Content Operations

In the second episode of The Uninvited Author podcast series, authors Sarah O’Keefe and Carlos Evia examine how foundational communication theories help structure modern content operations. They unpack how AI adds new intentionality to creating and delivering content, providing the theoretical groundwork creators and leaders need to manage workflow risks and build sustainable AI-optimized content ops.

Sarah O’Keefe: It’s not that you have to go talk to your management or your CEO or whoever you’re dealing with about Umberto Echo, although that might work. It is that this needs to be in the back of your mind so that when somebody pushes back with something that is clearly nonsensical and is just simply not going to work, you can explain why. You have the foundation that allows you to move forward and say, “Okay, so as we’re building out the system, as we’re bringing AI into the equation, here’s where it’s going to do well and here’s where it’s risky.”

Related links:

Terje Hillesund

Marshall T Poe

Umberto Eco

Daniel Dennett

Digital sovereignty in the age of AI

From ad hoc to autonomous: The AI content ops maturity model

Check out other episodes in The Uninvited Author podcast series

LinkedIn:

Sarah O’Keefe

Carlos Evia

Transcript:

Disclaimer: This is a machine-generated transcript with edits.

Introduction with ambient background music

Christine Cuellar: From Scriptorium, this is Content Operations, a show that delivers industry-leading insights for global organizations.

Bill Swallow: In the end, you have a unified experience so that people aren’t relearning how to engage with your content in every context you produce it.

Sarah O’Keefe: Change is perceived as being risky; you have to convince me that making the change is less risky than not making the change.

Alan Pringle: And at some point, you are going to have tools, technology, and processes that no longer support your needs, so if you think about that ahead of time, you’re going to be much better off.

End of introduction

SO: Hey everybody, welcome back. This is Sarah O’Keefe again, and I am here once again with Carlos Evia.

CE: Hello.

SO: And this is part two of our podcast series about the book that we’ve just released called The Uninvited Author. And we want to talk in this episode about some of the core concepts that we used in breaking down how we look at the process of creating, managing, and delivering content and what that looks like. So Carlos, what were some of the key concepts that we that we brought into this discussion?

CE: Well, we were looking at things that were a bit broader than just one type of content. We talk about content a lot in our lives. I mean, you in your work and you do as well in my work from slightly different perspectives, but with a core of what unites our experiences is technical content or enabling content, that content that at the end of the day, you’re gonna read not for entertainment, but when you need assistance, you need information to complete or perform a task. But we wanted this book to be a bit broader than just specific cases about technical or enabling content. So instead of just jumping to the life cycle of technical content, that many versions of that exist. I think you were the one who found this text cycle that came from a professor in Norway. 

SO: Yeah.

CE: And my Norwegian is pretty bad, so I will attempt to pronounce Terje Hillesund. I hope that is correct. We might get some tomatoes thrown at us for mispronouncing this media studies professor’s name. and he does research from where we can tell he’s still active. He does research on digital publishing, especially when it comes to electronic books and EPUBs. So he proposed a text cycle that had some very clear stages. What he calls them stages, right? Or phases? What does he? I think he’s stages.

SO: I’m not actually sure. And also it probably sounded better in the original Norwegian.

CE: We need to do an AI translation of this episode into Norwegian and see how it goes. So those let’s call them stages, this is our adaptation of it, are pretty much life cycle like, but they’re not just specific about one type or one combination of elements of content. So they’re very broad for any type of communication that is particularly being written, but not just delivered in text. We also applied it to multimedia and other digital approaches to text. And we have a whole section in the book saying: what do we mean by text? It’s not just words written on a page, but it can be audio and visual content, anything that is contained in bits and is delivered through electronic channels, even if you at the end of the day get it in a piece of paper that had to come from a file that was printed. So do you want to talk about the stages or should I talk about the stages, whatever you wanna do?

SO: So breaking down the stages. As Carlos is saying, it’s not just text, words on a page per se. and in fact, you could apply the so-called text cycle to spoken communication, which kind of makes me twitch a little bit. 

CE: Mm-hmm.

SO: If you think about this, and of course we’ve got a bunch of images for this in the book, but there are six phases to this text process or cycle. The first one is write, which is really having the idea. Then there’s produce, which is something like writing it down. There’s storing, which, you know, in a digital content world would be parking it in a file or a database. There’s representation. To represent it is to format it and make it look a certain way. And then you distribute it, and finally you read it, or you consume it. Now, most of us, if you’ve ever thought about this, which most regular people don’t have any need to, think about writing and reading. There’s an author; they write some stuff, and then there’s a reader, and they read the stuff. But as you start breaking down this process and thinking about what really goes into that, if you go back to the earliest communication, so now we’re talking about spoken communication. Well, the process of writing, of creating the idea, of packaging that idea of storing it, of representing it, which is to say, to use your words to speak it. And then you use your words also, your voice to distribute. 

And then you’ve got the reader, the consumer, they’re sitting right there listening to you. And so this entire six-phase process is really just two, right? It’s two actions. I speak, you listen. And then all these other pieces that are represented in this text cycle are all embedded in that little two-step process. The minute you introduce actual writing, the process of putting something on a clay tablet or piece of paper, which of course came much, much later, well, now I have an idea in my head, and then I take a pen or a stylus or a chisel or something, and I actually encode that information onto a tablet or we’ll go with paper, right? We put it on a piece of paper. So I’ve now produced it using visible marks, and I’ve stored it on that piece of paper, and I’ve represented it on that piece of paper. But the key thing is that I have not yet distributed it because I haven’t distributed the idea. Now if I hand you the piece of paper and you drive across town and hand it to somebody else, that’s distribution, and then they read it.

