MSBizApps & MPP - Cork PBI UG
Overview MSBizApps & MPP - Cork PBI UGOverview MSBizApps & MPP - Cork PBI UG
Overview MSBizApps & MPP - Cork PBI UG
 
Implementing ChatOps using Microsoft Power Platform - M365 Saturday Ahmedabad...
Implementing ChatOps using Microsoft Power Platform - M365 Saturday Ahmedabad...Implementing ChatOps using Microsoft Power Platform - M365 Saturday Ahmedabad...
Implementing ChatOps using Microsoft Power Platform - M365 Saturday Ahmedabad...
 

Similar to Rsqrd AI: Making Conversational AI Work for Everybody

Six Steps to Conversation Driven Development
Six Steps to Conversation Driven DevelopmentSix Steps to Conversation Driven Development
Six Steps to Conversation Driven DevelopmentRasa Technologies
 
Rapid Product Design in the Wild, Agile 2013
Rapid Product Design in the Wild, Agile 2013Rapid Product Design in the Wild, Agile 2013
Rapid Product Design in the Wild, Agile 2013Michele Ide-Smith
 
The ultimate guide to prototyping
The ultimate guide to prototypingThe ultimate guide to prototyping
The ultimate guide to prototypingMarcelo Graciolli
 
User Centered Design: guarantee that your business process automation project...
User Centered Design: guarantee that your business process automation project...User Centered Design: guarantee that your business process automation project...
User Centered Design: guarantee that your business process automation project...Bonitasoft
 
Webinar - Design thinking 101 - 2018-07-24
Webinar - Design thinking 101 - 2018-07-24Webinar - Design thinking 101 - 2018-07-24
Webinar - Design thinking 101 - 2018-07-24TechSoup
 
UX South Africa 2014 - Keynote
UX South Africa 2014 - KeynoteUX South Africa 2014 - Keynote
UX South Africa 2014 - KeynotePhil Barrett
 
"Open" includes users - Leverage their input
"Open" includes users - Leverage their input"Open" includes users - Leverage their input
"Open" includes users - Leverage their inputRandy Earl
 
Form Function Class 6, Manila, Philippines 14/11/2015
Form Function Class 6, Manila, Philippines 14/11/2015Form Function Class 6, Manila, Philippines 14/11/2015
Form Function Class 6, Manila, Philippines 14/11/2015Holger Bartel
 
Executive Directors Chat- Artificial Intelligence - The Good, the Bad, and th...
Executive Directors Chat- Artificial Intelligence - The Good, the Bad, and th...Executive Directors Chat- Artificial Intelligence - The Good, the Bad, and th...
Executive Directors Chat- Artificial Intelligence - The Good, the Bad, and th...TechSoup
 
UX class presentation
UX class presentationUX class presentation
UX class presentationTheo V
 
Info Session : University Institute of engineering and technology , Kurukshet...
Info Session : University Institute of engineering and technology , Kurukshet...Info Session : University Institute of engineering and technology , Kurukshet...
Info Session : University Institute of engineering and technology , Kurukshet...HRITIKKHURANA1
 
Google: Rapid Prototyping for AR
Google: Rapid Prototyping for ARGoogle: Rapid Prototyping for AR
Google: Rapid Prototyping for ARAugmentedWorldExpo
 
What's Next: Ogilvy x Google Chatbots Partnership
What's Next: Ogilvy x Google Chatbots PartnershipWhat's Next: Ogilvy x Google Chatbots Partnership
What's Next: Ogilvy x Google Chatbots PartnershipOgilvy Consulting
 
Cisco Next generation meetings
Cisco Next generation meetingsCisco Next generation meetings
Cisco Next generation meetingsErwin Koreneef
 
Rapid Product Design in the Wild
Rapid Product Design in the WildRapid Product Design in the Wild
Rapid Product Design in the WildMichele Ide-Smith
 
top developer mistakes
top developer mistakes top developer mistakes
top developer mistakes Hanokh Aloni
 
