Voice This! Podcast: Bonus Episode

Conversations with Things with Diana Deibel & Rebecca Evanhoe

Context

Join Millani, Marco, Diana, and Rebecca to explore the book Conversations with Things co-authored by Diana and Rebecca.

Topics include

• [8:00] challenges for conversation designers
• [10:25] language-led mindset
• [14:15] identifying use cases
• [21:35] personality design
• [27:05] and benefits and challenges of co-design.

Bios

About Diana Deibel

Diana Deibel, Design Director at Grand Studio in Chicago, is a Brazilian-American award-winning writer and VUI designer with a background in fictional dialogue. She has designed multi-channel voice-first products, chatbots for healthcare, insurance and HR operations, smart speaker skills, and large IVR systems. She is a national speaker and VUI consultant who has set up voice practices for Fortune 100 companies, among others. In addition to conversational design, she has written and produced for a variety of networks and creatives including “Animal Planet” and “Blue Man Group”. She co-created two TV pilots, now in pre-development with One Bowl Productions, and has had several plays produced with the Modern-Day Griot Theatre Company in Brooklyn (under the name Diana de Souza). She loves learning, puns, and leading workshops on dialogue to help others find their voices.

About Rebecca Evanhoe

Rebecca Evanhoe, author and conversation designer, has been developing technology that you talk to since 2011 at companies like Amazon Web Services, Mobiquity, and Shadow Health. She has created virtual patient characters for chat-based learning games, bots for fun and service, and interactive experiences for Alexa and Google Home platforms. Along with her experience in voice and conversation, she earned an MFA in creative writing. She teaches conversation design as a visiting assistant professor at Pratt Institute, and she leads workshops in a variety of writing genres, from creative to technical to UX. Her fiction can be found in the O. Henry Prize Collection, Harper’s Magazine, Vice, NOON, and Gulf Coast, among others.

Quotes

[8:00] Challenges for conversation designers

Collaboration matters to your conversation design teams

I think there are a lot of things that are inherently tricky about being a conversation designer, and one of them is that it is such an interdisciplinary role. A lot of people tend to naturally have one area that they’re really strong in and other areas that they kind of have to learn or even collaborate with other people to cover.

The importance of process in conversation design

But a big challenge, like as we were writing the book, we started finding ourselves wanting to include more and more about process. Like Originally, I think we were going to dedicate one chapter in a process. And that ended up being two. And I think that is because one of the big challenges in the field is helping businesses understand what they’re missing if they leave out conversation design.

Become a conversation design advocate

And that’s a challenge for individual conversation designers, because it means that you’re inherently in a position of advocacy. So throughout the book, we tried to put in content not just for people to know how to do their jobs, but also like how to advocate for it.

[10:25] Language-led mindset

What a language-led mindset is?

Language-led mindset is where you start by trying to understand what language users are going to, to say, or you know, type or say out loud, to express their needs, and then scripting out how those full conversations are going to go. So it’s really just both a mindset and a process and a series of tools and steps that you would do to make sure that at every part of the design process, you’re not forgetting that what you’re building is a conversation.

What a language-led mindset is not?

I actually had this conversation with a couple UX designers earlier today who are learning conversation design for the first time. And one of them was like, Oh, I worked ahead, I built the happy path. And it was I looked at it, it was all in a flow. And I was like, Oh, really? Okay, well, we’re gonna talk about that. And we immediately talked about how you’ve got to stay out of flows when you’re initially scripting, some kind of happy path. And that’s a lot of this, like a language-led mindset. So that you’re, you don’t inadvertently start thinking about the functionality. And what the system can do, what you’re thinking about is, what should the system do? How should it respond to the human? Because the conversation is really the thing that should be leading all of the technology, because that is the format you’re in.

Identifying use cases

[14:15] Q: How do you know when you’re being approached with an ask that makes sense to deploy a conversational interface?

Diana starts with some key questions.

So the way that I usually start to think about this is, is this something that somebody would want to have a conversation about? Like, the very core of it is this is this conversational at all as a use case, if it’s something that is easier to be looked at, and grok or you know, it’s a tapping mechanism is better than speaking or typing something out, then a conversation might not be the right way to go.

Rebecca works together with clients to understand the root problems and potential interfaces.

a company needs to understand all their channels and where those channels are succeeding and failing, and how something like a chatbot or an IVR system or any kind of voice bot is going to fit into that ecosystem. Companies will come to me and say ‘customers are going to our web site and calling our phone line and we want to reduce the call volume so we need a chatbot on the web site.’ And my answer is always like, it sounds like you just need to improve findability on your web site, you have to make it easier for people to find what they’re looking for and complete the tasks on the web site without spending money on a chatbot.