SO: And so you can see this process of decoupling the phases starting to happen. And the key thing is when you look at digital content, we decouple more pieces. It gets more and more fragmented, and there are more and more people involved, more and more different roles involved in the process of having an idea, encoding that idea in some way and then representing it in some way and delivering it downstream to the person who finally consumes it. And so that was kind of the fundamental starting point for this book was to look at this text cycle and ask the question of: okay, well, what does it look like to have this text cycle in typically now a digital workflow? 

And now we introduce AI. And when you look at the six phases that we have here, it turns out that you can use AI in different ways at every point in the text cycle. And I think this is why, as authors, as content creators, looking at AI is so difficult because there are lots and lots of different things we can do with it. It’s not just go online, open up a chat bot and ask a question, which is how most people, the vast majority of everybody, that is how they interact with AI. But as an author, there’s a whole bunch of other stuff going on. so did you want to talk a little bit about what it looks like at some of the points in this text cycle to introduce AI.

CE: Yeah, but I think what something that I would like to mention is that we didn’t just use that one lens to analyze how content and communication has evolved based on this life cycle, the the text cycle, to get us to where we are right now working with artificial intelligence. So instead of that one lens, we combine it with other perspectives from different disciplines and particularly from history, we borrow the work of Marshall T. Poe about the ages of human communication. So Poe, who by the way is from Alabama, not from Norway, the develop a framework for studying human communication across history.

So Poe had five ages of communication, which include the age of speech, the age of manuscripts, the age of print, the age of audio and visual media, and the age of the internet. So what we did is to put a Hillison’s text cycle across the ages that Poe documents in his model to expand that and get to propose a new age of human communication that we surprised called the age of human communication with AI. And we were able to I want to say map the stages of the text cycle into what communication looks like now with artificial intelligence. And we start the book in very, I don’t want to say naive, but conservative ways of presenting artificial intelligence as an assistant with a, you know, we understand that people are using AI across the stages of the text cycle as an assistant for writing, as an assistant for producing, storing, and eventually as an assistant for reading, because readers are using AI chatbots and AI agents to consume content. 

And it gets to the point in which as the book progresses and you go to different chapters, and the title of the book I will remind the listeners is The Uninvited Author, because it’s precisely based on the idea that we have the tech cycle with humans, and humans have traditionally been the developers and readers of the tech cycle using machines and tools at different stages of the text cycle, but at the ends, here comes the little cart again outside.

SO: Yeah. Is this what this is? The uninvited cart.

CE: Buy a little cart. It’s the uninvited little cart. So at the end and at the beginning of the tech cycle across all of the ages of human communication in history, there’s a human being and a human being. But now it’s a human being and/or a machine. It’s a fancy silicon machine and not just a mechanical machine, but they are machines. And that has really modified the approaches for developing and interpreting content in this new age of human communication with artificial intelligence. And that’s why we took the liberty of proposing our new age following the model of Marshall T Poe. And a funny anecdote is that I’m gonna reveal all the dirty laundry. When we were writing the book, I heard a rumor that we forgot to include one of the listed stages of the tech cycle, and also one of our very effective and kind reviewers noticed that one of our invented stages of the era, the age of human communication with AI was wrong and we had to rewrite it. But I promise you that the version that was published incorporates all those comments and if you identify any other gaps. We blame it on the AI. 

SO: The worst part about all of this is that because we really limited our use of AI in writing this book, we don’t get to blame the AI for anything. So we’d like to, but sadly it’s all us. So the text cycle, and then we’ve got Marshall Poe. And then, you know, the third thing is because like Norway and Alabama I mean, what’s the average of Norway and Alabama? It’s Italy, obviously. And so we brought in Umberto Echo, who well, most of us probably know about him because he wrote a bunch of very literary detective novels that involved medieval friars, and that was super fun. But he also wrote about communication and fundamentally that as a writer, I am trying to communicate. I have a certain intent in what I’m trying to do. And the reader has maybe a different intent in using a document or in using the content that I wrote. And then the work itself, the document, the podcast, the thing, the article of communication has its own intent. And of course, what we’re finding now is that you add to that the fourth intention, which is the AI, the algorithm sitting inside the AI. Now, AI is not people.

CE: Not people.

SO: AI is perhaps made of people or made of people’s ideas, but AI is not is not people. And it doesn’t have intent in the same way that a human has motivation and some other things. But algorithms have input, and they have processing, and that leads to certain kinds of outputs and outcomes. And so an algorithm can have its own intent in the sense that there’s a certain kind of result that it is pushing towards.

CE: Yeah. And one of the components that I want to mention, and the book is kind of a geeky book because we write about topics related to technology, and that’s true. But it has a very strong humanities core. And humanity is not just…

SO: And really bad puns.

CE: And really bad jokes about people with weird names, but that’s a topic for another episode. I’m gonna completely go in that direction in another episode, I promise you, because at one point the book started as a love story. There are going to be two characters, Margarita and Cosmo, who fall in love, but then we went in a different direction because it was not a fiction book. Anywho, the humanities base of what we analyze in the book, and this is where I want to really emphasize: this is not an AI slop book that was written by AI. It was written by people and incorporating traditions across different disciplines. So we have the historical component; we have the history from Poe, we have the media studies component from Hillesund. And we’re gonna get, and Sarah already talked about it to the semiotic component from Umberto Echo. But from a philosophical perspective, Daniel Dennett, who died a couple of years ago, was a philosopher from Massachusetts. And one of the many things that Dennett wrote in his career was a theory of interpretation that says that we as human beings, when we encounter a phenomenon that we don’t understand, we tend to treat it as if it were a being that has intentions, that has intent. 

So combining the perspectives of Dennett with what Echo wrote about the limits of interpretation and how readers have their intentions when they encounter a text, and here again we go back to text being not just words, that come with intentions from the human authors. Echo was very against the idea of the school of deconstruction; I’m getting super geeky on this. I promise you, I’m not gonna continue on this path. Was a very strange school of thinking that said that anything goes. And if you take a book, you can interpret it to be whatever it is that you want it. If you find a poem, you can interpret it to be a recipe for making cake. And I’m making very stupid examples here. I apologize. 

