SlideShare a Scribd company logo
Designing conversations
How I learned to stop worrying and embraced
our new chatbot overlords
Justin Barr Young
@theJayBeeWhy
Carbon Five Talk Night, May 18 2016
Agenda
1. Defining Conversational UI and Bots
2. Bot platforms
3. Tips for designing bot conversations
Conversational UI:
Interacting with a computer through conversation,
versus a Graphical User Interface (GUI).
Chatbot:
A computer program designed to simulate
conversation with human users through chat.
Bots are a form of conversational UI.
Slack
Carbon Five Slackbots
Platforms
Current bot landscape breaks down into 3 separate strains:
1. SMS-based bots
2. Over the Top (OTT) bots, built on existing platforms
3. Dedicated native apps
1. SMS-based bots
Bots like Assist and Prompt communicate through texting
Largest app platform pre-installed on every device
Light-weight, low-cost way to launch and get feedback
No app store review!
Limited types of content, no extensibility
Assist
2. Over the Top (OTT) bots
OTT bots use platforms like Facebook Messenger or WhatsApp
Use a larger array of content like photos, GIFs, stickers
Users can easily find and befriend your bot
Platforms are becoming more robust with GUI features
and toolkits for developers
Platforms have rules and limits you have to abide by
Uber for Messenger
3. Dedicated native apps
Bots like Operator or Quartz live entirely in their own app
Freedom to use any content you want in messages
App “wrapper” can organize conversation threads or
incorporate traditional GUI features
Opens the door for “atomic applications”
High implementation costs
Operator
GoButler
Atomic Apps
Each message is its own mini application
Use text, media, and interface components in conversation
Leverages conversation and traditional GUI for tasks
when appropriate
Operator
Introducing the bot
When the user first talks to the bot:
Be clear about what the bot does and doesn’t do
Don’t be afraid to to glamorize the bot’s mission!
Offer a “help” command
Hey! I’m BurritoBot.
I can order burritos, tacos, and bowls for you!
BurritoBot
If you ever need help, just say “help” and I’ll offer
a list of all the commands you can use.
Asking questions
Do ask leading questions
Don’t ask open ended questions
Demonstrate the type of answer the bot is looking for
If the number of possible answers is small, just list them
What do you want to order?
1. Burrito
2. Taco
3. Bowl
BurritoBot
You can say the name of the item or its number,
like “1” or “burrito”.
Break things down
“Talk” in multiple paragraphs at a comfortable cadence
Ask complicated questions as separate, discrete questions
Confirm an answer before asking the next question
Great! Let’s order your burrito.
1. White
2. Wheat
3. Lettuce
BurritoBot
First, what kind of tortilla do you want?
Operator
Quartz
Be flexible
Consider different ways to say something.
Consider the different ways a user might semantically
answer a question
Consider how a user might format an answer
Offer syntax examples when asking a question
Assist
Task paths
Without visuals, user flows might seem confusing.
Over-communicate task paths
When a user wants to switch paths, be explicit about
pausing or ending the current path.
Start a new path after a few hours or a day of no response
Operator
Modals
Sometimes a bot has to insist that a user does something
Don’t repeat the same question over and over –
ask it in a variety of ways for the user
You want a burrito with a wheat tortilla, pinto beans,
carne asada, cheese, medium salsa, and guacamole.
BurritoBot
Is that right?
Are you ready to order your burrito?
I can’t order your burrito until you confirm the order above.
Is that order correct? (Answer “Y” or “N”)
Responding to the bot
Terminal commands are hard to remember, but
natural language is inefficient
Create short, memorable, and vernacular commands
Slack
Input types
Typing in natural language can take a while…
Give users an easy way to references items or answers
Assign list items a number or letter
Break down questions into Y / N answers
Think about the user’s device
Assist
Fill in the _____
Consider a “madlibs” model to reduce answer options
and move conversations along
Give users meaningful choices, not false choices
Make sure the users have agency in the conversation
We have two vegetarian options: “Veggie” has grilled
zucchinis, onions, and corn. “Soyrizo” is soy-based
chorizo with medium spice.
BurritoBot
What sounds good?
Soyrizo, please Gimme the Veggie
Good example: Lifeline
Bad example: Quartz
Terrible example: Lark
Organizing chat threads
Scenarios Script Responses
Conclusion
Pick the right platform: SMS, OTT, or dedicated app
Leverage both conversation and GUI components
(when available)
Break tasks down and ask leading questions
Use the right input type for your device and context
Thanks!
Justin Barr Young
@theJayBeeWhy
Carbon Five Talk Night, May 18 2016