It's a startup life: from idea to execution.
It's a startup life: from idea to execution.It's a startup life: from idea to execution.
It's a startup life: from idea to execution.Miet Claes
 

Similar to Rsqrd AI: Making Conversational AI Work for Everybody (20)

Six Steps to Conversation Driven Development
Six Steps to Conversation Driven DevelopmentSix Steps to Conversation Driven Development
Six Steps to Conversation Driven Development
 
Orientation session
Orientation sessionOrientation session
Orientation session
 
Rapid Product Design in the Wild, Agile 2013
Rapid Product Design in the Wild, Agile 2013Rapid Product Design in the Wild, Agile 2013
Rapid Product Design in the Wild, Agile 2013
 
The ultimate guide to prototyping
The ultimate guide to prototypingThe ultimate guide to prototyping
The ultimate guide to prototyping
 
User Centered Design: guarantee that your business process automation project...
User Centered Design: guarantee that your business process automation project...User Centered Design: guarantee that your business process automation project...
User Centered Design: guarantee that your business process automation project...
 
Webinar - Design thinking 101 - 2018-07-24
Webinar - Design thinking 101 - 2018-07-24Webinar - Design thinking 101 - 2018-07-24
Webinar - Design thinking 101 - 2018-07-24
 
UX South Africa 2014 - Keynote
UX South Africa 2014 - KeynoteUX South Africa 2014 - Keynote
UX South Africa 2014 - Keynote
 
"Open" includes users - Leverage their input
"Open" includes users - Leverage their input"Open" includes users - Leverage their input
"Open" includes users - Leverage their input
 
Form Function Class 6, Manila, Philippines 14/11/2015
Form Function Class 6, Manila, Philippines 14/11/2015Form Function Class 6, Manila, Philippines 14/11/2015
Form Function Class 6, Manila, Philippines 14/11/2015
 
LA Uncubed presentation
LA Uncubed presentationLA Uncubed presentation
LA Uncubed presentation
 
Executive Directors Chat- Artificial Intelligence - The Good, the Bad, and th...
Executive Directors Chat- Artificial Intelligence - The Good, the Bad, and th...Executive Directors Chat- Artificial Intelligence - The Good, the Bad, and th...
Executive Directors Chat- Artificial Intelligence - The Good, the Bad, and th...
 
UX class presentation
UX class presentationUX class presentation
UX class presentation
 
Info Session : University Institute of engineering and technology , Kurukshet...
Info Session : University Institute of engineering and technology , Kurukshet...Info Session : University Institute of engineering and technology , Kurukshet...
Info Session : University Institute of engineering and technology , Kurukshet...
 
Google: Rapid Prototyping for AR
Google: Rapid Prototyping for ARGoogle: Rapid Prototyping for AR
Google: Rapid Prototyping for AR
 
What's Next: Ogilvy x Google Chatbots Partnership
What's Next: Ogilvy x Google Chatbots PartnershipWhat's Next: Ogilvy x Google Chatbots Partnership
What's Next: Ogilvy x Google Chatbots Partnership
 
Cisco Next generation meetings
Cisco Next generation meetingsCisco Next generation meetings
Cisco Next generation meetings
 
Rapid Product Design in the Wild
Rapid Product Design in the WildRapid Product Design in the Wild
Rapid Product Design in the Wild
 
top developer mistakes
top developer mistakes top developer mistakes
top developer mistakes
 
IoT Product Design and Prototyping
IoT Product Design and PrototypingIoT Product Design and Prototyping
IoT Product Design and Prototyping
 
It's a startup life: from idea to execution.
It's a startup life: from idea to execution.It's a startup life: from idea to execution.
It's a startup life: from idea to execution.
 