Echo was very against that. And Echo said, yes, go ahead and interpret things in different ways, but there is a point in which your interpretation of a text is going to be silly and nonsensical. So that’s why he proposed the text itself has its intentions that have the primary purpose of avoiding or preventing that people are going to interpret a chicken recipe to be a love letter. So that’s nonsensical. We don’t go there. If you read the chicken recipe, it has steps. It has ingredients, it has prerequisites, and it has pictures of a chicken that is not a love letter unless you love chickens. But we’re not getting into that by any means. 

SO: Too late.

CE: And that’s what we came up with our contribution of the fourth layer of intentions, which, like we said, if you take a look at how the text cycle in the age of human communication with AI now includes AI agents, AI tools as readers and as authors, they come with their own intentions. And their intentions, not human intentions, are a hodgepodge combination of the training materials that the agents came from, the version of the model that you’re using. If your model is allowed to go out and perform web searches on the fly. If it keeps any record of interactions with the reader. So those are intentions that get imprinted into the text cycle in the age of human communication with AI. And that’s where we really created this prism of different approaches coming from the work that we do in technical communication, but also based on bigger conversations about history and communication studies and philosophy without making it sound too nerdy. I promise you, if you have read the book, you will see that there’s some nerdy elements, no doubt. But we try to make it accessible for our peers, our colleagues, managers in our industry, and not just in technical communication, but people who work across different sectors of content. And have to acknowledge, or have come to terms that machines are now being authors in the text cycles whether they invited them.

SO: it’s important to understand some of this underlying theoretical work and some of these frameworks, because as you move into this as a content creator or as a leader, as somebody that’s responsible for some sort of content, if you don’t understand how these things interoperate and fundamentally how they break down and how you can and cannot break them down, then you don’t have any possibility of actually bringing your AI-based or AI-enabled content operations under control. So it’s not that you have to go talk to your management or your CEO or whoever you’re dealing with about Umberto Echo, although, depending that might work. It is that this needs to be in the back of your mind so that when somebody pushes back with something that is clearly nonsensical and is just simply not going to work, that you can explain why, that you have that foundation that then allows you to move forward and say, okay, so as we’re building out the system, as we’re bringing AI into the equation, here’s where it’s going to do well and here’s where it’s risky. These are the pieces that it will not do well, and you know why. So fundamentally, we weren’t that interested in the question of what can Claude do today, or what kinds of ridiculous things can you make ChatGPT say if you feel like it.

CE: Mm-hmm.

SO: The fundamental question is much more how are large language models put together. And what kinds of things are they going to be good at and bad at? And how do you bring that into a workflow? And how do you understand the risks that you’re introducing and the benefits? So what’s the cost-benefit analysis of having an LLM in your in your process? And, you know, we touched on this at the very top of the podcast when we made some joke about it’s the AI’s fault, right? You know, if there’s a mistake, it’s the AI’s fault. Well, so first of all, it’s not because we didn’t really use much AI, but fundamentally and secondly, we don’t get to disclaim responsibility. if you’re in techcomm or e-learning or anything else and you put out a document and it was 100% AI-generated and then it’s wrong, the organization, I mean you may get to say, well, you made me use AI, it’s not my fault.

CE: Mm-hmm.

SO: But the organization doesn’t get to disclaim responsibility for the document because it was AI-generated. They’re going to have significant product liability. And I believe, on no evidence whatsoever, but I believe that when the product liability lawsuits come, and they will, right? The organization that goes up in front of a jury and says it’s the AI’s fault is going to lose. And I think they’re going to lose more than they would if they said, well, our humans did our we tried our best and we made a mistake, as opposed to, yeah, we offloaded it onto the AI. We didn’t read the results. We fired all the people that are creating content. And we’re sorry that you were horrifically injured in some way. But we weren’t sorry enough to do the work to prevent it, right? So there’s going to be huge product liability. And I think the jury sitting there is going to say, well you tried to save money, you tried to cut corners, and this is the result. And so I believe that ultimately the legal outcomes of excessive AI use are going to be you know, problematic enough to kind of reel people in. 

CE: Mm-hmm.

SO: Now that’s a very US-centric perspective because in Europe there are different regulatory issues. But even in the US with our current general lack of regulation, I think you’re going to see that product liability lever applied to force organizations to do better.

CE: I remember that when we were writing the book, we were in very early stages of the book, you posted to LinkedIn that we were writing the book, and you kinda opened it to people to propose if you were writing a book about AI and content, what would you want to see? And a few of the people who responded to that post were expecting concrete formulas, concrete prompts or recipes for creating agentic AI workflows or what should I ask my chatbot to have good content. And that’s not the book that we wanted to write. We wanted to write a book that will make people we hope think and consider those implications of using AI for creativity, for productivity, and like you said, for legal consequences of delegating everything to the artificial intelligence agents and expecting magic. 

And that’s what I keep going to. I keep saying that the problem is when people see AI as this oracle that is going to just magically solve all the problems without understanding how it works. And it is a monster. AI is applied to mean many different things. And we write about this in the book too. But also, it’s how what are the consequences of bringing AI as an invited component into our professional tech cycles. And by the way, going back to your LinkedIn activity, I think a couple of days ago you published something that said we are not anti-AI, we are anti-slop. And I think that’s something that is reflected in this book. We are not anti-AI. We have a whole section in the book that I think it presents in very good and honest detail how we use different tools that include artificial intelligence in the production of the book, but we were very cautious about avoiding perspectives of presenting AI slop, passing it as human products. There are so many books. If we go back to our main corner of technical communication, there are many books that have appeared on Amazon in the past few months about the DITA standard.