More Related Content

PDF
Chatbots DDD North2016
PDF
Lessons learned from building a commercial bot development platform
PDF
Mark Swaine UX Guy Designing Bot Experiences
PDF
Designing Intelligent Coversations: A Chatbot Workshop
PPTX
The Software Challenges of Building Smart Chatbots - ICSE'21
PPTX
Chatbots - A CMD for Humans (Ort Braude 2018)
PPTX
Chatbots - A CMD for Humans (Global Azure Bootcamp 2018, Tel-Aviv, Israel)
PDF
Chatbots 101
Chatbots DDD North2016
Lessons learned from building a commercial bot development platform
Mark Swaine UX Guy Designing Bot Experiences
Designing Intelligent Coversations: A Chatbot Workshop
The Software Challenges of Building Smart Chatbots - ICSE'21
Chatbots - A CMD for Humans (Ort Braude 2018)
Chatbots - A CMD for Humans (Global Azure Bootcamp 2018, Tel-Aviv, Israel)
Chatbots 101

Similar to Designing Conversations: How I learned to stop worrying and embraced our new chatbot overlords (20)

PPTX
Сергей Поплавский "DeepDive в Bot платформу Microsoft. Технические аспекты ра...
PDF
Chat apps v02
PDF
IRJET- Chatbot System for Latest Applications and Software
PPT
Building a bot with an intent
PPTX
Using Chatbots in Extension Programming
PPTX
Building bots to automate common developer tasks - Writing your first smart c...
PDF
The Chatbots Are Coming: A Guide to Chatbots, AI and Conversational Interfaces
 
PPTX
Build a mobile chatbot with Xamarin
PDF
Chatbots for Brand Representation in Comparison with Traditional Websites
PDF
Conversational Experiences for Humans
PDF
Conversational UIs for internal comms
PDF
Deus UX Machina
PDF
[TechWorldSummit Stockholm 2019] Building Bots for Human with Conversational ...
PDF
How to build an AI-powered chatbot.pdf
PDF
How to build an AI-powered chatbot.pdf
PDF
How to build an AI-powered chatbot.pdf
PPTX
Keys to Great Conversational Design from the Chatbot Conference
PDF
Let's Build a Chatbot!
PDF
Bot-Tender: A Chat Bot Walks into a Bar (Microsoft Tech Days Sweden 2018)
PDF
How to build a Chatbot with Google's Dialogflow
Сергей Поплавский "DeepDive в Bot платформу Microsoft. Технические аспекты ра...
Chat apps v02
IRJET- Chatbot System for Latest Applications and Software
Building a bot with an intent
Using Chatbots in Extension Programming
Building bots to automate common developer tasks - Writing your first smart c...
The Chatbots Are Coming: A Guide to Chatbots, AI and Conversational Interfaces
 
Build a mobile chatbot with Xamarin
Chatbots for Brand Representation in Comparison with Traditional Websites
Conversational Experiences for Humans
Conversational UIs for internal comms
Deus UX Machina
[TechWorldSummit Stockholm 2019] Building Bots for Human with Conversational ...
How to build an AI-powered chatbot.pdf
How to build an AI-powered chatbot.pdf
How to build an AI-powered chatbot.pdf
Keys to Great Conversational Design from the Chatbot Conference
Let's Build a Chatbot!
Bot-Tender: A Chat Bot Walks into a Bar (Microsoft Tech Days Sweden 2018)
How to build a Chatbot with Google's Dialogflow
Ad

Recently uploaded (20)

PDF
cuic standard and advanced reporting.pdf
PPTX
sap open course for s4hana steps from ECC to s4
PPTX
Spectroscopy.pptx food analysis technology
PPTX
Detection-First SIEM: Rule Types, Dashboards, and Threat-Informed Strategy
PDF
Mobile App Security Testing_ A Comprehensive Guide.pdf
PPT
“AI and Expert System Decision Support & Business Intelligence Systems”
PDF
Empathic Computing: Creating Shared Understanding
PDF
Peak of Data & AI Encore- AI for Metadata and Smarter Workflows
PDF
Building Integrated photovoltaic BIPV_UPV.pdf
PDF
TokAI - TikTok AI Agent : The First AI Application That Analyzes 10,000+ Vira...
PPTX
Big Data Technologies - Introduction.pptx
PPTX
VMware vSphere Foundation How to Sell Presentation-Ver1.4-2-14-2024.pptx
PDF
Encapsulation theory and applications.pdf
PPTX
Understanding_Digital_Forensics_Presentation.pptx
PDF
Electronic commerce courselecture one. Pdf
PDF
MIND Revenue Release Quarter 2 2025 Press Release
PDF
Unlocking AI with Model Context Protocol (MCP)
PPTX
KOM of Painting work and Equipment Insulation REV00 update 25-dec.pptx
PDF
Agricultural_Statistics_at_a_Glance_2022_0.pdf
PPTX
20250228 LYD VKU AI Blended-Learning.pptx
cuic standard and advanced reporting.pdf
sap open course for s4hana steps from ECC to s4
Spectroscopy.pptx food analysis technology
Detection-First SIEM: Rule Types, Dashboards, and Threat-Informed Strategy
Mobile App Security Testing_ A Comprehensive Guide.pdf
“AI and Expert System Decision Support & Business Intelligence Systems”
Empathic Computing: Creating Shared Understanding
Peak of Data & AI Encore- AI for Metadata and Smarter Workflows
Building Integrated photovoltaic BIPV_UPV.pdf
TokAI - TikTok AI Agent : The First AI Application That Analyzes 10,000+ Vira...
Big Data Technologies - Introduction.pptx
VMware vSphere Foundation How to Sell Presentation-Ver1.4-2-14-2024.pptx
Encapsulation theory and applications.pdf
Understanding_Digital_Forensics_Presentation.pptx
Electronic commerce courselecture one. Pdf
MIND Revenue Release Quarter 2 2025 Press Release
Unlocking AI with Model Context Protocol (MCP)
KOM of Painting work and Equipment Insulation REV00 update 25-dec.pptx
Agricultural_Statistics_at_a_Glance_2022_0.pdf
20250228 LYD VKU AI Blended-Learning.pptx
Ad