More from Sanjana Chowdhury

Rsqrd AI: Application of Explanation Model in Healthcare
Rsqrd AI: Application of Explanation Model in HealthcareRsqrd AI: Application of Explanation Model in Healthcare
Rsqrd AI: Application of Explanation Model in HealthcareSanjana Chowdhury
 
Rsqrd AI: Recent Advances in Explainable Machine Learning Research
Rsqrd AI: Recent Advances in Explainable Machine Learning ResearchRsqrd AI: Recent Advances in Explainable Machine Learning Research
Rsqrd AI: Recent Advances in Explainable Machine Learning ResearchSanjana Chowdhury
 
Rsqrd AI: Incorporating Priors with Feature Attribution on Text Classification
Rsqrd AI: Incorporating Priors with Feature Attribution on Text ClassificationRsqrd AI: Incorporating Priors with Feature Attribution on Text Classification
Rsqrd AI: Incorporating Priors with Feature Attribution on Text ClassificationSanjana Chowdhury
 
Rsqrd AI: Discovering Natural Bugs Using Adversarial Perturbations
Rsqrd AI: Discovering Natural Bugs Using Adversarial PerturbationsRsqrd AI: Discovering Natural Bugs Using Adversarial Perturbations
Rsqrd AI: Discovering Natural Bugs Using Adversarial PerturbationsSanjana Chowdhury
 
Rsqrd AI: A Survey of The Current Ecosystem of Explainability Techniques
Rsqrd AI: A Survey of The Current Ecosystem of Explainability TechniquesRsqrd AI: A Survey of The Current Ecosystem of Explainability Techniques
Rsqrd AI: A Survey of The Current Ecosystem of Explainability TechniquesSanjana Chowdhury
 
Rsqrd AI: Explaining ML Models w/ Geometric Intuition
Rsqrd AI: Explaining ML Models w/ Geometric IntuitionRsqrd AI: Explaining ML Models w/ Geometric Intuition
Rsqrd AI: Explaining ML Models w/ Geometric IntuitionSanjana Chowdhury
 
Rsqrd AI: Errudite- Scalable, Reproducible, and Testable Error Analysis
Rsqrd AI: Errudite- Scalable, Reproducible, and Testable Error AnalysisRsqrd AI: Errudite- Scalable, Reproducible, and Testable Error Analysis
Rsqrd AI: Errudite- Scalable, Reproducible, and Testable Error AnalysisSanjana Chowdhury
 
Rsqrd AI: Exploring Machine Learning Model Predictions
Rsqrd AI: Exploring Machine Learning Model PredictionsRsqrd AI: Exploring Machine Learning Model Predictions
Rsqrd AI: Exploring Machine Learning Model PredictionsSanjana Chowdhury
 
Rsqrd AI: Zestimates and Zillow AI Platform
Rsqrd AI: Zestimates and Zillow AI PlatformRsqrd AI: Zestimates and Zillow AI Platform
Rsqrd AI: Zestimates and Zillow AI PlatformSanjana Chowdhury
 
Rsqrd AI: ML Tooling at an AI-first Startup
Rsqrd AI: ML Tooling at an AI-first StartupRsqrd AI: ML Tooling at an AI-first Startup
Rsqrd AI: ML Tooling at an AI-first StartupSanjana Chowdhury
 
Rsqrd AI: From R&D to ROI of AI
Rsqrd AI: From R&D to ROI of AIRsqrd AI: From R&D to ROI of AI
Rsqrd AI: From R&D to ROI of AISanjana Chowdhury
 
Rsqrd AI: How to Design a Reliable and Reproducible Pipeline
Rsqrd AI: How to Design a Reliable and Reproducible PipelineRsqrd AI: How to Design a Reliable and Reproducible Pipeline
Rsqrd AI: How to Design a Reliable and Reproducible PipelineSanjana Chowdhury
 

More from Sanjana Chowdhury (12)