That you can see that no humans were involved in the writing of those books. Somebody just prompted a chatbot and said, go fetch information about DITA. And that’s not the book that we wanted to create. This is not a book with concrete recipes on how to use things with AI. And it is not a book that we delegated to AI. It’s a book written by humans coming from different workplace, practitioners, and academic disciplines, asking questions about what does this mean and how do we go to the next stage and learn to live with these synthetic authors without losing our humanity and without getting in trouble.

SO: And I hope that this book is valuable to the people that are going to read it because it was painful to write. I mean, it hurt. So I, you know, if I’m gonna go through this pain and suffering, then I wish for it to be useful. And if people look at it and say, you know, you could have prompted your way to this with AI, then I’m probably just gonna like curl up in the corner and cry.

CE: Yeah.

SO: So all right, on that cheery note, we will leave it there for this episode, and we will return and talk a little less about theory and a little more about fun things you can do with synthetic content and what that means to our operations. So thank you, Carlos, and I’ll see you on the next one. Bye.

CE: Thank you. Bye bye.

The post From clay tablets to LLMs: Applying communication theory to AI-optimized content ops appeared first on Scriptorium.

Is AI the catalyst that will finally bring content design and content ops together? In this episode, Sarah O’Keefe speaks with Kate Agena, Vice President of Content Design at SAP, about why fluency is cheap while meaning remains expensive in an AI-driven world.

Kate Agena: But users don’t care if content is coming from marketing, product, or whatever: they want whatever it is that they need at the time they need it. If everything is just kind of in one pile of information, that’s not going to come out correctly. So I think ops is just so incredibly important now, and content ops in particular are going to be far more important than they were.

Related links:

KateAgena.com

Paz Parez: Context architecture

Digital sovereignty in the age of AI

From ad hoc to autonomous: The AI content ops maturity model

LinkedIn:

Sarah O’Keefe

Kate Agena

Transcript:

Disclaimer: This is a machine-generated transcript with edits.

Introduction with ambient background music

Christine Cuellar: From Scriptorium, this is Content Operations, a show that delivers industry-leading insights for global organizations.

Bill Swallow: In the end, you have a unified experience so that people aren’t relearning how to engage with your content in every context you produce it.

Sarah O’Keefe: Change is perceived as being risky; you have to convince me that making the change is less risky than not making the change.

Alan Pringle: And at some point, you are going to have tools, technology, and processes that no longer support your needs, so if you think about that ahead of time, you’re going to be much better off.

End of introduction

SO: Hi everyone, I’m Sarah O’Keefe. I’m here today with Kate Agena, who is Vice President of Content Design at SAP and also founder of the Content Design Leaders Membership Community. She has a PhD from Purdue, and in doing her PhD, she studied how tech writers could use iterative development processes to impact software design, otherwise known as, at least to me, basically waterfall versus agile. So she’s got some really interesting background as a tech writer and kind of started out there via I think information development at IBM and then landed in content design. So welcome, Kate.

Kate Agena: Thank you so much, Sarah. Happy to be here.

SO: Yeah, we’re glad to have you and to connect some of the maybe more technical content enabling content side of things to content design. our focus today is actually on that, on the fact that content design and content ops are related, or maybe should be, but somehow aren’t connected. And Kate has a theory that AI is actually going to for once be a force for good and maybe bring these disciplines together. So we should talk about that. But first, give us your definition, your short definition of content design. What is that?

KA: Yeah, so for me, UX content design is a UX design practice, first of all. And it is the practice of designing the information and the language within a product experience so people can understand what’s happening, they can make decisions better, and they can accomplish whatever it is that they’re trying to do.

SO: Yeah, and I think I would argue that content ops is the tooling and the processes that sit underneath that, that this content design process or discipline flows over or inside. so I was reading up on some of your stuff, and I’ve included Kate’s personal website in our show notes. One of the things that you said, and I’ve seen this in longer phrasing from other people, but you had a very succinct definition of this. You said fluency is now cheap and meaning is not. 

So, we’ve said for many, many years, that it is not true that anyone can write. However, it turns out that with AI, if you know, if writing counts as let the AI generate the text, then I guess it is actually true that anyone can write. The problem is that we evaluate content on fluency. If it’s poorly written, if it’s hard to understand, if it’s ungrammatical, we assume it’s low quality. But that isn’t true anymore because AI will always generate something that looks good, looks plausible. So it sounds good, it’s well written for values of the mechanics are correct, but it’s not necessarily accurate. So when you say that fluency is cheap because of AI, but meaning is not. What what is meaning and why is it still expensive?

KA: Yeah. So I mean, for me, I think coming from the techcomm world where, you know, and from rhetoric where obviously I’m always worried about things like audience purpose and context. What is it that the person is needing? What are they trying to do? And then design really makes you think about psychology and you know, where is this in a user’s journey and maybe in the user’s day and additional, you know, a lot of different context around whatever the content is. And that emphasizes so much user research. You understand if you’re, you know, if you have experience doing content design, you have to like, you know, changing one phrase, changing one word can make a huge difference on, you know, even product success, but certainly on how a user reacts to that content. 

And so it’s, you know, it’s very different for an AI to just kind of generate a phrase that has the general meaning, supposedly, that you need in that piece of UI, than to really do all of the thinking about the human context that’s around that. And I think there’s a lot of discernment that happens that a content designer brings in, or even a technical writer brings in to documentation, maybe. 

As they’re kind of interpreting a lot of times what devs have put in, that any tech writer will tell you that they do a lot of work to get maybe specs or you know, JIRA information or a description that a developer gave them into a format that users can actually understand. And with content design, it’s the same that you really have a lot of human context that you need to take into account. And that’s a lot of discernment that I think. You know, you can’t give all of that context to the AI so easily. and if you try to, I think you it’s it’s gonna get lost in the context window at some point.

