Menu
January 23, 2019 | By

AI IRL Podcast Episode 4: Why Natural Language Design Is the First Step to Make an Effective Chatbot


Subscribe via iTunes, Spotify and more.

In all the hype of AI and the rush to get something “out the door”, companies are starting to realize how poor AI and chatbot design can be detrimental to a business.  Having “AI” isn’t good enough.  Having an AI chatbot that can control conversations and solve problems all while keeping the user engaged and feeling great about the interaction is key.

This is where Hans van Dam’s expertise comes in.

Hans is the managing director of Robocopy and founder of The Conversational Academy. His company is changing the way AI interacts with customers by putting first thing first: natural language design. The Conversational Academy exists to train designers in this skill.

Whether you’re a UX designer, a copywriter, or a product owner, this episode is for you.

The 2 Ways Companies Get the Process Wrong.

  1. Many companies start by creating a flowchart, focusing on the business process they already have in place and knowledge management. Then they hand it to a copywriter to change the lorem ipsum into words.  In actually, you want to take it the other way around. Start with a user.
  2. Hans says instead of focusing on “what’s the next line the bot needs to say,” put two people in a room. Tell one he’s a bot and the other he’s a human. Have them play it out like improv theater. Whatever comes out is the first draft. Start with one user, what they want to achieve and how they want to feel.

Another problem many companies have is getting carried away with fancy, shiny tech.

“Before diving into the weirdest tech, just try putting together a couple conversations that work.” Hans Van Dam

One thing Hans’ company gets so right, is their 3 basic ingredients: understanding psychology, understanding tech, and writing effective copy. There are many benefits to nailing the perfect blend of these ingredients.

Natural Language Design Lets You Control the Conversation

It’s important to understand each party’s needs. Artificial and human brains have different limitations, capabilities, and triggers.

Bots need:

  • intent
  • context
  • variables
  • entities

Humans need:

  • empathy
  • guidance
  • persuasion
  • a pat on the back

Natural language creation should blend each party’s needs. Hans emphasizes creating methods for each different conversation type.

A customer service conversation has its own structure: the AI needs to do intent recognition, then try to solve a problem. In another case, maybe a financial institution is using a bot to try to persuade the user to update his payment information. This is a very different conversation in which the bot is asking tougher questions about a person’s finances.

“Being very thoughtful about conversation design allows you to take control of the conversations.” Hans

If you control the conversation you depend less on your AI. It’s not AI vs. conversation design. They need each other.

What about Buttons?

If you can solve an issue without buttons, then you know you have a perfect conversation. Hans emphasizes voice as his primary focus; however, there are some cases where buttons can be very effective.

Buttons can be used to steer the user’s thoughts. Maybe you want your user to give a positive answer; if you have 4 buttons and 3 are positive, the odds of a positive answer increase. This can work well for persuasion conversations like sales or booking meetings.

It can be good to have buttons, but it depends on the use case. In most cases, the goal is to push conversation design to try to solve without buttons.

4 Reasons Conversation Design Needs to Focus on Empathy

Every conversation involves the feelings of the human user. Emotions should not be ignored. Hans gives four reasons he focuses intently on integrating empathy into each conversation.

  1. It’s the hardest thing to get right.  Hans utilizes a bot scorecard that grades for 5 things: personality, natural language, helpfulness, persuasiveness, and empathy. Empathy is always the trickiest one.
  2. Even though users know a bot isn’t really “sorry,” they want to feel understood.  Often this can be done without simulating emotion. A bot can say “Ok, so you’re stuck on a train, and therefore you’re going to miss your flight.” Without feelings, the bot is understanding what’s going on, which makes the user feel listened to.
  3. Empathy helps with intent recognition.  If a bot says “Ok, so such-and-such thing is going on” and the user confirms, the user feels understood, and the bot knows which dialog to run.
  4. It prevents escalation.  Empathy is about addressing the softer side of the brain to keep them engaged and motivated. Keep them interacting with the chatbot.

“Empathy isn’t just saying ‘I’m sorry,’ it’s showing you understand the user and his context. Hans”

Fearful users can become inactive, if a process feels overwhelming, these are the kind of people who allow envelopes to go unopened and pile up. Angry users can become vengeful; they write negative reviews and posts on social media telling others to stay away.  Copywriting that uses empathetic psychological techniques like depersonalization, positive framing, social proof, and expectation management can prevent these frustrating situations.

Hans gives one caution here though. Companies can become over-obsessed with sentiment analysis. At the end of the day, when there’s something negative happening to a user, the person is upset and you need to deal with it. They care about empathy but they really just want the problem solved.

Conversational Academy

Robocopy started out as a small agency; they trained their own people in their own in-house academy.  People were emailing Hans all over the world asking to get into it.

So they launched a webinar series that was a huge hit.  Now they’re putting together a full course, over 10 hours of video in which people can be trained and certified conversation designers.

His program teaches:

  • natural language,
  • cooperative principles,
  • persona development,
  • scenario development,
  • conversation design,
  • sales and persuasion,
  • managing emotions,
  • optimization
  • copywriting techniques

It launches in January

Alongside the program is a subscription model for continuous improvement.  They plan to teach conversation design that’s specific to certain platforms, talk about trust and AI, have guest lectures, and much more.