Rsqrd AI: Application of Explanation Model in Healthcare
Rsqrd AI: Application of Explanation Model in HealthcareRsqrd AI: Application of Explanation Model in Healthcare
Rsqrd AI: Application of Explanation Model in Healthcare
 
Rsqrd AI: Recent Advances in Explainable Machine Learning Research
Rsqrd AI: Recent Advances in Explainable Machine Learning ResearchRsqrd AI: Recent Advances in Explainable Machine Learning Research
Rsqrd AI: Recent Advances in Explainable Machine Learning Research
 
Rsqrd AI: Incorporating Priors with Feature Attribution on Text Classification
Rsqrd AI: Incorporating Priors with Feature Attribution on Text ClassificationRsqrd AI: Incorporating Priors with Feature Attribution on Text Classification
Rsqrd AI: Incorporating Priors with Feature Attribution on Text Classification
 
Rsqrd AI: Discovering Natural Bugs Using Adversarial Perturbations
Rsqrd AI: Discovering Natural Bugs Using Adversarial PerturbationsRsqrd AI: Discovering Natural Bugs Using Adversarial Perturbations
Rsqrd AI: Discovering Natural Bugs Using Adversarial Perturbations
 
Rsqrd AI: A Survey of The Current Ecosystem of Explainability Techniques
Rsqrd AI: A Survey of The Current Ecosystem of Explainability TechniquesRsqrd AI: A Survey of The Current Ecosystem of Explainability Techniques
Rsqrd AI: A Survey of The Current Ecosystem of Explainability Techniques
 
Rsqrd AI: Explaining ML Models w/ Geometric Intuition
Rsqrd AI: Explaining ML Models w/ Geometric IntuitionRsqrd AI: Explaining ML Models w/ Geometric Intuition
Rsqrd AI: Explaining ML Models w/ Geometric Intuition
 
Rsqrd AI: Errudite- Scalable, Reproducible, and Testable Error Analysis
Rsqrd AI: Errudite- Scalable, Reproducible, and Testable Error AnalysisRsqrd AI: Errudite- Scalable, Reproducible, and Testable Error Analysis
Rsqrd AI: Errudite- Scalable, Reproducible, and Testable Error Analysis
 
Rsqrd AI: Exploring Machine Learning Model Predictions
Rsqrd AI: Exploring Machine Learning Model PredictionsRsqrd AI: Exploring Machine Learning Model Predictions
Rsqrd AI: Exploring Machine Learning Model Predictions
 
Rsqrd AI: Zestimates and Zillow AI Platform
Rsqrd AI: Zestimates and Zillow AI PlatformRsqrd AI: Zestimates and Zillow AI Platform
Rsqrd AI: Zestimates and Zillow AI Platform
 
Rsqrd AI: ML Tooling at an AI-first Startup
Rsqrd AI: ML Tooling at an AI-first StartupRsqrd AI: ML Tooling at an AI-first Startup
Rsqrd AI: ML Tooling at an AI-first Startup
 
Rsqrd AI: From R&D to ROI of AI
Rsqrd AI: From R&D to ROI of AIRsqrd AI: From R&D to ROI of AI
Rsqrd AI: From R&D to ROI of AI
 
Rsqrd AI: How to Design a Reliable and Reproducible Pipeline
Rsqrd AI: How to Design a Reliable and Reproducible PipelineRsqrd AI: How to Design a Reliable and Reproducible Pipeline
Rsqrd AI: How to Design a Reliable and Reproducible Pipeline
 

Recently uploaded

Automation Ops Series: Session 1 - Introduction and setup DevOps for UiPath p...
Automation Ops Series: Session 1 - Introduction and setup DevOps for UiPath p...Automation Ops Series: Session 1 - Introduction and setup DevOps for UiPath p...
Automation Ops Series: Session 1 - Introduction and setup DevOps for UiPath p...DianaGray10
 