SO: So then as we’re working through this and we’re saying, well, you know, writing and discernment and humans are more important than ever, you know, I had yet another note from a colleague who’s facing a layoff. And it’s pretty clear that at the individual level, people are losing their jobs because of AI. the AI can do it, we’re getting rid of our entire team. The AI can do it, you’re out. So there are lots of content people looking for work on sort of both sides of this fence that we’re talking about, but there are also new opportunities. So acknowledging that there’s huge disruption and a lot of pain, where do you see some potential and some new jobs and some new specializations evolving?

KA: Yeah, I think there’s a lot. And I I feel like there should be kind of niches that people can find something that feels a little bit closer to their own skill set to move into. In content design, a lot of folks are moving into content systems, which is a little closer to content ops. Also, content ops, I think, should be something that people could be moving into more content strategies, you know, kind of ideas that we would have thought about as content strategy a while back.

So there’s definitely the system side, which is just expanding because now we’re talking about things like SAP calls it a compositional design system that would allow a machine to use that design system to generate UIs on the fly based on user intent. And to do that, you need an awful lot of information to help that machine kind of go through a tree of decision-making.

And find patterns. What are the good patterns for doing this specific thing? How do you understand what the user is actually looking to do? And then things that you know used to be a human would be involved, and so they would bring in all of their human knowledge. You need to encode that into components and things as well. So there’s, you know, kind of system-level voice and tone, personality, behavioral things, but also, you know, on the component level, there needs to be a pattern for what the copy should be on that specific component. So I think content systems is a huge new area. Where, you know, before I think we always wanted to put resource into that kind of work and there wasn’t any appetite for resourcing it. And now it’s kind of table stakes that we need to get there. If they want AI to do these things, we need to have a lot more effort put into content systems and governance. You know, it’s one thing to build it, and it’s another thing to keep it going. 

SO: A bad word.

KA: So content systems, yes, content systems is a big one. A second big one for content designers is model design, or there’s a lot of different names going around for it now. Paz Paris called it model design when she first kind of identified it when she was at Google working on, actually, I think it was working on Bard at the time, before it was Gemini. And that’s work that content designers have been kind of really a natural fit for. So that’s things like system prompts and skills and evals and determining all of that stuff around kind of how the model will behave with folks. so model design is a second one, content engineering people call it, that kind of thing. So that’s a second big one, I think, for content designers. 

I don’t think static UI content design is going to fully go away, but I don’t think anyone will be doing exclusively that. I think there’s a new need that you have to have patterns and guidelines that fit your static UI, but you have to have all of those also articulated for the machines. And then everything has to go together. So I think on the content design side, that’s where most people are trying to learn skills. And then I see this additional area that I feel from my background would be ideal for folks with a tech writing background, which is, you know, you just have such a greater need for structured content and for kind of interpreting what maybe a developer or a data scientist or a PM or someone else, even a designer, articulates as this is the need, and we need this put into clear structured content.

That the machine can read. And I think that there’s a big space for that. Because I also feel like there’s, you know, I mean, I see in SAP, we have a ton of data scientists, we have a huge amount of folks that are working on ontologies and knowledge graphs and things like that. But from the design perspective, I feel like coming from the user’s side of things, there’s probably a gap in between somewhere where there needs to be some kind of like interpretation layer that connects with how the user sees things to how the data sees things. And I have a feeling that, you know, that needs to be designed. It’s not, it’s not objective. And so I feel like there’s a space for designing that level, that’s a new level that I am not sure until we’re really trying these things and finding that we’re not quite connecting. I don’t think companies will realize they need that. But I have a feeling that’s going to come. And I think content folks are best equipped to do that.

SO: So one of the things that sends me into sort of incandescent rage is, you know, we talk about all these content groups and all this investment that’s being done and structured content and all the rest of it. And then you go talk to the AI team and what you’ll discover is that they go over to SharePoint and they grab a bunch of PDFs and they dump them in their LLM. And then they’re like, yeah, we have to figure out how to do the metadata and it’s real challenge. Really, you don’t say. okay, allow me to show you the back end of where these PDFs come from. And they’re like, that looks hard, just I need a PDF-based solution. And then I just start foaming at the mouth, and that doesn’t go well. So I’m still working on that one. 

But as we, you know, as content design, it sounds like evolves a little bit towards systems, which means content ops to a certain extent. And then content ops, you know, needs to connect better with content design because just automating it, see my example of PDFs being dumped, is not actually thoughtful necessarily, and it needs to be done better. So where do you see opportunities for these things to connect via the I guess like catalyst of AI or something?

KA: Yeah, I mean, I think so content designers can bring language, they can bring interaction patterns, they can bring meaning into structured content, terminology, taxonomy, and the context layer. And I think that, you know, all of that needs to go into systems, and those systems need to be scalable, they need that they’re that bad word again. They need to be governed, they need to be maintained. there’s, you know, I mean. We know how difficult it is in any org, I think, of any size to get any kind of handle on all of the content. And there’s this idea that, you know, with AI, you can just like magically throw it all in and it’s gonna come out in some way that makes sense. And that’s, you know, just not going to be the case, I think. so I I think that there’s there’s room already in content design for there to be more content ops.

I think that content designers kind of define what good content experience is. And at this point, to make that scalable, it has to show up in a lot of different places. And there has to be a really complex architecture for that context to be given to the machine in a way that’s going to be effective and efficient. So, you know, there’s this architecture of there’s, you know, system level prompts that are going to apply to everything. There’s skills that need to be pulled at the moment that that specific skill is needed. And, you know, and we’ve got a lot of UX writing skills and things like that. But I think that this like large UX writing skill is not the answer. It’s going to be pretty granular skills that are needed and an architecture to help the machine know when to use which one.