“Everyone’s building hammers and we’re the only one’s training carpenters

This AI discussion with Hans van Dam was taken from our podcast. If you want more AI: In Real Life, check out our podcast on iTunes.

View transcript »


[Ryan Lester]
00:03 – 00:08
Hello, welcome, this is Ryan Lester host of AI in real life.
[Ryan Lester]
00:08 – 00:18
Welcome to this week’s podcast really excited for my guest this week interesting topic around the maturity of AI and customer engagement joining me.
[Ryan Lester]
00:18 – 00:24
Today is Hans Hans is the founder of robocopy based in Amsterdam.
[Ryan Lester]
00:24 – 00:42
They’ve really identified this leading opportunity or use case around the role of conversational designer in Ai and engaging with customers that conversational designed to really be front and center and really the way the Hans and his team are taking a leadership role in that is through building out a conversational Academy.
[Ryan Lester]
00:42 – 00:51
So helping companies better understand how they can put this design aspect front and center and how you engage with people through things like Ai and chatbots.
[Ryan Lester]
00:51 – 00:53
So Hans welcome.
[Ryan Lester]
00:53 – 00:56
Thanks so much for joining today, and I’ll thank you so much for having me.
[Ryan Lester]
00:57 – 00:59
Yeah, looking forward to our conversation.
[Ryan Lester]
00:59 – 01:28
I think that too often the user experience part of this the design element gets lost in the tech and I think this is a great topic that people really can learn and really Advanced things in a much better more effective way and kind of getting bogged down in some of the NLP related topics of AI first question I have for you to start off is it’s where do you see people failing when it comes to conversation to design, I guess where are these symptoms that the patient showing us where things are not going well in conversational design.
[Ryan Lester]
01:28 – 01:52
Well, I think the first step is really that the first steps the most important one and everybody gets it wrong to really focused on technology and on Knowledge Management and to business process that they already have in place and they start with that and they lead with that so they create a flow chart and then they sort of put that all together and the last step is to sort of hand that to a copywriter.
[Hans van Dam]:
01:52 – 01:57
That’s just going to turn to lorem ipsum into some words, but you
[Hans van Dam]:
01:57 – 02:14
You want to take it the other way around and sort of start with the user and star through role play and Sample dialogue to create a natural conversation and it’ll last step would really be to turn it into your software and then to make it work and to use start using technology.
[Hans van Dam]:
02:14 – 02:17
So I think people really get it backwards.
[Ryan Lester]
02:17 – 02:25
Yeah, the thing I think about is, you know, I’ve heard you talk about this topic and I think about it as almost if you’re writing a screenplay.
[Ryan Lester]
02:25 – 02:27
It’s like you want to understand.
[Ryan Lester]
02:27 – 02:42
What’s the story you want to tell you know, what’s the outcome you’re driving towards versus working on each script of the play and I think too often companies get to your point caught up in the well, what’s the next line that needs to be delivered by the bot versus what’s the actual story?
[Ryan Lester]
02:42 – 02:49
We’re trying to tell where we trying to take the audience and and I think to your point they get really caught up in this whole what’s the intent?
[Ryan Lester]
02:49 – 02:56
Let’s go to find that let’s work on the natural language processing and they they lose the forest for the trees to use kind of that analogy.
[Ryan Lester]
02:57 – 03:04
Yeah, and also what happens a lot, you know, when I’m a user I don’t care about other users their dialogues with this chat bot.
[Hans van Dam]:
03:04 – 03:25
So, you know what, you’ll see a lot of conversations are being constructed that if somebody wants a he doesn’t want be and you can sort of feel that in the dialogue because they sort of you know, they start with it sort of the Knowledge Management and then, you know, then you have different scenarios and they build around that but you just want to start with one user and sort of see what they want to achieve and design for that.
[Hans van Dam]:
03:25 – 03:31
So what we do is when we start out we make a list of like what are the Bots requirements in this conversation?
[Hans van Dam]:
03:31 – 03:38
So, you know if I want to change my address, I need to know the current address the new address and then I need to confirm that and verify my identity.
[Hans van Dam]:
03:38 – 03:42
So those are sort of like the Bots needs right and on the other hand.
[Hans van Dam]:
03:42 – 03:57
We have a user a human being that has certain needs and you know, he has certain things that will boost him that will increase motivations and their certain barriers that he faces that’s going to demotivate him under certain information needs that he has
[Hans van Dam]:
03:57 – 04:01
So what we do we just put two people in the room and we tell one person.
[Hans van Dam]:
04:01 – 04:09
Okay, you’re a chatbot and this is the information that you want to get from this conversation and at to get to a resolution and we tell the other person.
[Hans van Dam]:
04:09 – 04:17
