Content + AI

Lisa Jennings Young Over the past five years, Lisa Jennings Young has pioneered the adoption of AI tools in content-design practices at Twitter and Microsoft. Lisa has watched in real time the realization of the benefits of natural-language AI tools to help govern and create content, as well as to assist with content-design research and operations. We talked about: her pioneering work with AI when she as at Twitter her thoughts on the important role that natural language processing (NLP) plays in content-design governance now natural language generation (NLG) can help content designers how she sees NLP and NLG helping her scale content-designer operations the principles that guide the implementation of AI at Microsoft: is it good for Microsoft? is it good for individual teams? is it good for our customers? how her work aligns with Microsoft's strategic objectives some of the work that content designers do that she doesn't see AI replacing anytime soon: stakeholder alignment, customer research, journey mapping, content ecosystem analysis, etc. how implementing AI tools has resulted in new communications opportunities with cross-functional partners the importance of prompt engineering skills her hot take on AI and content design: "It's not about replacing writers, it's about affecting them. So AI won't replace writers, but writers working with AI will replace writers working without AI." Lisa's bio Lisa Jennings Young is the Head of Content Design for Microsoft Teams. She has over 20 years of experience creating content strategies that scale, with a passion for bringing life and voice to digital products. With extensive experience in process design, tooling, writing AI, and content moderation, she helps teams do more than write digital interfaces. She helps them create human experiences. Before heading up Content Design for Microsoft Teams, Lisa was Head of Content Design at Twitter. While there, she built a team that set a global example for how social media can be more inclusive, accountable, and equitable for everyone. When not spending time with her husband and four kids, Lisa loves to read nonfiction, tend her Oakland garden, and cook for crowds. Oaktown Spice is her home away from home. Her spice game is on point. Connect with Lisa online LinkedIn Video Here’s the video version of our conversation: https://youtu.be/gVFsTiSuxWs Podcast intro transcript This is the Content and AI podcast, episode number 8. Few people have had as good a front-row seat as Lisa Jennings Young to see the emergence of AI tools for content-design practice. First at Twitter, where she pioneered some of the earliest use of natural language processing tools in a content-design operation, and now at Microsoft, where she leads a team of content designers and technical writers, Lisa has led the way in showing how AI technology can both help content professionals and democratize writing skills for non-experts. Interview transcript Larry: Hey everyone, welcome to episode number eight of the Content and AI podcast. I'm really happy today to welcome to the show, Lisa Jennings Young. Lisa is a principal content design director at Microsoft Teams, and welcome to the show, Lisa. Tell the folks a little bit more about what you're doing these days. Lisa: Thank you so much, Larry. It's great to be here. So yeah, so I am at Microsoft Teams right now, leading content design for that product. I've been there six months. I resigned from Twitter last November, so almost a year now. And yeah, I've been settling into Microsoft. It's a huge company, getting to know the lay of the land, really connecting with my amazing team there. So yeah, so it's been a good six months. Larry: Yeah, that's interesting. I think when we talk historically, I think of you and I were just chatting a year and a half ago at Confab, and it was just a normal conversation about work stuff and things. And then we connected again earlier this year in February. I put together a panel for Tracy Playle, that Utterly Content, about AI. And you were the first person I thought of for that panel, because you've been working with AI tech, and you had been doing stuff at Twitter, and I know you're doing it again at Microsoft. So anyhow, I just want to observe that our relationship over the last year and a half has been a microcosm of all the craziness we're all going through, watching this stuff evolve. Lisa: Yeah, we were just having a casual conversation and things changed. Larry: Tiny bit. Yeah. But the thing that's been a steady across that is your interest in, and use of, AI. I don't know, maybe talk a little bit about the stuff that you and Jordan had done at Twitter, because that was really interesting and promising. Lisa: When I first started at Twitter, one of the things... Because my career started as a tech writer. Then I moved into content strategy, enterprise content