[17:45] Q: Have you ever had to turn down an ask or request to make something into a conversational interface?

Rebecca’s experience with agency and working for herself.

I know for me, a lot of times when you work as a designer, at an agency or in any kind of consultant role, the SOW is already signed in. So even if you disagree with the use case, you’re kind of locked in. And so it’s really just about like making sure you can meet as many of the business goals or the customer goals as possible, kind of doing the best you can.

But now that I work for myself, I do occasionally not work with clients. Because Yeah, because they’re, they’re a little bit off base or, or they’re just kind of not I mean, I, as you can tell from the book, and also from talks that I give and stuff, I have a real strong point of view on how to make this stuff good, and what it should be used for. And not every client won’t, is excited about, I don’t have a shared vision with every client. So definitely. There’s a lot of viewpoints out there. And I think, you know, I feel like, that’s useful because we’re all learning together as a community.

Diana conducts exploratory user research to help clients decide on the suitable interface and scope of the project.

I think I have the privilege of working as a, as a consultant at a consultancy where I am on the leadership team, part of my responsibility is writing those SOW’s that Rebecca was talking about, with the clients, and a big part of the work we do is helping scope and what that work is going to be and we intentionally do a lot of flexibility building into our scoping because clients tend to come to the studio when they don’t really know what the problem is.

So part of the work that my team does is to help figure out what that problem is, and then what the right solution would be, with conversation design being one of the tools in the toolkit.

So even when I have people coming to me and say, Hey, I have this hypothesis that we should build a chatbot for this. We have the flexibility to say well Okay, let’s go find out. Let’s validate that with users that that’s where they’re going to find the solution, first of all, and that they’re going to use it there and do some initial research work around this. And if it comes back and they’re all in, then yeah, let’s build it. But if it comes back that what’s really going to be useful here is more of a mobile app. But let’s build a mobile app or let’s build a human to human service or something that makes sense for what that problem is.

[21:35] Personality can be straightforward depending on the use case

With personalities, people project or perceive personality naturally, their brains can’t help but do it, so you do have to be really intentional with personality. Knowing that a lot of companies immediately go to we want it to be really unique and quirky and have a sense of humour. But actually it can be pretty straightforward, it doesn’t need to have jokes and colourful language, and sometimes too much of a cheerful or upbeat or in-your-face personality can be really jarring depending on the use case… it’s okay if your personality is boring and straightforward if it gets the job done and is the best for users.”

[27:05] Benefits and Challenges of Co-design

Q: How might a conversation designer meaningfully incorporate their co-creators perspective into their release product, while at the same time taking into account the same co-creators lack of design expertise and their individualistic perspective?

Bringing in co-designers who understand the content

When I approach it, I think that I am the expert in design and in the design process and the structure in which this should go into. But the content itself, I am not the expert in. That is coming from my co designer. And they have to tell me, that’s what they’re bringing to the table, they have to tell me what goes in the format that then I can structure around it.

Their job is not to tell me, the functionality should happen this way. But my job is not to tell them. That’s not how you would say it, you should say it this way. So we have to really, like, collaborate together and define those roles and responsibilities.

Guiding and compensating co-designers

It absolutely results in better products for users. I think it is uncomfortable for companies because they think that it takes extra time, or extra people. And then the other big flag to raise is that co designers also need to be compensated in ways that are not exploitative. So like, don’t give them a gift card, if they’re contributing their lived experiences and doing emotional and cerebral labour for your company. And, and it’s making the company 1000s millions of dollars and they just got an Amazon gift card. That’s exploitation. So it is absolutely where I think design should be going. Well, yeah, I don’t think it’s easy because I think it’s easy to think we know more than we do at all. I fall into that trap a lot. In so in, in some ways, it is a bit of a mentality shift where you’re going from knowing stuff and advocating for it to making space for others, and setting up conditions for them to kind of basically guide them to give fruitful information.

References

• Conversations with Things — By Diana Deibel & Rebecca Evanhoe
• Conversational Design — By Erika Hall
• Design Justice ​​- By Sasha Costanza-Chock

About Voice This! Podcast

Conversations with the people who make conversational AI 🎙️Join Millani Jayasingkam and guests as they discuss voice technology, conversation design, AI trends, and the strategy of creating effective conversational experiences. Tune in for first-hand learnings, insights, anecdotes, and sometimes jokes! Say hi and send us your questions at: voicethispod@gmail.com.

Find us wherever you get your podcasts or Listen on Spotify!