Okay, you are a human being you’ve tried changing your address four times before it always filled and to keep sending the mail to the wrong address.
[Hans van Dam]:
04:18 – 04:27
So you want your address change and you want to change now and then, you know, it’s like improvisational theater and they have a dialogue and whatever comes out of that conversation.
[Ryan Lester]
04:27 – 04:51
That’s like your first low-fidelity conversation design and then you build on that as opposed to really, you know, trying to make it all perfect and think about the big picture and all the other different scenarios that could have taken place just start with one user and what they want to achieve and how they feel when they want to achieve that it’s great.
[Ryan Lester]
04:51 – 04:56
I think we see a similar challenge of just the topic of AI where companies are trying to take on everything at
[Ryan Lester]
04:57 – 05:02
They’re trying to go out every user Journey trying to a multiple use cases when in reality.
[Ryan Lester]
05:02 – 05:04
It’s focus on that first workflow.
[Ryan Lester]
05:04 – 05:07
And what’s the first thing you want to tackle to your point?
[Ryan Lester]
05:07 – 05:11
It’s around change of address or it’s around some specific workflow then understand.
[Ryan Lester]
05:11 – 05:11
Alright.
[Ryan Lester]
05:11 – 05:14
Well, what’s the information that needs to exchange as part of that workflow?
[Ryan Lester]
05:14 – 05:17
And then how do we build it out in a way that’s flexible.
[Ryan Lester]
05:17 – 05:19
But also helps lead that customer to a better outcome.
[Ryan Lester]
05:20 – 05:32
So I think that’s really great advice of focusing in on that core use case understanding what the information needs to be exchanged and then building out in a way that’s natural and comfortable for the user through that conversational design.
[Ryan Lester]
05:33 – 05:56
Yeah, I mean for us like, you know, if you have a conversation between a bot and a human there’s like everybody’s focused on natural language understanding and all the technology behind that but if you have a conversation between a bot and a human there’s one big difference between these two people and one is that one has an artificial brain and the other one has to human brain and they both lie, you know, they both have their own limitations.
[Hans van Dam]:
05:57 – 05:59
And capabilities and they both have their own triggers.
[Hans van Dam]:
05:59 – 06:16
So, you know a bot needs intent and context and variables and entities and all that stuff and natural language understanding solves that but human needs, you know, empathy and guidance and persuasion and helpfulness and maybe a pat on the shoulder once in a while.
[Hans van Dam]:
06:16 – 06:54
So natural language creation should focus on that and if you’re going to have good conversations between Bots and humans their natural language creation needs to be equally important as natural language understanding so before diving into like the weirdest Technologies and getting very Advanced whatever thing just try to put to just try putting together a couple conversations that work for both the body and the human that’s going to create good interactions and I think a lot of people sort of, you know, get carried away with which fancy shiny Tech before really, you know touching on like the most basic needs of the user.
[Ryan Lester]
06:55 – 07:20
Yeah, and I think your points also going over much of this is about people get caught up in the inbound of you know, what’s the intent what’s user saying but then there’s the feedback loop back to the user to say, you know, oh I need more information here or oh is this what you’re really saying or is this not what you’re really saying and that natural language creation aspect of you know, how are you interacting with that user in a very conversational way is critically important.
[Ryan Lester]
07:21 – 07:31
I guess are there some other best practices are things you’ve seen in this world of natural language creation that companies should be thinking about I mean, there are so many I feel like
[Hans van Dam]:
07:32 – 07:44
People are now I think we’re getting into the phase where people are becoming aware that they don’t know, right and sodaro more open to conversation design a sort of recognizing that as an issue as a problem.
[Hans van Dam]:
07:44 – 07:48
They need to solve and there’s just a lot of techniques that they can use.
[Hans van Dam]:
07:48 – 08:00
So what we try to do it RoboCop, he’s really, you know, we understand the technology we understand the psychology and we’re very good at copywriting and those are like a three ingredients that we have.
[Hans van Dam]:
08:00 – 08:06
And so what we do is try to really create methods around each and every conversation.
[Hans van Dam]:
08:06 – 08:11
So for a customer service conversation, there’s just certain conversational faces.
[Hans van Dam]:
08:12 – 08:26
So first you start with like d intake pretty much, you know, the intended recognition while you probably had going to have to ask a few questions to really make sure that you get it and then usually, you know going through a dialogue like this.
[Hans van Dam]:
08:26 – 08:30
You’re probably going to be asking questions to get to a resolution right?
[Hans van Dam]:
08:30 – 08:32
So if your TV’s not working
[Hans van Dam]:
08:32 – 08:34
Is it plugged in or does the internet work etc?
[Hans van Dam]:
08:34 – 08:37
So you sort of have to guide you use it through there?