strategy, marketing websites, etc, etc. And so I've always been really interested in how you work at scale. I had usually been a team of one, a content strategist of one or a content designer of one. And how do you really make an impact? So one of the first things I did when I joined Twitter was I put together a proposal for bringing in this AI platform I had heard about right before I left Advent Software called, at the time it was called Cordoba, and they've since rebranded as Writer. Lisa: But yeah, that's one of the first things I brought in, because I really wanted to, we actually were a very small team then, there was two of us who were working on the consumer side of Twitter. How could we do that at scale? And I was very intrigued from content, brand adherence... At the time, there wasn't Gen AI, there was one type of writing AI, this was back when I started Twitter, which would've been four, five years ago? Oh my gosh. Lisa: And it's natural language processing. And especially at a place like Twitter, the words are at the center of the design. And we learned that over and over. And when you're at the center, everything is magnified like a thousand times. So I've always been fascinated by, and intrigued by, and motivated by, how do we ensure that the words we craft so carefully remain intentional, consistent, and relevant over time? Lisa: So it comes down to governance, content governance, and how we can achieve that singular consistent brand voice at scale. So at the time, the role of AI in Twitter's content design practice was brand adherence, enforcing our brand guidelines. A way to ensure that consistency and cohesion over time, so that whoever writes the copy for the next experience just doesn't have to start from scratch. I mean, you're talking about all the user research you do, the drafting, the revisions, the experimentation. You don't want to lose that. So at the time, writing AI for us, again, was natural language processing, or NLP. Lisa: So NLP is that branch of artificial intelligence concerned with giving computers the ability to understand text and spoken words in the same way people do. At Twitter, we used it like we're doing at Microsoft now, to keep our writing on brand and ensure our guidelines, ensure we can enforce them across all those touch points of of microcopy that can make the digital experience. Lisa: So when you're working on a global... It's like the one constant, it does come down to build on our successes, rather than starting from scratch each time. So that's the NLP part, kind of basically where we were when we were at Confab the last time, is what we were talking about. Larry: Well, and actually, you're reminding me even before that, I think it was at Lavacon about the time you started at Twitter, but I think I saw a Cordoba demo, and they likened it to a writing coach standing over your shoulder going like, "Oh no, that's not how we say that here." And that's NLP in action. It understands what you're doing and says, "Well, actually we do that a little differently." But I gather you were just going to talk about the other thing that's kind of been more in the headlines lately about AI. Lisa: Yeah, and it's funny, because when we were talking last Confab, the way I was presenting writing AI was like, "Hey, we as content designers aren't using NLG, Natural Language Generation." This, again, this is over a year ago. And at the time, it didn't have the research insights, and I still believe this today, when you get to content design, AI doesn't have those research insights. It doesn't understand our product strategy, our business goals, our user needs, which is why writing AI won't replace content designers for absolute sure. Lisa: It's not aware of our content formats at this time, or our surfaces, or of our cultural zeitgeist. But since that time, and I don't know, the audience probably knows NLG, but just in case not, NLG is that branch of AI that produces natural or spoken language from both structured and unstructured data. And so again, so at the time, I had a different perspective on AI, and it's evolved over the year, and I really see now that I've been in it into it for a while, how it can really give writers that boost. Lisa: It's like having the jet pack on your back, and that's because of the structured and the unstructured. So for example, at Microsoft, we'll be using it not only for the rewrite, simplify, shorten, which is great when you're working in tiny boxes, five characters or two words can make a huge difference. But also for that structured part, we were able to work with and build our own custom templates, so we can feed it the inputs and the outputs ,so that when, for example, there's absolutely more writing than my help team can do. Lisa: That's one of the exciting things that I do love about Microsoft, is I get to have work with content designers and help and support.