And then evals and also the whole process of doing evals and getting results and doing things that will improve the results next time around. To me, those are all really ops-centered things. And we’re going to need better systems to run all of that. And I think we also are going to need better systems to help deal with those silos and silos of content and disagreement on content, because you know, if a user is interacting with an AI from a product, you know, it’s not so different. I in so many ways nothing has changed. But they don’t care if it’s you know coming from marketing or from the product or from whatever, they want whatever it is that they need at the time. And if you know everything is just kind of in one pile of information, that’s not going to come out. Correctly. So I think ops is just so incredibly important now, and content ops in particular are going to be far more important than they were. 

SO: Mm.

KA: I think, you know, at least in orgs that I’ve been in, that’s been kind of more, you know, there’s marketing content ops, and they have marketing CMS and all of a whole system there, and maybe, maybe also with like experience, like journeys and things like that. So they know all about the customer and what they’ve done and what they haven’t done and what question they asked and et cetera. But that’s completely siloed from product content. There’s customer support content, that’s a whole other thing. You know, all of these things have been separate. And we’re going to have to find more ways to unify that entire picture in a way that actually can make sense.

SO: Right. And the interesting thing to me is that fundamentally, if you think about it, the reason that they’re siloed is because in the olden days they were siloed, right? 

KA: Mm-hmm.

SO: You go to a trade show, and you get marketing paper, collateral, handouts, and then you buy the product and the product comes with documentation like a book on paper. And maybe you read it and maybe you don’t, but that’s where the technical documentation lives. And then you have a problem. So you call up on the phone or your field services tech comes on site and helps you out. So then along comes digital, just broadly digital web online stuff. Well, now everything is on the web page, but it’s like training.yada.com and docs.blah.com and well www.yada.com, which is of course the marketing content. So even there though, once you sort of find yourself in the learning management system, the experience is different. And so you’re signaled that that’s where you are. Fine.

KA: Right.

SO: And then there’s a docs portal, we hope. And then there’s the marketing, the dot-com. But now the way this is going to work is that I, as a reader, as a content consumer, am going to ask the AI for information. And it’s going to give me this flat text. And by flat, I mean not designed by the originator.

KA: Mm-hmm.

SO: Right? It just shoves it through the LLM and spews out a bunch of text at me and says, here’s the answer you’re looking for, here’s the information you’re looking for, maybe. And so therefore, that whole signaling mechanism that says, I am training content, or I am marketing content, or I am tech support content is basically gone. It’s just here’s the answer to your question, and it’s conversational, it’s interesting, and maybe it’s accurate; we don’t know. It’s probably accurate at a high level in the sense that the first question you ask is pretty accurate. As you start drilling down, it gets less and less and less accurate because it has less and less and less information to average in order to give you that answer. So with all of that, I was gonna ask you how the next couple of years are gonna go, but then I decided that was dumb. So how do you think the next six months, or maybe six weeks, or you know, even next week? Like pick a time period and tell us what you think.

KA: Yeah, I mean, from my point of view, and I talk to a lot of folks from across content design, and that’s kind of been my focus the last months is to really think about future of UX content and where we’re headed. I do see what you were saying earlier of you know, there are have been a lot of layoffs. I expect there will probably continue to be a lot of layoffs in content roles and design roles and everything else probably as well.

So I think that in the short run, things are gonna be pretty bumpy. I do think that companies are getting to the point where the development that they’ve been doing on their products is getting further along. They’re closer to releasing something or at least using something with customers. And I also have a feeling that there’s going to be we’re getting closer to this point where companies are going to start seeing the way that we thought we could do this is not working. And they’re gonna have to start trying to figure out where are the points that it’s breaking. Now, whether or not they will have the folks at the table who will know where to point as, you know, these are the kinds of skills that we need back here. I don’t know. I guess I’m in some ways I’m not terribly optimistic about that in the short term. but I do think eventually they’re going to have to figure out what’s actually required.

To build these products that they want to build. And I think that a lot of content people are going to be required to do that work. And so I’m hopeful, I don’t know if in the next six months, but in the next year anyway, that we will see a major turnaround of companies starting to really hire back content folks. I’m not sure if they will have the same titles they had before, or there’ll be new titles. But I do think within a year, we’re going to start seeing the turnaround on content folks having a lot of work. but I I have a feeling that the success of the products themselves are going to be the thing that’s going to cause that turnaround to happen.

SO: What’s your best advice to the people that are being displaced right now?

KA: Yeah, I mean, I think there’s so much hype about AI, and a lot of us would probably wish that we could tell folks, don’t worry about it. You don’t have to learn it, you can choose not to. And I mean, there’s a lot of talk now in design at least of people maybe wanting to leave tech. And I think that can be a valid choice. But if you do want to stay in tech and you do want to stay in user experience or even in techcomm, I think you really need to be upskilling, a lot of upskilling. And there’s a ton of information out there. I think there’s courses are just starting to come out. A lot of them are not necessarily that good. now I think the better courses are starting to come out. 

SO: Because ironically, if you write them with AI, they’re not going to be that good.

KA: That’s the problem. That is the problem. So find the folks that have actually done it who are teaching things because they’re gonna be the ones that have, you know, better advice for you and more realistic advice of kind of, you know, this is what this is what I’m seeing while I’m doing it, or this is how it came about, as you know, I mean, model design is a whole new field. It’s not that they’ve necessarily figured out the best way to do these things, but the same kinds of skills that we have as content folks are the things that are going to stay the same, even if the format changes. And you know, now we’re thinking about all these markdown files. And, you know, I think in design systems there’s a lot of talk about adding context to JSON files and things like that. All of that stuff can change, but the ability to know what good looks like doesn’t change. 