[Hans van Dam]:
08:37 – 08:43
So for each face, we just try to really create copy writing techniques that will help you.
[Hans van Dam]:
08:44 – 08:49
So I know that if I’m going to have to ask you six questions that you’re going to lose motivation throughout.
[Hans van Dam]:
08:49 – 08:59
So what I have to do is do stuff to increase your motivation one way of doing that is maybe using social proof or expectation management.
[Hans van Dam]:
08:59 – 09:03
So I’ll say, you know, Ryan I’m going to ask you six questions.
[Hans van Dam]:
09:03 – 09:06
Most people have it sorted out within a minute.
[Hans van Dam]:
09:07 – 09:10
So that’s already you know, putting into your mind.
[Hans van Dam]:
09:10 – 09:10
Okay.
[Hans van Dam]:
09:10 – 09:15
So more people are going through this process and they have it sorted out.
[Hans van Dam]:
09:15 – 09:22
So that means it’s going to be successful so that those are like little psychological tricks that I can use to sort of increase motivation.
[Hans van Dam]:
09:22 – 09:32
So for every dialogue, we sort of really tried to create the framework and then attach copywriting principles to it to create better.
[Hans van Dam]:
09:32 – 09:38
Experiences so small commitments is another one right if I’m going to have to ask you a couple tough questions.
[Hans van Dam]:
09:38 – 09:44
Maybe I’m a financial institute and I’m going to need to ask you questions about where your money comes from or whatever.
[Hans van Dam]:
09:44 – 09:47
I know those are tough questions to ask.
[Hans van Dam]:
09:47 – 09:50
So what I want to do is just use small commitments and
[Hans van Dam]:
09:56 – 10:00
Did I lose my audio their last?
[Ryan Lester]
10:00 – 10:02
Yeah, I think we lost audio for a minute.
[Ryan Lester]
10:02 – 10:05
Why don’t you you did go quiet.
[Ryan Lester]
10:05 – 10:10
Do you want to go back to the last time?
[Ryan Lester]
10:10 – 10:18
I caught you you were saying something to the effect of if you want to get multi if you’re getting if you’re getting to fill out multiple items.
[Ryan Lester]
10:19 – 10:21
I got the escalation of commitment.
[Ryan Lester]
10:21 – 10:27
I think the word was used of just like you want to give them because it’s topic was a good one either.
[Ryan Lester]
10:27 – 10:30
So I’m gonna have to ask you a couple questions or want to increase motivation.
[Ryan Lester]
10:30 – 10:34
So that’s what so if you want to go back to their or want to go back a little further.
[Ryan Lester]
10:35 – 10:56
It was good up until I don’t know why we lost audio per second, but it was good up until you got to a point where you were just talking about like the that I liked your, you know, it’ll take one minute to fill out so you can either start right after that and we’ll just seem them together or you can start back at the beginning if you’re more comfortable, whatever you’ve yeah, I’ll just start I’ll just start with
[Hans van Dam]:
10:56 – 10:57
Asking a couple of questions.
[Hans van Dam]:
10:57 – 10:59
Yeah, I’ll pick it up.
[Hans van Dam]:
10:59 – 11:08
Yeah, so if I’m going to have to ask you a couple questions, maybe I’m going to ask you six questions and I know that you’re going to lose motivation throughout those six questions.
[Hans van Dam]:
11:08 – 11:13
So I have to do stuff to sort of get you pumped up and motivated to go through that process.
[Hans van Dam]:
11:13 – 11:18
So a technique that I could use is by saying, you know, I’m going to ask you six questions.
[Hans van Dam]:
11:18 – 11:47
Most people have to sort it out in a minute that’s already putting in your mind that you know, it’s social proof why you know more people are going through this process and they get it sorted out which suggests that it’s going to be successful and therefore worth your while so that those are principles that we can apply in these conversations, but also like small commitments if you know if I’m a bank and I’m going to have to ask you some serious questions about maybe where your money comes from or something like that.
[Hans van Dam]:
11:47 – 11:54
It helps to have a couple like simple questions in front of that where you can just say yes to and
[Hans van Dam]:
11:55 – 12:02
Very little risk Etc and that just increases your motivation and that allows me to then ask a tougher question.
[Hans van Dam]:
12:02 – 12:10
So what we try to do here at robocopy is really figure out, you know, which kind of conversations are there that can be solved by Bots.
[Hans van Dam]:
12:10 – 12:11
And what are they?
[Hans van Dam]:
12:11 – 12:17
What do they consist of and then what are the techniques that we can use per element within that conversation?
[Ryan Lester]
12:18 – 12:23
Yeah, that’s a great those examples are really they really bring it to life for me.
[Ryan Lester]
12:23 – 12:24
I think they’re great.
[Ryan Lester]
12:25 – 12:30
It’s interesting to me to of I think this space is new in the sense of that.
[Ryan Lester]
12:30 – 12:30
Yep.
[Ryan Lester]
12:30 – 12:37
I think there’s a little bit of experience of this from things through social but social engagement tend to be less complex.
[Ryan Lester]
12:37 – 12:44
There’s usually less workflow involved and so you’re starting to build this new competency within your company around to your point.
[Ryan Lester]
12:44 – 12:54
What’s the content how we displaying a message with the goal of driving conversion, you know getting a better outcome moving our customer along in the journey, but you’re doing it through this.