Claudia Francesca Mueller At Trusted Shops, Claudia Francesca Mueller and her colleagues have built an AI-powered chatbot called Piuma that lets non-writers access content guidance through a natural-language interface. It took just a few weeks to launch the initial version of Piuma, building the chat interface with Voiceflow and using the LangChain development framework to access both their content design guidance and OpenAI's API. Even though the chatbot's functionality matched their users' expectations almost perfectly, they still find that they have to constantly collaborate with their partners to fully understand their needs and communicate the benefits of the product. We talked about: her work as a content design and localization lead at Trusted Shops Piuma, the AI chatbot they have built at Trusted Shops how Piuma arose from research and discovery work they did around how to best share their content-design guidance how they developed Piuma using Voiceflow with guidance from a conversational design expert the learning curve around incorporating LLMs into a chatbot like Piuma how they decided which parts of their voice and tone guidance to include in the chatbot how Voiceflow works with the OpenAI and Langchain the need to sometimes adjust the source documentation that the LLM is consulting to get the answers you want in the chatbot how her multilingual background helps her understand computer languages the challenges of getting designers to adopt a new tool like Piuma her ongoing communication with designers to understand their needs and how to address them how she balances evangelism and outreach with collaboration around improving Piuma the tendency of humans to stay with familiar patterns and routines Claudia's bio Claudia Francesca Mueller is a multilingual content designer living in Amsterdam. She speaks Swiss-German, Italian, German, English and Dutch daily, and feels at home when languages are mixed up in one sentence. That’s how she has also learned to bridge culture gaps with style and the right tone. Her love for languages, words, culture, shapes and colours brought her to content design. A discipline that became her passion and that she loves to live as an expert, leader and coach. Her background and career in multiple content roles have strongly shaped her thinking. She believes content is a holistic discipline where words are only one of many tools to convey a message. Currently, Claudia works at Trusted Shops as Principal Content Design and Localization. Connect with Claudia online LinkedIn Video Here’s the video version of our conversation: https://www.youtube.com/watch?v=43688rk97rc Podcast intro transcript This is the Content and AI podcast, episode number 7. On any one digital product team, there are never enough content designers or UX writers. So when interaction designers or engineers have to write interface copy, they typically have to consult content-design documentation. AI creates new ways to share this kind of content guidance. At Trusted Shops, Claudia Francesca Mueller and her colleagues have built an AI-powered chatbot that lets non-writers access content guidance through a natural-language interface. Interview transcript Larry: Hi, everyone. Welcome to episode number seven of the Content and AI podcast. I am really delighted today to welcome to the show Claudia Francesca Mueller. Claudia is a multilingual content designer and a localization lead at Trusted Shops. Welcome, Claudia. Tell the folks a little bit more about what you're doing these days. Claudia: Hi, everybody. Thanks a lot for having me, Larry. As you said, I'm a content design and localization lead at Trusted Shops. Trusted Shops, for the ones that don't know what Trusted Shops is, it is a German e-commerce software as a service company. We certify shops. And if you're a trustworthy shop, you will get a badge and you can start collecting reviews. We offer a review system management to the customers or shop owners. And for the consumers, we offer a buyer protection. And I'm part of a UX team at Trusted Shops. We are seven designers at the moment. And in the content localization team, we're five people. Claudia: Together, I do the math, we're around 13, 14, 15 people in the UX team. And I'm responsible for the content design craft at Trusted Shops. I jump into, let's say, projects that have a high impact on business, but I am also responsible to develop the craft. That means helping others in the team to write UX copy. One of the things that actually was part of this lately was developing a UX writing body called Piuma. That was one of the projects I worked on it this year. I can tell how we came actually to build Piuma the chatbot. Larry: That's why I wanted to have you on. And also, something you just said, we talked about this a little bit before we went on the air, but your official title is principal content designer at Trusted Shops. And I think what you just described is a classic principle role that, "Hey, there's this new thing. Got to do it. Somebody super experienced has to take this on." I just wanted to get that back in there because it sounds like you're genuinely doing principal-level work. But I'd love to hear the origin story of Piuma, especially the name. Claudia: Piuma is my cat. And she's always here in my home office. And when we started working on this project, and I worked together with a lovely technical writer in our team, I said, "Well, we need a name." And he said, "Well, we just call it like your cat, Piuma." And I was like, "Yeah, that's a good one because I really love Piuma and she's always here." That's how we actually got a name for the project, but also for the chatbot. And the whole idea of this chatbot ... Well, I have to go back in time a little bit because when I started Trusted Shops, we were talking about consistency. There was no consistency. There were a lot of voices, casual, funny. You could see whatever you wanted to see just in our content, in our UI. We thought, "Well, we need consistency, so let's develop a voice and tone guideline." Claudia: And that's also what we did. But after just doing all this work that actually took a year because, as I said, I have other tasks, that was just side project, we implemented those, so this voice and tone guideline, in the design system, in the existing design system, so we could call it content and design system. Also, actually for advocacy reasons, of course, when it comes to content design. The next step was like, okay, so now we have this documentation, but it's just a documentation, so how do we get people using this documentation? Because we all know it's not really attractive to have a documentation lying somewhere. And people just forget about it. How can you do that that just designers that actually are busy