From Challenger to Champion: How SpiraPlan Outperforms JIRA+Plugins
From Challenger to Champion: How SpiraPlan Outperforms JIRA+PluginsFrom Challenger to Champion: How SpiraPlan Outperforms JIRA+Plugins
From Challenger to Champion: How SpiraPlan Outperforms JIRA+PluginsInflectra
 
Dev Dives: Leverage APIs and Gen AI to power automations for RPA and software...
Dev Dives: Leverage APIs and Gen AI to power automations for RPA and software...Dev Dives: Leverage APIs and Gen AI to power automations for RPA and software...
Dev Dives: Leverage APIs and Gen AI to power automations for RPA and software...UiPathCommunity
 
Battle of React State Managers in frontend applications
Battle of React State Managers in frontend applicationsBattle of React State Managers in frontend applications
Battle of React State Managers in frontend applicationsEvangelia Mitsopoulou
 
Early Tech Adoption: Foolish or Pragmatic? - 17th ISACA South Florida WOW Con...
Early Tech Adoption: Foolish or Pragmatic? - 17th ISACA South Florida WOW Con...Early Tech Adoption: Foolish or Pragmatic? - 17th ISACA South Florida WOW Con...
Early Tech Adoption: Foolish or Pragmatic? - 17th ISACA South Florida WOW Con...Adrian Sanabria
 
Progress Report: Ministry of IT under Dr. Umar Saif Aug 23-Feb'24
Progress Report: Ministry of IT under Dr. Umar Saif Aug 23-Feb'24Progress Report: Ministry of IT under Dr. Umar Saif Aug 23-Feb'24
Progress Report: Ministry of IT under Dr. Umar Saif Aug 23-Feb'24Umar Saif
 
Campotel: Telecommunications Infra and Network Builder - Company Profile
Campotel: Telecommunications Infra and Network Builder - Company ProfileCampotel: Telecommunications Infra and Network Builder - Company Profile
Campotel: Telecommunications Infra and Network Builder - Company ProfileCampotelPhilippines
 
How we think about an advisor tech stack
How we think about an advisor tech stackHow we think about an advisor tech stack
How we think about an advisor tech stackSummit
 
Synergy in Leadership and Product Excellence: A Blueprint for Growth by CPO, ...
Synergy in Leadership and Product Excellence: A Blueprint for Growth by CPO, ...Synergy in Leadership and Product Excellence: A Blueprint for Growth by CPO, ...
Synergy in Leadership and Product Excellence: A Blueprint for Growth by CPO, ...Product School
 
Introducing the New FME Community Webinar - Feb 21, 2024 (2).pdf
Introducing the New FME Community Webinar - Feb 21, 2024 (2).pdfIntroducing the New FME Community Webinar - Feb 21, 2024 (2).pdf
Introducing the New FME Community Webinar - Feb 21, 2024 (2).pdfSafe Software
 
Bringing nullability into existing code - dammit is not the answer.pptx
Bringing nullability into existing code - dammit is not the answer.pptxBringing nullability into existing code - dammit is not the answer.pptx
Bringing nullability into existing code - dammit is not the answer.pptxMaarten Balliauw
 
Relationship Counselling: From Disjointed Features to Product-First Thinking ...
Relationship Counselling: From Disjointed Features to Product-First Thinking ...Relationship Counselling: From Disjointed Features to Product-First Thinking ...
Relationship Counselling: From Disjointed Features to Product-First Thinking ...Product School
 
Apex Replay Debugger and Salesforce Platform Events.pptx
Apex Replay Debugger and Salesforce Platform Events.pptxApex Replay Debugger and Salesforce Platform Events.pptx
Apex Replay Debugger and Salesforce Platform Events.pptxmohayyudin7826
 
Bit N Build Poland
Bit N Build PolandBit N Build Poland
Bit N Build PolandGDSC PJATK
 
Dynamical systems simulation in Python for science and engineering
Dynamical systems simulation in Python for science and engineeringDynamical systems simulation in Python for science and engineering
Dynamical systems simulation in Python for science and engineeringMassimo Talia
 