Designing Conversations: How I learned to stop worrying and embraced our new chatbot overlords

  • 1. Designing conversations How I learned to stop worrying and embraced our new chatbot overlords Justin Barr Young @theJayBeeWhy Carbon Five Talk Night, May 18 2016
  • 2. Agenda 1. Defining Conversational UI and Bots 2. Bot platforms 3. Tips for designing bot conversations
  • 3. Conversational UI: Interacting with a computer through conversation, versus a Graphical User Interface (GUI). Chatbot: A computer program designed to simulate conversation with human users through chat. Bots are a form of conversational UI.
  • 6. Platforms Current bot landscape breaks down into 3 separate strains: 1. SMS-based bots 2. Over the Top (OTT) bots, built on existing platforms 3. Dedicated native apps
  • 7. 1. SMS-based bots Bots like Assist and Prompt communicate through texting Largest app platform pre-installed on every device Light-weight, low-cost way to launch and get feedback No app store review! Limited types of content, no extensibility
  • 9. 2. Over the Top (OTT) bots OTT bots use platforms like Facebook Messenger or WhatsApp Use a larger array of content like photos, GIFs, stickers Users can easily find and befriend your bot Platforms are becoming more robust with GUI features and toolkits for developers Platforms have rules and limits you have to abide by
  • 11. 3. Dedicated native apps Bots like Operator or Quartz live entirely in their own app Freedom to use any content you want in messages App “wrapper” can organize conversation threads or incorporate traditional GUI features Opens the door for “atomic applications” High implementation costs
  • 14. Atomic Apps Each message is its own mini application Use text, media, and interface components in conversation Leverages conversation and traditional GUI for tasks when appropriate
  • 16. Introducing the bot When the user first talks to the bot: Be clear about what the bot does and doesn’t do Don’t be afraid to to glamorize the bot’s mission! Offer a “help” command
  • 17. Hey! I’m BurritoBot. I can order burritos, tacos, and bowls for you! BurritoBot If you ever need help, just say “help” and I’ll offer a list of all the commands you can use.
  • 18. Asking questions Do ask leading questions Don’t ask open ended questions Demonstrate the type of answer the bot is looking for If the number of possible answers is small, just list them
  • 19. What do you want to order? 1. Burrito 2. Taco 3. Bowl BurritoBot You can say the name of the item or its number, like “1” or “burrito”.
  • 20. Break things down “Talk” in multiple paragraphs at a comfortable cadence Ask complicated questions as separate, discrete questions Confirm an answer before asking the next question
  • 21. Great! Let’s order your burrito. 1. White 2. Wheat 3. Lettuce BurritoBot First, what kind of tortilla do you want?
  • 24. Be flexible Consider different ways to say something. Consider the different ways a user might semantically answer a question Consider how a user might format an answer Offer syntax examples when asking a question
  • 26. Task paths Without visuals, user flows might seem confusing. Over-communicate task paths When a user wants to switch paths, be explicit about pausing or ending the current path. Start a new path after a few hours or a day of no response
  • 28. Modals Sometimes a bot has to insist that a user does something Don’t repeat the same question over and over – ask it in a variety of ways for the user
  • 29. You want a burrito with a wheat tortilla, pinto beans, carne asada, cheese, medium salsa, and guacamole. BurritoBot Is that right? Are you ready to order your burrito? I can’t order your burrito until you confirm the order above. Is that order correct? (Answer “Y” or “N”)
  • 30. Responding to the bot Terminal commands are hard to remember, but natural language is inefficient Create short, memorable, and vernacular commands
  • 31. Slack
  • 32. Input types Typing in natural language can take a while… Give users an easy way to references items or answers Assign list items a number or letter Break down questions into Y / N answers Think about the user’s device
  • 34. Fill in the _____ Consider a “madlibs” model to reduce answer options and move conversations along Give users meaningful choices, not false choices Make sure the users have agency in the conversation
  • 35. We have two vegetarian options: “Veggie” has grilled zucchinis, onions, and corn. “Soyrizo” is soy-based chorizo with medium spice. BurritoBot What sounds good? Soyrizo, please Gimme the Veggie
  • 40. Conclusion Pick the right platform: SMS, OTT, or dedicated app Leverage both conversation and GUI components (when available) Break tasks down and ask leading questions Use the right input type for your device and context
  • 41. Thanks! Justin Barr Young @theJayBeeWhy Carbon Five Talk Night, May 18 2016