mostly with other things, more the visuals, how can we get them using this documentation? We thought about a lot of different softwares and we involved the designers as well in this process. Claudia: We thought about Ditto and Frontitude. And somehow, all of these softwares were not convincing. Designers were like, "Yeah, we don't know. It seems like a lot of work." And so we were like, "Okay, so if this software are not the solution or are not actually what you need in your daily life on your daily work, let's find something that works for you." We did a survey and we did research with the designers and OpenAI came up. One of designers just said literally, "Wow, it would be so great to just have a plugin in Figma and we can just ChatGPT." And then I was like, "Hmm." And then at the same time, I saw somebody from Expedia that was posting on LinkedIn about a chatbot. And I was like, "Okay." I just combined ... I was just making the connection. Just have our documentation as a knowledge base and data that we can use actually for the chatbot and we build a chatbot in Figma. Claudia: That's actually how this whole idea started on this project. And everybody was like, "Oh, yeah, that's such a great idea. Let's do this." Of course, there was missing knowledge in this whole project that I couldn't fill because I've never worked ... I've never built a chatbot. I know OpenAI, yes. I slightly knew what the LLM is, but how do we connect this data? How do we get a chatbot, the user interface? We needed an expert. And luckily enough, I had one at hand here in the Netherlands and a conversational designer expert. And so we asked her, "Would you be interested to help us for this project?" And she was like, "Oh, yeah, that's such an interesting project. I really want to help you." And so we hired her and she helped us with the first MVP and the concept of talk to your style guide. Claudia: And so she recommended to use Voiceflow. That's one of the programs out there. It's a commercial program, of course. Platform that you can use and that you actually ... It's actually really accessible because you're going to work especially on the conversational flow with blocks. And it's really intuitive, so it's easy actually to ... I would say for content designers that are not really technical yet, that you just work on the conversation, let's say. And of course, there's prompt engineering involved because you have to tell, let's say, the LLM and the whole data what it has to do, that you get the answer you want. But still, for starting up with conversation AI, I think, and building a chatbot, it's a great program. We started working on that together also with a technical writer that helped me with the data. It's really easy. Claudia: You just upload a file or website. It's like the most easy you can think of. And then you're just busy actually with the conversation. And of course, when you start working with it, you get curious because you want to know how it works because if you know how it works,

Kurt Cagle, a tech veteran, discusses the rapid AI advancements, open-source impact, and knowledge graph technology. He compares building AI products to a risky endeavor and stresses staying nimble. Topics include LLMs, tokenization, and the democratizing AI ecosystem. Kurt's advice: be aware of AI developments and avoid getting stuck with one technology.

Tane Piper "Leading-edge technology" may not be the first thing that comes to mind when you walk into an IKEA store, but maybe it should be. IKEA is using AI technologies across its vast collection of businesses to deliver better content experiences to its customers. Tane Piper leads an engineering team at Inter IKEA - the business unit that owns the IKEA brand - that is building their next generation of content and artificial intelligence tooling. We talked about: his role at Inter IKEA the scope of AI activities at IKEA how their knowledge graph provides a "ground reality" for the info they share enterprise uses of AI at IKEA how narrowing the scope of models to your own enterprise improves quality and reduces costs the importance of testing implementations of AI technology how their knowledge graph helps connect content across the enterprise - and offers new content metrics and analytics benefits how their systems facilitate content discovery and reuse how he uses ChatGPT to accelerate his business research his thoughts on AI technologies can add a qualitative dimension to content metrics how AI and machine learning practices may reduce the amount of data that enterprises need to collect and store how they are developing prompt engineering skills at IKEA the importance of taking a pragmatic approach to AI adoption Tane's bio Tane Piper is a self-taught software developer with over 22 years of experience. He has worked across a diverse set of environments, from startups and creative agencies to his current role as a Software Engineering Leader at IKEA. Here, Tane focuses on projects that blend content strategy, knowledge graphs, and artificial intelligence. His approach to leadership is centered on teamwork, innovation, and nurturing growth within his team. He enjoys experimenting with a wide range of technologies. He is involved in the open-source community, releasing various libraries over the year, and writing technical articles sharing his findings. When not engaged in software development, Tane can often be found in his garden, a hobby that provides him with a peaceful counterbalance to his professional life. Alongside his wife, he is also dedicated to the ethical breeding of Polish Hunting Spaniels, reflecting their shared passion for animal welfare. Connect with Tane online LInkedIn Video Here’s the video version of our conversation: https://youtu.be/9qX8fUpWFgQ Podcast intro transcript This is the Content and AI podcast, episode number 5. When you think of the iconic furniture retailer IKEA, leading-edge technology may not be the first thing that pops into your mind. But it should. Like most enterprises now, IKEA is exploring the many ways that LLMs, machine learning, knowledge graphs, and other AI technologies can help them sell more furniture and understand their business better. Tane Piper leads an engineering team at IKEA that is building their next generation of content and artificial intelligence tooling. Interview transcript Larry: Hey, everyone. Welcome to episode number 5 of the Content + AI podcast. I'm really delighted today to welcome to the show Tane Piper. Tane is a software engineering leader at Inter IKEA. And that's the first thing I want to ask you about Tane, is IKEA is this big sprawling complex organization. Tell me about Inter IKEA and how that fits in with the overall IKEA brand. Tane: Yeah. Thanks, Larry. So Inter IKEA, as many people know, you