"How we created an SRE team in Temabit as a part of FOZZY Group in conditions...
"How we created an SRE team in Temabit as a part of FOZZY Group in conditions..."How we created an SRE team in Temabit as a part of FOZZY Group in conditions...
"How we created an SRE team in Temabit as a part of FOZZY Group in conditions...Fwdays
 
"AIRe - AI Reliability Engineering", Denys Vasyliev
"AIRe - AI Reliability Engineering", Denys Vasyliev"AIRe - AI Reliability Engineering", Denys Vasyliev
"AIRe - AI Reliability Engineering", Denys VasylievFwdays
 
Enhancing Productivity and Insight A Tour of JDK Tools Progress Beyond Java 17
Enhancing Productivity and Insight  A Tour of JDK Tools Progress Beyond Java 17Enhancing Productivity and Insight  A Tour of JDK Tools Progress Beyond Java 17
Enhancing Productivity and Insight A Tour of JDK Tools Progress Beyond Java 17Ana-Maria Mihalceanu
 
Curtain Module Manual Zigbee Neo CS01-1C.pdf
Curtain Module Manual Zigbee Neo CS01-1C.pdfCurtain Module Manual Zigbee Neo CS01-1C.pdf
Curtain Module Manual Zigbee Neo CS01-1C.pdfDomotica daVinci
 

Recently uploaded (20)

In sharing we trust. Taking advantage of a diverse consortium to build a tran...
In sharing we trust. Taking advantage of a diverse consortium to build a tran...In sharing we trust. Taking advantage of a diverse consortium to build a tran...
In sharing we trust. Taking advantage of a diverse consortium to build a tran...
 
Automation Ops Series: Session 1 - Introduction and setup DevOps for UiPath p...
Automation Ops Series: Session 1 - Introduction and setup DevOps for UiPath p...Automation Ops Series: Session 1 - Introduction and setup DevOps for UiPath p...
Automation Ops Series: Session 1 - Introduction and setup DevOps for UiPath p...
 
From Challenger to Champion: How SpiraPlan Outperforms JIRA+Plugins
From Challenger to Champion: How SpiraPlan Outperforms JIRA+PluginsFrom Challenger to Champion: How SpiraPlan Outperforms JIRA+Plugins
From Challenger to Champion: How SpiraPlan Outperforms JIRA+Plugins
 
Dev Dives: Leverage APIs and Gen AI to power automations for RPA and software...
Dev Dives: Leverage APIs and Gen AI to power automations for RPA and software...Dev Dives: Leverage APIs and Gen AI to power automations for RPA and software...
Dev Dives: Leverage APIs and Gen AI to power automations for RPA and software...
 
Battle of React State Managers in frontend applications
Battle of React State Managers in frontend applicationsBattle of React State Managers in frontend applications
Battle of React State Managers in frontend applications
 
Early Tech Adoption: Foolish or Pragmatic? - 17th ISACA South Florida WOW Con...
Early Tech Adoption: Foolish or Pragmatic? - 17th ISACA South Florida WOW Con...Early Tech Adoption: Foolish or Pragmatic? - 17th ISACA South Florida WOW Con...
Early Tech Adoption: Foolish or Pragmatic? - 17th ISACA South Florida WOW Con...
 