So I think it’s a combination of trying to get really clear on those fundamental skills that you have. So, you know, are you, are you a good writer? Are you a good designer? And what makes you a good writer or a good designer? Can you articulate those things? And can you get better at being able to articulate those things? Because I think that’s what’s going to be needed. We’re going to need to define what good looks like and be able to create an eval for what good looks like in a way that we didn’t have to before. So one thing is double down on your fundamentals and make sure that you’re really you know, not just kind of a surface-level writer, but you’re getting down into the depths of why what you’re doing is right. 

And then second is, you know, that upskilling on could be on model design, could be on content systems, could be on, you know, I mean, Mike Iantosca is constantly putting out new stuff on how DITA can be expanded to use AI. So I think depending on where your kind of comfort is, there’s plenty of ways that you can find things, even for free. And that’s one of the things I would tell people is there’s lots of courses, but you don’t have to spend a fortune, especially if you don’t have work right now. There’s so much good information out there for free. So just, you know, go out there, start digging into it. And also use AI in your, you know, daily activities because a lot of times you it’s something you’ve said many times, like if you talk to an AI for five minutes, it might sound really smart, but the more you use it, you’ll figure out that it’s it doesn’t get it right so easily.

SO: Yeah, I think the best advice I have right now is that while I think we have a recognition that there’s some really problematic stuff going on, and we haven’t talked about, you know, the problems with bias and ethics, but you cannot in in this universe that we live in, which is largely, you know, tech and software, you cannot be the anti-AI person. That is not going to work.

KA: Mm-hmm.

SO: So my advice to people is to do two things at the same time, which are try nudge your AI strategy, your organization, assuming you still have a job, into a place of using it intelligently and away from a place of using it unthinkingly and unethically, without putting yourself in the position of becoming known as the person who is sort of sounding the alarm. So it’s like look like an advocate, but nudging it in a direction it needs to go. 

KA: Absolutely. I love that.

SO: Because people are making some really, really dumb decisions. I don’t mean us people, but at a at a very high level, there’s a lot of people that perceive AI as the solution to all of their problems, which are basically, goody, we’ll never have to hire anybody again. And that’s real dumb. And I worry a whole lot about the products that we work on and what would happen if and when those products are AI-ified in non-strategic ways and what could happen.

KA: Mm.

SO: I think about medical devices and bad AI, and it kind of makes me twitch.

KA: Mm-hmm. Mm-hmm.

SO: So you know I see risks there. And I think I wanted to close with that. Either what do you see as the biggest risk, or maybe that, and also what’s the biggest opportunity here? Like what are the two sides of the coin of this, you know, innovation, new thing that we’re in the middle of?

KA: Yeah, I think there’s a ton of risks. As you say, it’s not popular to be the person who’s talking about those all the time. But all those things you mentioned are huge risks. I’m not even sure I would call them risks. They’re inevitable at this moment. A lot of, you know, the issues with ethics, issues with inclusion, issues. I mean, in content design, I feel like content designers care so much about the users. 

They’re just completely full of empathy for users. And they’re often the ones who come in and argue with a PM or argue with someone about the way that they’re, you know, suggesting something is done in a product. And, you know, I don’t know that we can even, if we try to encode that into some kind of discernment for a machine, I’m not sure that it can do that. So I think there’s a huge risk of taking humans out of these processes because I just think humans bring so much to them on that kind of risk side. I also think there’s a huge risk that these products will never quite get to the level that the companies need them to get to. 

You know, if you’ve worked in content, you know all the things you need to deal with legal and all the compliance issues that you have and how difficult it is to get people to trust your product enough to want to adopt it. If if you’re in consumer work, even more so that you’re, you know, constantly focused on how do we get people to trust this product and want to use this product. and I’m just not sure. Well, I just feel like it’s we’re very, very far from the orchestration, the mechanisms, the context, the data: All the different pieces that would need to be in place and working pretty well, working pretty smoothly in a way that orgs have never been able to make all of those things work really smoothly. And I don’t think that AI can magically clean that all up. And so I think there’s definitely a risk that companies are putting so much effort into AI and expecting it to get to a level that it’s just not going to get to.

So I think that’s a huge risk. In the meantime, my take on it and my take for my team and others in content is use this time to be learning and we’ll see where it goes. You know, but in the meantime, if you’re learning and, like you say, I think if you have an opportunity to nudge something in a better direction, do it. You know, speak up with some ideas. Yes, you don’t want to be the person who’s anti-AI at this moment in your company, probably. But that doesn’t mean you don’t have small opportunities where you can nudge things in a positive place. so I think that’s a lot of risk, a lot of danger. 

And that’s not even touching on all of the real dangers that I think we all can kind of see coming with AI. And then to move on to the biggest opportunity, I think I mean it’s a challenging moment for people in content. And I feel like we have our work cut out for us. And if this is ever going to get to a functioning place, it’s going to require a lot of really smart people who work in content and who have the skills that we have. And so in that way, I feel there is a ton of opportunity for for folks who have a background in content fields. And so I think you know, I think that’s wonderful and to maybe tie them together. One thing I love about that is that content folks tend to care about ethics and tend to care, you know, they have a good set of values that they want to bring to things. 

SO: Yup

KA: And so if a future necessity at some point will be a lot of content folks, I think that’s going to be a positive for all of these AI experiences eventually.

SO: I think that I heard this I think over the weekend, and I can’t remember from whom, but it was 100% not me. So let’s start there. There was an interesting discussion around the idea that code is effectively an artificial language. It’s a language in a box. It has a set number of things that you can do with it, which means that effectively, it’s a solvable problem for a machine. Content language, not code, but language, is not that. 