go to IKEA, you go to a shop, but what a lot of people don't know is it is actually a franchise system. So, Inter IKEA is the owner of the IKEA concept, so it owns the furniture side, the range we call it, the supply, and also the retail concept, which is where I work. So we come up with the ideas behind IKEA, how the store works, what the concept is when you go to an IKEA store, this kind of Swedishness of it all. And when you as a customer go to the store, you're mostly dealing with franchisees, so somebody who is working with us to build the IKEA brand in a new market. Larry: That's it. And having responsibility for the retail concept of one of the most iconic brands in the world, there's absolutely no pressure in this job, I'm going to guess. Tane: Oh, no pressure. No pressure at all. No. In some way, yes and no. I mean, yes, it's a big task. We are a very big, well-known brand around the world, but in insight when we're working on things, I think we're pretty normal. We talk about pretty normal things day-to-day. I mean, at the moment why I'm here with you today, we talk about things like content and AI and how we can use these to leverage them to improve not only the lives of our customers, they're many people, but also what we do day-to-day. Larry: Great. And that's the thing about AI is it's so sprawling and especially in a big enterprise like Ikea, it's going to be everywhere. Actually, I want to start because where we met, we met a couple of years ago at The Knowledge Graph Conference in New York City and we were talking then about knowledge graphs and knowledge representation and that. And we've subsequently talked about the work that Adam and Katariina are doing up in Sweden with the knowledge graph and all that stuff, but there's so much more going on. Can you talk a little bit about the scope, like there I know that they're doing the recommendation system that's driven by the knowledge graph, but there's so much else going on. Can you give a quick overview of how AI technologies are manifesting at IKEA? Tane: Oh, absolutely. I think in many layers we're looking at it. I think when you think about what AI is, I mean AI is kind of a catchall term for a lot of things. So I mean on one end you have machine learning. So where we're really looking at existing things like lots of unstructured content for example, in terms of an organization, we have lots of things in PowerPoints and PDF files that you can be understood by using something like machine learning. And then, yeah, very much on the other side with generative AI, certainly the opportunities that are there, the future opportunities of doing things like home furnishing recommendations and doing that in such a way that the machine understands the customer context, like the size of the room or where the location where they are. Tane: And can tailor and help to give the right recommendations based on that with that knowledge graph at the bottom. I think that's the thing that when we talk about AI and machine learning, especially with a lot of the LLM stuff that is coming along is we know that's very unstructured, unatributed. So by having that kind of ground reality with knowledge graph, that's really what we are looking to build upon, at least in the area where I work, with content as well. So yeah, I mean, we have a group inside where it's an informal kind of group, but we chat across multiple areas in the business and I think we're all kind of looking at how can we bring AI to different parts of the business because there are different use cases and what use case works for our area does not necessarily work for say supply. Larry: Oh, interesting. Yeah. Well I guess the one that comes to mind immediately for a lot of people, because it's been all the fuss for the last year, is degenerative AI stuff. And the famous thing about that is its proneness to hallucinations and things like that. And when you're running a brand like IKEA, it's really important to not hallucinate, and in your communication, and you talked a minute ago about the knowledge graph as the grounding your information in reality. Can you talk a little bit about that, how you can benefit from, because I'm assuming you can benefit from technologies like generative AI but still maintain your brand and maintain the accuracy of the information you're sharing? Tane: Absolutely. I think one of the things I like that what we've done is we've not necessarily rushed into building a lot of stuff with AI and really going all in with it in many ways. And I think what that's allowing us to do is as an organization and as brand look at what is it we need to do to show going forward that there isn't anything that can harm the brand perception, or harm the brand itself. I mean out there are already things like there's somebody created a model that allows you to create IKEA style manuals for things and it's a specific model to do that. That kind of stuff is very difficult to say what effect it would have on the brand, but I think as long as people understand it's not coming from IKEA. Tane: I think that's the thing is when you put a brand out there like that, the people have a bit more of that brand themselves. So I think that's the thing we have to take away from it. But obviously, there is protection of the brand, and yes we have to look at when we bring these generative AI services in, especially where people will be having conversations with them, putting those guardrails in there that mean that if you're talking to a home furnishing bot or agent, you're only getting home furnishing information. It's not going to give you information on philosophy, or science, or anything like that. It's keeping within the bounds of what should be doing. Larry: Yeah. Well, you mentioned both a minute ago when you were talking about machine learning, the benefits of learning from what you already have, and then as you just mentioned that, that kind of understanding of the world you operate in. So tell me about the relationship between understanding your current ... Because you have not only product information that we all see on the web, but there's tons of information, I forget what you call them, but the folks working in the stores and other enterprise employees at IKEA use. Can you talk a little bit about that ecosystem and how AI and ML interact as you're both understanding and generating content? Tane:

AI is impacting technical documentation through support agents, generative content, and changing delivery methods. Sarah O'Keefe discusses the importance of governance, scalable documentation, generative AI concerns, chat-based interfaces, and trust in online interactions. She also explores AI integration, metadata usage, ethical challenges, and the need for strategic thinking in content practices.