Progress Report: Ministry of IT under Dr. Umar Saif Aug 23-Feb'24
Progress Report: Ministry of IT under Dr. Umar Saif Aug 23-Feb'24Progress Report: Ministry of IT under Dr. Umar Saif Aug 23-Feb'24
Progress Report: Ministry of IT under Dr. Umar Saif Aug 23-Feb'24
 
Campotel: Telecommunications Infra and Network Builder - Company Profile
Campotel: Telecommunications Infra and Network Builder - Company ProfileCampotel: Telecommunications Infra and Network Builder - Company Profile
Campotel: Telecommunications Infra and Network Builder - Company Profile
 
How we think about an advisor tech stack
How we think about an advisor tech stackHow we think about an advisor tech stack
How we think about an advisor tech stack
 
Synergy in Leadership and Product Excellence: A Blueprint for Growth by CPO, ...
Synergy in Leadership and Product Excellence: A Blueprint for Growth by CPO, ...Synergy in Leadership and Product Excellence: A Blueprint for Growth by CPO, ...
Synergy in Leadership and Product Excellence: A Blueprint for Growth by CPO, ...
 
Introducing the New FME Community Webinar - Feb 21, 2024 (2).pdf
Introducing the New FME Community Webinar - Feb 21, 2024 (2).pdfIntroducing the New FME Community Webinar - Feb 21, 2024 (2).pdf
Introducing the New FME Community Webinar - Feb 21, 2024 (2).pdf
 
Bringing nullability into existing code - dammit is not the answer.pptx
Bringing nullability into existing code - dammit is not the answer.pptxBringing nullability into existing code - dammit is not the answer.pptx
Bringing nullability into existing code - dammit is not the answer.pptx
 
Relationship Counselling: From Disjointed Features to Product-First Thinking ...
Relationship Counselling: From Disjointed Features to Product-First Thinking ...Relationship Counselling: From Disjointed Features to Product-First Thinking ...
Relationship Counselling: From Disjointed Features to Product-First Thinking ...
 
Apex Replay Debugger and Salesforce Platform Events.pptx
Apex Replay Debugger and Salesforce Platform Events.pptxApex Replay Debugger and Salesforce Platform Events.pptx
Apex Replay Debugger and Salesforce Platform Events.pptx
 
Bit N Build Poland
Bit N Build PolandBit N Build Poland
Bit N Build Poland
 
Dynamical systems simulation in Python for science and engineering
Dynamical systems simulation in Python for science and engineeringDynamical systems simulation in Python for science and engineering
Dynamical systems simulation in Python for science and engineering
 
"How we created an SRE team in Temabit as a part of FOZZY Group in conditions...
"How we created an SRE team in Temabit as a part of FOZZY Group in conditions..."How we created an SRE team in Temabit as a part of FOZZY Group in conditions...
"How we created an SRE team in Temabit as a part of FOZZY Group in conditions...
 
"AIRe - AI Reliability Engineering", Denys Vasyliev
"AIRe - AI Reliability Engineering", Denys Vasyliev"AIRe - AI Reliability Engineering", Denys Vasyliev
"AIRe - AI Reliability Engineering", Denys Vasyliev
 
Enhancing Productivity and Insight A Tour of JDK Tools Progress Beyond Java 17
Enhancing Productivity and Insight  A Tour of JDK Tools Progress Beyond Java 17Enhancing Productivity and Insight  A Tour of JDK Tools Progress Beyond Java 17
Enhancing Productivity and Insight A Tour of JDK Tools Progress Beyond Java 17
 
Curtain Module Manual Zigbee Neo CS01-1C.pdf
Curtain Module Manual Zigbee Neo CS01-1C.pdfCurtain Module Manual Zigbee Neo CS01-1C.pdf
Curtain Module Manual Zigbee Neo CS01-1C.pdf
 