[Ryan Lester]
12:55 – 13:10
Interface which in many ways is new you might be doing some of this but by training your agents and you know having them do some role plays, but the way you script things for a bot is different than the way you script it for an agent because to your point, you know bought doesn’t have empathy.
[Ryan Lester]
13:10 – 13:11
They can’t do things on the fly.
[Ryan Lester]
13:11 – 13:19
So you really have to be deliberate in the way you’re creating your content to your Point Drive those better outcomes.
[Ryan Lester]
13:19 – 13:25
And the other cool thing is you can then A/B test it so you can say hey we think this is the right way of doing it.
[Ryan Lester]
13:25 – 13:29
Let’s try this way or try it that way and see which one drives to the better outcome.
[Ryan Lester]
13:29 – 13:36
Is it telling them how length of time or telling them what the outcome will be that’s going to drive them to hopefully complete that six-step process.
[Ryan Lester]
13:36 – 13:44
So I really like this thought and approach of being deliberate about how you’re creating the content but also using it as a way to test and learn.
[Ryan Lester]
13:45 – 13:55
Yeah, and I think also, you know being very conscious about how you design these conversations allows you to take control of the conversation and
[Hans van Dam]:
13:55 – 13:56
What that good?
[Hans van Dam]:
13:56 – 14:22
What that’s good for is that if you control the conversation going to depend Less on your AI, so, you know, if I see if I’m a bot and I say, you know, if I just tell you ask me any question that you can ask me any question, right and it’s going to be difficult if I’m about to answer that right, but if I say, you know my bit more proactive and I say, you know ask me a question about coffee then you’re probably going to ask me a question about coffee.
[Hans van Dam]:
14:23 – 14:34
So by being more proactive as a bottom thinking carefully about the psychology and how it can influence my user with conversation design and uncertain framing of words.
[Hans van Dam]:
14:34 – 14:55
I can influence them in such a way that I’m going to get the inputs that my a I can then understand and process so it’s not people always talk about, you know, AI first this conversation design, but I think they go hand in hand and that they need each other to function very well and I think that’s those also.
[Hans van Dam]:
14:55 – 14:58
Something that companies are becoming more and more aware of now.
[Ryan Lester]
14:58 – 15:00
Yeah, I agree.
[Ryan Lester]
15:00 – 15:09
One thing I push on your Seagate your thoughts on is so then how much do you guys spend time on buttons versus text input and you have an opinion on that?
[Ryan Lester]
15:09 – 15:10
Yeah.
[Ryan Lester]
15:10 – 15:12
That’s we got that one a lot.
[Hans van Dam]:
15:13 – 15:24
So in general what we do is we design for this first and you know, because if you can solve an issue just without buttons then it’s perfect.
[Hans van Dam]:
15:24 – 15:29
Then you have a great conversation but buttons are great way to influence users, right?
[Hans van Dam]:
15:29 – 15:35
You can just you know, Steer their thoughts and use it as framing put something in their minds.
[Hans van Dam]:
15:35 – 15:48
But also if you’re a chatbot and you know, you want your users to give a positive answer you can just you know, if you have four buttons and three of them are positive the odds of answering, you know, your questions in a positive way dramatically increase.
[Hans van Dam]:
15:48 – 15:55
So if you’re using Bots for persuasion for maybe sales or booking meetings Etc or you know signups for
[Hans van Dam]:
15:55 – 16:01
Demos chatbots with buttons can be very helpful and very persuasive.
[Hans van Dam]:
16:01 – 16:13
So it’s good to have buttons but it sort of depends on the use case and you know, if you want to push the limits of conversation design, I will you know was try and go without buttons and see if you can solve it that way.
[Hans van Dam]:
16:14 – 16:14
Yeah.
[Ryan Lester]
16:14 – 16:21
I think your point is a good one to of you can introduce bias with your buttons of see, you know, three out of your drawer positive.
[Ryan Lester]
16:21 – 16:34
You might be biasing your data to say, hey, everything’s great or whether this is the only thing customers want to do when in reality there may be other use cases that are interesting but you’re not promoting those use cases by kind of driving people with buttons.
[Ryan Lester]
16:34 – 16:38
I think your your points are going to have to be selective as to where and how you use it.
[Ryan Lester]
16:38 – 16:55
The one of the topic I want to spend some time on is you’ve touched on this earlier, but I want to tease out a bit more about kind of emotions and I think one thing that you have to be cautious about but is an interesting opportunity is how you deal with emotions and conversationalist design and customer service.
[Ryan Lester]
16:55 – 17:06
Can you spend a little bit time talking about when you know the work you guys are doing how you can make sure the emotional element it doesn’t get lost or what an opportunity to deal with emotion and conversational design.
[Ryan Lester]
17:06 – 17:07
Yeah.
[Ryan Lester]
17:07 – 17:14
So I mean the questions always that we got is to do users care about empathy.
[Hans van Dam]:
17:14 – 17:29