Noz Urbina Modern content projects begin with research to create lifelike customer personas and build detailed customer journey maps. Whether you're on a tight budget or have a team of UX researchers at your disposal, AI can help accelerate and improve the development of these personas and journey maps. Noz Urbina has developed the RAUX (Rapid AI-powered UX) method to help omnichannel content strategists develop realistic personas and craft effective customer journey maps. We talked about: his work at his consultancy, Urbina Consulting, and his learning hub, OmnichannelX the RAUX AI method he has developed to accelerate user research, customer journey mapping, content design, and content development and drafting his simple equation for doling out information in complex content environments how AI can help you aggregate and understand your sources of customer information to help build personas how he looks at customer journeys and journey mapping how content fits into his customer journey maps, and how AI facilitates the tedious work that precedes and informs how to address key customer needs the AI-driven persona-development prompt methodology at the core of the RAUX methodology how to prompt AI agents in ways that mitigate the biases that often come with public data sources how you can query an AI persona that you have developed with the RAUX prompt methodology to help you fill in the details of a customer journey map how LLM's propensity to hallucination is actually a benefit when you're trying to conjure human feelings, questions, and queries how AI lets us all become programmers without becoming coders how AI can help with content creation, especially tasks like brainstorming and drafting the importance of thinking about how to use AI at every stage of the content lifecycle Noz's bio Noz Urbina is one of the few industry professionals who has been working in what we now call "multichannel" and "omnichannel" content design and strategy for over two decades. In that time, he has become a globally recognised leader in the field of content and customer experience. He’s well known as a pioneer in customer journey mapping and adaptive content modelling for delivering personalised, contextually-relevant content experiences in any environment. Noz is co-founder and Programme Director of the OmnichannelX Conference and Podcast. He is also co-author of the book “Content Strategy: Connecting the dots between business, brand, and benefits” and lecturer in the Master's Programme in Content Strategy at the University of Applied Sciences of Graz, Austria. Noz's company, Urbina Consulting, works with the world’s largest organisations and most complex content challenges, but his mission is to help all brands be able to have relationships with people, the way that people have with each other. Past clients have included Johnson & Johnson, Eli Lilly, Roche, and Sanofi Pharmaceuticals; Microsoft; Mastercard; Barclays Bank; Abbott Laboratories; RobbieWilliams.com; and hundreds more. Connect with Noz online Urbina Consulting noz at urbinaconsulting dot com Video Here’s the video version of our conversation: https://youtu.be/svFi95biaSU Podcast intro transcript This is the Content and AI podcast, episode number 3. These days, designing content experiences starts with detailed customer persona development and extensive customer journey mapping. Whether you've got a six-figure budget or you're doing scrappy do-it-yourself customer discovery, AI can help you accelerate and improve your research process. Noz Urbina has developed a detailed methodology that he calls RAUX (Rapid AI-powered UX) to help you develop realistic personas and craft effective customer journey maps. Interview transcript Larry: Hi, everyone. Welcome to episode number three of the Content and AI podcast. I'm really delighted today to welcome to the show Noz Urbina. Noz is an omnichannel strategist at Urbina Consulting, but I know you do a lot of other stuff there too, Noz. Tell the folks what you're up to these days. Noz: Yeah, absolutely. Yeah, as you said, I'm an omnichannel strategist, which involves a lot. It's a lot of customer journey mapping, a lot of stakeholder ecosystems, content modeling, metadata modeling, working with people like ontologists and taxonomists and systems architects to really build full workflows that support omnichannel. Noz: My job is I'm founder and I lead a lot of the projects at Urbina Consulting. I also have founded an organization called OmnichannelX, which was a conference but has been pivoted to a year-round buffet of learning opportunities. We used to do an annual conference, the usual four-day thing. And we found that we weren't going to be able to do physical after COVID. It was just the conference market is too difficult. And we only had one physical conference before COVID, so we never really had a chance to establish ourselves as a physical conference. Noz: We were going to do it online anyway. Why not make it an all year thing where people can come and they can pick and mix and they can go look at things from the archives and the library? We run the podcast