1 Best Practices Conversational UX Design 2 Best Practices - - PowerPoint PPT Presentation

1

2

Best Practices Conversational UX Design

3

Best Practices Conversational UX Design

SET THE RIGHT EXPECTATIONS

Set the right tone Tell users what they can do and what to expect Is it more an open or a closed conversation?

4

Best Practices Conversational UX Design

UX Bear: http://uxchat.me/ Image Context Matters: https://chatbotsmagazine.com/context-is-king-creating-intelligent-conversations-for-chatbots-9372bd6c2ca4

CONSIDER THE CONTEXT

Where is the chatbot integrated? What is the context of your user?

5

Best Practices Conversational UX Design

Image: https://www.gizmodo.com.au/2016/04/facebook-chatbots-are-frustrating-and-useless/

MAKE SENSE OF USE CASES

Does the new flow make sense? What use cases the bot can do and can’t do Is it more efficient than using other channels?

6

Best Practices Conversational UX Design

Image: https://magazine.chatkit.com/2018/11/28/how-to-give-your-chatbot-a-personality/

PERSONALITY IS CRUICIAL

What personality should your chatbot reflect? Create a persona that best fits your product

7

Best Practices Conversational UX Design

UX Bear: http://uxchat.me/

DESIGN LANGUAGE

Take the time to design language Find the right tone of language

8

Best Practices Conversational UX Design

Do you want to order pizza or pasta? Yes.

EFFICIENT COMMUNICATION

Clearly set the expectations for your bot Formulate clear questions and answers

9

Best Practices Conversational UX Design

Image: https://chatbotsmagazine.com/how-to-write-user-friendly-error-messages-41e66a77a026

TALK ABOUT FAILURE

A user’s question always needs to be answered Acknowledge failure in a remorseful tone

10

Best Practices Conversational UX Design

Image: https://www.kommunicate.io/blog/chatbot-human-handoff/

SMOOTH HANDOVER

Define clear handshakes between human and bot Integrate your bot in your customer facing strategy

11

Best Practices Conversational AI - Training & Testing

12

Best Practices Conversational AI Training & Testing

Current “natural language understanding” ≠ true language understanding Conversational AI calculate a user’s intention taking into consideration

• the user’s input
• the intent it is taught to expect
• the training it receives based on intent

13

Information Action Flight details Flight prices Booking a flight Checking in

Intents

Best Practices Conversational AI Training & Testing

14

Intention: flight prices Calculated intent: flight details Intention: flight prices Calculated intent: checking in Intention: flight prices Calculated intent: flight prices

Best Practices Conversational AI Training & Testing

15 Variety of natural language makes a broad language training extremely difficult The more varied language inputs are, the better the application will be able to recognize intent Finding large groups of different people to interact with is difficult in prototype and beta phases Chatbot & Virtual Assistant Testing

• uncover training gaps
• provide invaluable training data

Best Practices Conversational AI Training & Testing

16

Intents Opening hours Locations Special offers Careers

125 individual questions 125 individual questions 25 individual questions 25 individual questions

Chatbot of a retail chain

Best Practices Conversational AI Training & Testing

17 36 testers came up with more than 3500 questions regarding store locations Overly creative questions

• Where are stores in 48.158538, 11.645419?
• Is it possibe to use the bus from Bad Homburg to go

shopping in one of your stores?

• What stores are near the highway?

Best Practices Conversational AI Training & Testing

I‘m not allowed to vary the same question with different locations? I don‘t think there are 125 different ways to ask for a store location.

18 Build your bot up slowly, but consistently

• Start with the core intents
• Train all intents sufficiently to avoid under- and overtraining
• Use as many different users as possible
• Limit their individual input; train in iterations if possible
• Consider what kind of training fits your intents best
• Does the intent encompass isolated information?
• Does the intent trigger a process?
• Never stop training your bot

Best Practices Conversational AI Training & Testing

19

10 Do’s & Dont’s when designing a chatbot

20

TEST, TEST, TEST: Test in iterations and with your specific target group

10

CRAWL, WALK, RUN: Build a core MVP with intents, build layer by layer

9

SET THE RIGHT EXPECTATIONS: Users need to know clearly what to and what not to expect

3

PERSONALITY IS CRUCIAL: Start with a bot persona - don't let your bot pretend to be a human?

4

DESIGN LANGUAGE: Target-group & chatbot personality specific language design

5

CHOOSE THE RIGHT PLATFORM: Right platform, right technology – choose wisely

1

TALK ABOUT FAILURE: Compensate flaws and error loops – give clear feedback to the users

6

SMOOTH HANDOVER: Integrate in customer facing strategy, define handshakes with human

7

MAKE SENSE OF USE CASES: Design clear use cases where usage of the bot make sense

8

CHOOSE THE RIGHT PEOPLE: Several disciplines needed – technology, screenwriting, linguistics

2

21

We are here to help

Testing Reality: Real Users. Real Devices. Real time

Chatbot & Virtual Assistant Testing

Our all-inclusive language test for your chatbot, conversational AI or language assistant: Use our crowd to test and optimise the capabilities of your application under real conditions! Discover more >

Contact us for more details or live demo

Do you have questions about Chatbot and virtual assistant testing? Would you like to have more information on how we can help you make your digital products even better? Just send us a message. Get in touch >