Right and usually, you know, people say I don’t want to bought the Cesar it’s say sorry and apologize because I know it’s a but but still, you know users love empathy and they love it when the body’s response to like an emotional way.
[Hans van Dam]:
17:29 – 17:35
It’s the same way that your coffee machine in your office says sorry when it’s broken, right?
[Hans van Dam]:
17:35 – 17:38
It feels good when a machine apologizes and it just
[Hans van Dam]:
17:38 – 17:39
She’s our brain.
[Hans van Dam]:
17:39 – 17:47
So yeah dealing with emotions is really important and it’s crucial to creating good bot experiences.
[Hans van Dam]:
17:47 – 17:54
So what we do in general we have a bought score card that allows us to sort of assess chatbots and voice assistance.
[Hans van Dam]:
17:54 – 18:09
We do that based on personality natural language empathy helpfulness and persuasiveness and empathy is always a tricky one users are complicated right ad you can cut that out.
[Hans van Dam]:
18:09 – 18:09
It was weird.
[Ryan Lester]
18:09 – 18:12
Yeah.
[Ryan Lester]
18:12 – 18:13
That was f****** weird.
[Hans van Dam]:
18:13 – 18:13
Yeah.
[Hans van Dam]:
18:13 – 18:29
So users say they don’t want empathy but they do want it and it’s important that they get it because it’s the only way to keep them active and empathy isn’t just saying, I’m sorry, but empathy is showing that you understand the user and his context.
[Hans van Dam]:
18:29 – 18:38
So without using emotions really because you know, if you say, okay, so you’re stuck on a train and there for you.
[Hans van Dam]:
18:38 – 18:39
Miss your flight.
[Hans van Dam]:
18:40 – 18:46
That’s empathy right and you’re not apologizing or addressing talking about feelings whatsoever.
[Hans van Dam]:
18:46 – 19:09
You’re just saying, okay, you know, I understand what’s going on and do user feels great because you really feel like you’re being listened to so it’s really good for you as a bot developer because then if the user confirms that you exactly know what the intent was, right so empathy is really important in intent recognition because if you say, oh so distant that is going up,
[Ryan Lester]
19:11 – 19:14
Hey your audio cut out again.
[Ryan Lester]
19:14 – 19:18
I don’t know why I’m not sure if this is something on my end or not.
[Ryan Lester]
19:18 – 19:20
I don’t think I’m back again now or not.
[Hans van Dam]:
19:20 – 19:20
You’re back.
[Hans van Dam]:
19:20 – 19:21
You’re back.
[Ryan Lester]
19:21 – 19:21
Yeah.
[Ryan Lester]
19:21 – 19:22
Yes.
[Ryan Lester]
19:22 – 19:26
Sometimes it just gives me a button that says hey, are you still using this microphone?
[Hans van Dam]:
19:26 – 19:30
And then I say yes, and then carries on its own.
[Ryan Lester]
19:30 – 19:35
Is that a GoToMeeting thing that comes up or is it something else?
[Ryan Lester]
19:35 – 19:37
No to go to meeting thing.
[Ryan Lester]
19:37 – 19:43
All right, go to meeting is our product and I use it because it’s our product but I may switch to something else.
[Ryan Lester]
19:43 – 19:45
I haven’t I haven’t I haven’t issues in general.
[Ryan Lester]
19:45 – 19:52
I mean go to means that design for webinars, but I use it because it works well, but in any case, I don’t know why it’s doing that to you.
[Ryan Lester]
19:52 – 19:52
So it’s frustrating.
[Ryan Lester]
19:52 – 19:53
I apologize.
[Ryan Lester]
19:53 – 19:54
Nah, that’s okay.
[Ryan Lester]
19:54 – 19:56
What did I where did I go?
[Ryan Lester]
19:56 – 20:06
So you were saying that like someone’s on a train and it’s good for you to acknowledge what their issue is, but I think it’s a good point.
[Ryan Lester]
20:07 – 20:11
So I think you kind of end with like so you finish that story and now it’s kind of
[Ryan Lester]
20:11 – 20:13
So what’s the point of as you’re a designer?
[Ryan Lester]
20:13 – 20:16
You should talk about does that make sense?
[Ryan Lester]
20:16 – 20:17
Yeah.
[Ryan Lester]
20:17 – 20:17
Yeah.
[Ryan Lester]
20:17 – 20:17
Sure.
[Ryan Lester]
20:17 – 20:21
Yeah, so empathy is really important.
[Hans van Dam]:
20:21 – 20:24
And as a designer, you always need to be aware of it.
[Hans van Dam]:
20:24 – 20:34
So it’s perfect for intent recognition and getting to use it to confirm that that’s in fact what’s going on, he feels understood, you know, which dialogue to run so it’s perfect for that.
[Hans van Dam]:
20:34 – 20:37
But then you can take it to a whole new level.
[Hans van Dam]:
20:37 – 20:48
So what we’ve developed with the psychologists on our team is called the escalation prevention model and what it means is that there’s negative emotions and they can lead to undesired Behavior.
[Hans van Dam]:
20:49 – 20:52
So someone that’s fearful can become inactive.
[Hans van Dam]:
20:52 – 21:03
So someone that’s you know, dealing with and financial institution and they sort of get fear because they don’t understand it and what’s going on in the process too difficult.
[Hans van Dam]:
21:03 – 21:05
So they become inactive.
[Hans van Dam]:
21:05 – 21:09
These are the people that Stop opening their envelopes and the mail just piles up.
[Hans van Dam]:
21:09 – 21:11
So what do you do in a situation?
[Hans van Dam]:
21:11 – 21:19
Like that and we just have copy writings techniques that you can just use to sort of prevent the undesired behavior from happening.
[Hans van Dam]:
21:19 – 21:27
So action perspective is is very important here and you want to depersonalize the situations a lot of the time.