regularly there too. It's actually doing a little bit too well because sometimes, what I'm talking in business situations, people go, "Oh, yeah, well maybe OmnichannelX can come in." And I go, "Oh, no, no, no." Urbina are the consultants. OmnichannelX is our learning hub where we try to advance the industry and provide learning resources for all the good people out there. Larry: Well, that's great. It's always good to have a little too much success, so congrats on that. Noz: Thank you. Larry: But hey, the reason I wanted to have you on the show today, this is the whole point of this new podcast is about AI and in particular using how folks are using AI in content practice. Now, my first two episodes were background setting and level setting on the whole field of AI. You're really the first person that I've had on, this is how I want the whole rest of the episodes to be like. You're out there in the world doing cool stuff with AI in your practice today. All that stuff you just mentioned, the customer journey mapping, content muddling, all those things. Tell me how... Well, you have a specific model, I know called RAUX, the Rapid AI-powered UX. Tell me a little bit about how that came to be and what you do with it. Noz: All right. Okay. You got to pronounce the cool way, which is RAUX. Larry: Okay, now I'm on board. Okay. Noz: The RAUX methodology, I couldn't resist the acronym. It's not just for UX strictly speaking. Depending on how you define UX. It's for any type of experience or content design, but it also extends into the early research stages and also the content development and drafting stages. Noz: What we found was that in order to be able to do content design, content strategy properly, we really had to do customer journey mapping. Because if you Google customer journey map, you get some very disappointing diagrams which are aligned with a couple boxes superimposed over it. And so I get a newsletter or see an ad and I click a landing page and I download a thing. And it's just this happy path of contact points and they put some notes on them. Noz: That's really inadequate for content people. If we're really trying to get into the informational needs and the informational journey and requirements of our people, the level of customer journey mapping that we were getting from your usual UX design process was not what we needed. Noz: What we've started doing at Urbina Consulting, because we're an omni-channel consultancy, is we're trying to put together a methodology which works for everybody. You can just use it for designing product, you can use it for designing digital experiences of any kind. We've come up with integration requirements. And for example, we realized that we needed to pull this data from the CRM, so in real time we could show on the website what was happening in the call center. Which is not your usual kind of content requirement, but it comes out through properly analyzing the journey. Noz: But it's a lot of work. What RAUX is about is using AI to accelerate that process. Taking the research you do have or starting wherever you are and using AI at several points in the whole content life cycle from research all the way out to delivery. Larry: Nice. And I know I do a little bit of content modeling and journey mapping myself. And typically, especially in journey mapping, that is one of the, we're all used to these giant grid things. We all work in spreadsheets all the time. But a good journey map is the ultimate, giant deepest spreadsheet you've ever worked with. And there's so many cells to fill and this is what this helps with. Right? Noz: Yeah, exactly. What we like to do is have a decent narrative. We want people to have a story that's told in the first person. We don't do, the user does this and then they click here and then they do that. Because I've literally found this in workshopping. When you speak about the user in the third person, you start to objectify them. Noz: That if you really want to drive empathy in the team when they read the narrative, they should be role-playing in their heads. They should be living the story that this person is going through. That's, the writing of that is a bit of an art. You have to be able to empathize and you have to be able to think in the first person and get yourself out of your own head as the person who might own these assets that are in question or be very close to the problem. Noz: That's a decent amount of work is also the figuring out the questions over time. Our journey mapping methodology at its simplest, you were saying there's all these cells, all these rows. At its simplest, it's literally just that.

Paco Nathan, an AI expert since the 1980s, shares insights on using graphs in AI, structured content benefits, and the tech stack of AI tools. He discusses sequence-to-sequence and diffusion technologies, preferring SSM over LLMs. Nathan also talks about the impact of LLM chat agents on content, the importance of using personal data sets, and detailed task analysis in building AI models. He contrasts AI developments at big companies with the open-source AI ecosystem.