Rsqrd AI: Making Conversational AI Work for Everybody

  • 1. Making Conversational AI Work for Everybody: An Intro to Conversation Driven Development Dr. Rachael Tatman
  • 3. How I got here About Me ● 2012- 2017: PhD in Linguistics ○ Modelling demographic disparities in Automatic Speech Recognition ○ FAT* ML ● 2017- 2020: Developer Advocate @ Kaggle (Google) ○ "The home of data science" ○ Machine learning education ○ Live Streaming: Livecoding & Paper Reading ● 2020 - now: Developer Advocate @ Rasa ○ Open source conversational AI framework & free software for conversation driven development ○ Developer education ○ Video, blogs, tutorials, live streaming, talks :)
  • 4. Sooo.... why do I choose to work on chatbots/ conversational AI?
  • 5. Some false assumptions we tend to make - Everyone has access to a computer - Everyone has access to the internet - Everyone knows how to Google stuff - Everyone likes visual interfaces - Everyone has a good/affordable enough internet connection to load graphics - Everyone knows how to use a website - Everyone knows how to use YOUR website - Everyone can make calls during business hours https://answers.microsoft.com/en-us/ie/forum/ie11-iewindows8_1/how-much-data-being-us ed-when-visiting-a-website/5028b804-3adf-4093-b10a-a058d020b19a
  • 6. Why conversational AI? - Most people already know how to have a conversation - NLP methods are able to handle a lot more variation in input now - A focused Conversational AI can help people do tasks much faster - Chalmers, a conversational assistant for people experiencing homelessness, helped people find information 60 times faster than searching (https://www.amplelabs.co/chalmers/)
  • 7. Why conversational AI? - Most people already know how to have a conversation - NLP methods are able to handle a lot more variation in input now - A focused Conversational AI can help people do tasks much faster - Chalmers, an converational assistant for people experiencing homelessness, helped people find information 60 times faster than searching Your assistant has to hold up their end of the bargain: have a good, helpful conversation that meets your users’ expectations and genuinely helps them. Good design is important, but you probably can’t predict everything your users will need/want/do.
  • 9. CDD captures the lessons we’ve learned as a community WHY CDD If you’ve built conversational AI before, you know that: ● It is very hard. ● Building a prototype is not the hard part. ● The hard parts all show up when you want to go from a prototype to something you’d want to ship. Conversation-Driven Development should: ● Help all of us build better conversational AI. ● Save newcomers from having to learn this the hard way.
  • 10. Conversation-Driven Development is made up of six actions ABOUT CDD share fixtrackreview annotate test
  • 11. Users will always surprise you. So get some test users to try your prototype as early as possible. Shipping without having a bunch of test users has never worked. Your project won’t be the exception. Share
  • 12. Review At every stage of a project, it is worth reading what users are saying. Avoid getting caught up in metrics right away. Conversations are valuable data.
  • 13. Annotate Using a script to generate synthetic training data Turning real messages into training examples
  • 14. Test Professional teams don’t ship applications without tests. Use whole conversations as end-to-end tests Run them on a continuous integration (CI) server.
  • 15. PrototypeTrack Use proxy measures to track which conversations are successful and which ones failed. ‘Negative’ signals are useful too, e.g. users not getting back in touch with support.
  • 16. PrototypeFix Study conversations that went smoothly and ones that failed. Successful conversations can become new tests 🎉 Fix issues by annotating more data and/or fixing your code 🔧
  • 18. It’s not a linear process: you’ll find yourself jumping between these actions PROCESS share fixtrackreview annotate test
  • 19. Some actions require software skills, others a deep understanding of the user TEAM Image credit: Freepik
  • 20. How does this help?
  • 21. Why conversational AI? - Most people already know how to have a conversation - NLP methods are able to handle a lot more variation in input now - A focused Conversational AI can help people do tasks much faster - Chalmers, an converational assistant for people experiencing homelessness, helped people find information 60 times faster than searching Your assistant has to hold up their end of the bargain: have a good, helpful conversation that meets your users’ expectations and genuinely helps them. Good design is important, but you probably can’t predict everything your users will need/want/do.
  • 22. Why does CDD help? - CDD lets you meet users where they are now and help them right away - You don’t have to predict or guess what your users want or need - You can make quick, incremental improvements - You can meet shifting needs or expectations
  • 23. Rachael Tatman @rctatman r.tatman@rasa.com Rasa Technologies GmbH, Schönhauser Allee 175, 10119 Berlin, Germany Questions?