[Hans van Dam]:
21:27 – 21:51
So when you’re dealing with a user that maybe his account was shut down because he didn’t pay the bill you want to depersonalize so you don’t want to say you got shot down because you did not pay your bill you want to say well when we don’t get the money at the end of the mount at the month when we don’t get the money at the end of the month accounts automatically get shut down.
[Hans van Dam]:
21:52 – 21:54
What’s your what’s your zip code?
[Hans van Dam]:
21:55 – 21:56
I can look into it for you.
[Hans van Dam]:
21:56 – 22:03
So these are really psychological tricks that you can use and to address emotions and to deal with it.
[Hans van Dam]:
22:03 – 22:11
Somebody said that’s very angry can get can become revengeful, you know, so maybe something went wrong with the company and
[Hans van Dam]:
22:11 – 22:18
You’re going to post basment bad messages on social media on your Facebook wall and you’re going to trash you and take revenge that way.
[Hans van Dam]:
22:18 – 22:19
So how do you deal with that?
[Hans van Dam]:
22:19 – 22:28
You know you apologize you use positive framing that puts them in a different state of mind and again action perspective.
[Hans van Dam]:
22:28 – 22:31
So yeah emotions are really important.
[Hans van Dam]:
22:31 – 22:38
You can’t ignore it and they work that’s the only way to keep users engaged and to get them through the process.
[Hans van Dam]:
22:39 – 22:59
So I would say everything in conversation design is emotional but emotional doesn’t mean to just say sorry, you know, it’s just addressing the softer side of the brain to keep them activated and to keep them motivated and to keep them going through to keep them interacting with your chat butterflies assistant.
[Ryan Lester]
22:59 – 23:11
And yeah, I’d want to I really like that you’re saying is that I’m taking away of this too is the fact of it’s about like clearly stating the problem in the sense of I’m hearing what you’re saying.
[Ryan Lester]
23:11 – 23:14
And I’m going to rearticulated to you in a way to your plan.
[Ryan Lester]
23:14 – 23:17
That’s empathy thing of you know, like your account is turned off.
[Ryan Lester]
23:18 – 23:38
Here’s why we believe your account is turned off factually based not sorry to hear your counters off that doesn’t help them solve their problem but rearticulating it but doing it in a way that the bot can then verify and then move the move the problem forward to hopefully a better outcome and to your point if you’re doing that with a bot where a bot is it’s like will do everything.
[Ryan Lester]
23:38 – 23:44
So the better you can design it in a way that we articulates the problem back to the user.
[Ryan Lester]
23:44 – 24:05
So for verification, is this the intent is this really what they’re trying to do, but then also helps them to understand what here’s what I’m going to do next with this problem and doing in a way that’s clear has a flow and keeps the the user comfortable that we’re moving them towards a better outcome when they’re probably coming in dissatisfied or upset because of the fact that they had a problem or they have some issue.
[Ryan Lester]
24:05 – 24:11
So I think this is a really great way of thinking about how you kind of do conversational design.
[Ryan Lester]
24:11 – 24:15
Yeah, and I also think yeah, I think you actually rephrase that very well.
[Hans van Dam]:
24:15 – 24:25
But you know, a lot of companies are like obsessed about you know, sentiment analysis and they invest a lot of money into understanding the users emotions.
[Hans van Dam]:
24:25 – 24:30
But you know, you don’t need sentiment analysis to understand that somebody’s upset when the house burns down.
[Hans van Dam]:
24:30 – 24:31
Right?
[Hans van Dam]:
24:31 – 24:48
So it’s much better to take those resources and investment in conversation designed really address the emotion instead of you know, investing it in shiny technology that does not necessarily do you any good because you know uses a pretty easy to predict when there’s a negative experience.
[Hans van Dam]:
24:48 – 24:54
They’re upset deal with it, you know and design conversations in such a way that they feel better and the technology works better.
[Ryan Lester]
24:55 – 25:04
Yeah, absolutely and at the end of the day, you know, they care about your empathy but they really just what their problem solved so so you can say sorry a hundred times if you’re not solving their problem doesn’t really matter.
[Ryan Lester]
25:04 – 25:06
Yeah, that’s a good point too.
[Ryan Lester]
25:06 – 25:11
Yeah, so I wanted to just think there’s a number of really
[Ryan Lester]
25:11 – 25:13
Things you touched on and I really appreciate it.
[Ryan Lester]
25:13 – 25:16
And I really like the fact that we’re focusing on the user.
[Ryan Lester]
25:16 – 25:30
We’re focusing on the experience, which is so important what touches it’s the beginning but I know there’s an academy conversation Academy that you’re working on so you could tell us a little more about that and how folks can find out more about building their own conversational design expertise.
[Ryan Lester]
25:30 – 25:31
Yeah.
[Ryan Lester]
25:31 – 25:31
Perfect.
[Ryan Lester]
25:31 – 25:32
Thank you.
[Hans van Dam]:
25:32 – 25:33
Yes.
[Hans van Dam]:
25:34 – 25:49