Dan McCreary, experienced in selling AI solutions to executives, discusses the importance of storytelling in making enterprises intelligent and nimble. He uses a jellyfish and flatworm metaphor to visualize competitive environments. Topics include knowledge graphs, micro-personalization, labeled property graphs, and the significance of freeing data from spreadsheets for AI productivity benefits.

Update 11 November 2023: I've talked with a lot of people, both interviews for the podcast and informational chats, over the past few weeks and have made some interesting discoveries. So, in addition to helping us all understand AI and how to use it in our work, I'm adding to this podcast's scope coverage of people working in content roles on AI products. Like any other software, AI products need content strategy, content design, UX writing, technical documentation, etc., and we'll hear from those folks soon. Here's the video version of this episode: https://www.youtube.com/watch?v=5qAfH0_0h5I Episode transcript Welcome to the Content and AI podcast. This is episode number 0, an introduction to the show. This episode is just me talking about my intention and plans. Going forward, it will be conversations with experts on both AI and content practice. My intent with this new podcast is twofold: one, to demystify the family of technologies and practices known as artificial intelligence and, two, to democratize the use of AI across the span of content use cases, everything from research and discovery, to content creation and authoring, to content design, content engineering, and content operations. All the stuff we do. I'll talk to folks in the AI field of course - and at first that will largely be a bunch of old white guys, which in itself points to some of data sampling and bias problems that AI practitioners face. But I'll also talk to a diverse range of content practitioners working in product content, support documentation, conversational design, website content, marketing content, content-marketing content - anyone who's adding AI to their digital content workflows - which is pretty much all of us at this point. We've already seen the applications of AI all over the place: auto correct and auto fill in forms digital assistants like Alexa, Cortona, Bixby, and Siri search engines social media feeds personalized content in advertising and on websites and digitial products recommendations from ecommerce merchants robots on assembly lines fraud prevention drug discovery medical diagnosis generative AI, the computer-generated text, and image, and videos that are flooding your in box and social media feeds We'll go under the hood (or as they say in England, the bonnet, I'm recording this in London) - we'll go under the hood, behind the scenes top look at the scope of AI. Not all agree on the precise scope - but we'll look at topics like: NLP, natural language processing, and its applications in areas like conversation design machine learning - statistical modeling of data - embeddings and vectorization and predicting which words come next knowledge representation - bringing real-world facts to the table, which we're already seeing with practices like retrieval augmented generation (RAG) neural networks - machine-based augmented decision making expert systems - rules-based ways to augment human decision making since the 70s computer vision robotics AI ethics and Silicon Valley hype To that last point, we'll pay attention to folks like Timnit Gebru and her collaborator Emily M. Bender. Timnit Gebru is the AI researcher who was fired from Google for pointing out the shortcomings in their approach. She and Bender coauthored the now-famous "stochastic parrots" academic paper. And one of my early guests, one of those old white guys, a delightful and remarkably accomplished human named Paco Nathan - will help us see the current state of AI through lens of an industry veteran with deep deep deep experience in the technical foundations of AI and a ton of experience in the tech startup world. So we'll try to balance the tech hype coming out of Silicon Valley. But we can't and won't ignore that hype - regardless of its merits, they've got the attention of executives and decision makers and the media, so we'll definitely keep an eye on the the big players in the AI space like OpenAI, Anthropic, and Google's Deepmind, and show you how to best use their products. Finally, we'll keep on the radar screen the concept of art general intelligence (AGI). But my main intent is to democratize AI technology to help content practitioners understand and use AI as expertly and efficiently as possible (edit: and to help content practitioners working on AI products). We've already seen many ways that AI can help content folks: content creation - relieving the terror of the blank page, tedious outline tasks, research, etc authoring, enterprise UX, auto- and assisted tagging, voice, tone, and style governance, creating content variants, repurposing existing content, etc. strategy formulation content design content engineering content operations AI's going to be able to help us across the span of content practice. No matter what kind of content work you do, you'll soon be using AI in any number of ways (edit: and you'll likely be helping to design the next generation of AI tools). Anyhow, welcome to the Content and AI podcast. I and my guests are here to help you navigate this dynamic new landscape and to use AI effectively in your content work. If you're doing interesting work with AI - and your boss will let you talk about it - DM me on LinkedIn - I'm always happy to chat about how we might get you on the show, or just chat about AI.