So what what what how it started is that we read we start out as an agency and I once wrote a blog post that said we train our own people in our own Academy and then all of a sudden from all over the world people are sending me emails and asking to get in on Dad Academy and please teach us.
[Hans van Dam]:
25:49 – 25:51
So that’s a good sign.
[Hans van Dam]:
25:51 – 25:51
Right?
[Hans van Dam]:
25:51 – 25:54
So we thought you know, maybe we have to do something with this.
[Hans van Dam]:
25:54 – 26:02
So we started out doing webinar series and we trained people from all over the world and it’s been a great experience, but it doesn’t scale obviously.
[Hans van Dam]:
26:02 – 26:11
So we’re now putting together a lots of video content and it allows people to just really get trained and to get a certificate
[Hans van Dam]:
26:11 – 26:20
As a conversation designer, so it’s really it’s about 10 hours of video where every after every class.
[Hans van Dam]:
26:20 – 26:21
There’s an exam.
[Hans van Dam]:
26:21 – 26:24
There’s little exercises that you can do little quizzes.
[Hans van Dam]:
26:24 – 26:45
So takes you from really understanding natural language and Cooperative principles Etc to Persona development scenario development conversation designed for service conversation design for seals and persuasion conversation designed for managing and managing emotions optimization Etc.
[Hans van Dam]:
26:45 – 26:51
So just takes you through all those steps and it’s going to teach you all these little copywriting techniques that you can then apply.
[Hans van Dam]:
26:51 – 27:00
So that’s the conversational Academy that we’re going to launch in January and and for larger companies that have larger conversation design teams.
[Hans van Dam]:
27:00 – 27:06
There’s actually a subscription model and we’re just going to continue to add content to that platform.
[Hans van Dam]:
27:06 – 27:11
So it’s been going to teach you how to apply conversation design for
[Hans van Dam]:
27:11 – 27:20
A certain platform or also how to deal with trust and AI so we’re going to have guest lectures from people doing that on our platform.
[Hans van Dam]:
27:20 – 27:22
So that’s the product that we’re going to launch in January.
[Ryan Lester]
27:22 – 27:24
We’re really excited about it.
[Ryan Lester]
27:24 – 27:25
Yeah.
[Ryan Lester]
27:25 – 27:26
Yeah, that’s crazy.
[Ryan Lester]
27:26 – 27:27
I think it sounds awesome.
[Ryan Lester]
27:27 – 27:46
And I think the other thing it’s need to me about this is that there’s got two parts of this is one you guys are doing a great job of kind of creating that Baseline content that’s very digestible easy-to-access helps you with kind of those key capabilities you need to be thinking about but then you know, this space is moving so fast and the Technology’s moving and we’re learning so much.
[Ryan Lester]
27:46 – 27:53
I think it’s also great that you guys are going to continue to invest and people can kind of go more that subscription model or more that continuous Improvement model.
[Ryan Lester]
27:53 – 27:55
Whereas people are deploying things in their learning.
[Ryan Lester]
27:55 – 27:59
They can capture those insights in real-time learn from new experts.
[Ryan Lester]
27:59 – 28:06
So I think this will be you know, you guys are certainly think in the bleeding edge or in the early leading aspect of this space.
[Ryan Lester]
28:06 – 28:11
I think it’s a really important one so I certainly am myself excited to see this
[Ryan Lester]
28:11 – 28:13
Yeah, well, thank you so much.
[Hans van Dam]:
28:13 – 28:23
Yeah, the way we look at it is that everybody’s focusing on technology and you know for us it looks like everybody’s you know building Hammers and we’re the only ones training carpenters and yourself.
[Ryan Lester]
28:23 – 28:33
There’s a great need for it in the market and it’s time we sort of start making technology more useful and talk about value and really make it, you know relevant for users.
[Hans van Dam]:
28:33 – 28:38
So that what we try to do is like we want to be to scrum of conversation design.
[Hans van Dam]:
28:38 – 28:49
So everyone that goes in the air a chatbot or a voice assistant sort of go through us and get basic training of really learning how to use psychology and copywriting to make it all work a little better.
[Hans van Dam]:
28:49 – 28:50
Yeah.
[Hans van Dam]:
28:50 – 28:51
Sounds great.
[Ryan Lester]
28:51 – 28:53
I love the vision and it looks like you guys are well along that way.
[Ryan Lester]
28:54 – 28:57
Well, hon, so thank you so much for the time.
[Ryan Lester]
28:57 – 29:01
I’ve certainly have enjoyed our discussion a lot of great topics and ideas to take from here.
[Ryan Lester]
29:01 – 29:06
I’m really excited for you guys are going to go as we head into 2019 and thank you so much for the time.
[Ryan Lester]
29:06 – 29:09
No, thank you so much for having me really enjoyed it.
[Hans van Dam]:
29:09 – 29:10
Thank you.
[Hans van Dam]:
29:10 – 29:11
Yeah, my pleasure.
[Ryan Lester]
29:11 – 29:14
And for those are listening, we also will do a blog post on this as well.
[Ryan Lester]
29:14 – 29:18
We can post some additional information from Hans and his team on where to find out more.
[Ryan Lester]
29:18 – 29:25
Thank you again for joining us this week on AI in real life, and we look forward to our next podcast next week.

Discuss / Read Comments

Leave a Reply

Leave a Reply

Explore our other AI Insights or Recent Posts.

Subscribe to the Bold360 Blog

Submit your email to get updates right to your inbox.