Because people can use language in interesting ways, you can use it in ways that’s never been used before. You can analogize the orca sitting off of Gibraltar to something interesting that nobody’s done before. That’s not a thing you do with software code, right? So language itself has simile and metaphor and all these other fun things, and it has different forms and shapes and things that you can do with it. And so fundamentally, solving for code automation is a different and much easier problem than solving for language automation. But we’re accustomed to thinking that code is hard and language is easy. And I think what we’re gonna find in an AI world is that the opposite is actually true. So that’s the opportunity that I see is once we get to that point, and I hear you saying a year, and I’m, you know, it could be next week, who knows?

KA: Who knows?

SO: Who knows? Okay, so yes, so our concluding thought is who knows? Yeah. It depends. That’s always

KA: It depends. That’s always the content answer, right?

SO: So Kate, well, thank you. This has been really, really interesting. And I hope you’ll come back at some point in six months or six weeks or whenever the next, you know, disaster strikes us, and we’ll take it from there.

KA: Perfect. Absolutely. There’s so many more things we could chat about.

SO: So many. Thank you.

Conclusion with ambient background music

CC: Thank you for listening to Content Operations by Scriptorium. For more information, visit Scriptorium.com or check the show notes for relevant links.

The post Bridging the gap between content design, content ops, and AI appeared first on Scriptorium.

In this podcast, Sarah O’Keefe and Carlos Evia discuss their upcoming book: The Uninvited Author: AI, Intent, and the Future of Content.

Carlos Evia: One of the things that we really want to invite people who end up reading this book to do is engage critically with AI tools across the text cycle. It’s not magic. It’s a collection of ugly computers in water-chugging data centers that work primarily on predictability approaches. And I truly think that we need to be critical in our engagement with AI as authors and as readers of content.

Related links:

Digital sovereignty in the age of AI

From ad hoc to autonomous: The AI content ops maturity model

Subscribe to our newsletter for updates on Sarah O’Keefe and Carlos Evia’s book: The Uninvited Author

LinkedIn:

Sarah O’Keefe

Carlos Evia

Transcript:

Disclaimer: This is a machine-generated transcript with edits.

Introduction with ambient background music

Christine Cuellar: From Scriptorium, this is Content Operations, a show that delivers industry-leading insights for global organizations.

Bill Swallow: In the end, you have a unified experience so that people aren’t relearning how to engage with your content in every context you produce it.

Sarah O’Keefe: Change is perceived as being risky; you have to convince me that making the change is less risky than not making the change.

Alan Pringle: And at some point, you are going to have tools, technology, and processes that no longer support your needs, so if you think about that ahead of time, you’re going to be much better off.

End of introduction

Sarah O’Keefe: Hey everyone, this is Sarah O’Keefe. I’m here with Carlos Evia. Hi, Carlos.

Carlos Evia: Hello!

SO: So, Carlos, for those of you who don’t know, is the co-author of this book that we’re working on and also professor at Virginia Tech. His official title, his official titles are Associate Dean of Strategic Initiatives at Virginia Tech, and he is also the CTO of the College of Liberal Arts and Human Sciences. I think, Carlos, that means you’re the computer guy in the humanities world.

CE: That means that people come and complain to me about curriculum and also about their computers. So yes.

SO: Okay, cool. And so with that, Carlos and I have written this book. And in this first episode to this special series, we wanted to give you an overview of what it is that we’ve done, or what it is we hope we’ve done, we are trying to achieve here. And probably the easiest way to do that is actually to break down the official book titles. So what is our official book title?

CE: The Uninvited Author: AI, Intent, and the Future of Content. And I don’t know if I got it right from memory.

SO: No, I think that’s right, only because I wrote it down. So I’ve been staring at it nonstop for, you know, four to six months now, but still. 

CE: Yeah. yeah. I see it now. Ha ha ha.

SO: You know, can we remember our own book title at this point in the writing process? And we should tell you that we’re recording this as we’re approaching sort of ninety percent done, which means that we still have approximately ninety percent of the work to do. And we’re a little punchy.

CE: My co-author today woke up being very optimistic about progress on the books. But I agree, 90% sounds accurate. Yes, I’m not gonna argue.

SO: Yes, you’re well, your co-author is slightly delusional, so we’ll just set that aside and move on. All right, so let’s talk about this. The main title is the uninvited author. So who is the uninvited author? What are we talking about here?

CE: Well, the uninvited author, surprise, is the AI author. We have seen how AI has been taking over the generation of content at different types of content, content for marketing purposes, content for technical purposes, content in video, in text, in audio. And in some of those cases, it’s creeping into people’s workflow without an invitation. And now, and we know people, I mean, across the different facets of content work that now are, on purpose, inviting AI agents to contribute or to take over and start driving the car of the content operations. But particularly for the type of content that we do in our little corner of technical communication, AI, authors kind of started coming as uninvited guests that will appear when a user will use a chatbot, say going to ChatGPT or going to Claude asking how do I do this instead of going to the published official manual of the name of the appliance or name, the software application. 

And what we realized is that what was happening is that as the company, I write my documentation, I put it on the website, I put it on a book if I’m in 1985, and I give that to my users. And I hope that that’s what they use. I am the author. I bring it to you. But now when a user prompts a chat button and says, how do I turn on this machine? How do I save a file in this software application? 

Now there’s a new author that is going to give information that might be accurate, that might reflect what I wrote, or might be inaccurate. It might be, like you said, delulu and inventing some other content. So that is the uninvited author. An author that is already here and is adding to what other humans have created or written or flat-out making up stuff out of nowhere that didn’t exist and that was not created by humans before.

SO: And I think that this this theme of loss of control for the humans returns in maybe every page of this every page of this book. So we have the AI that is now delivering… well, it was delivering content, right? And when you had a search engine, you would ask it a question and it would return answers, but in general, those answers were, “Here’s what I found in this document,” or “Here’s a collection of links,” or whatever. The what’s new is that the AI is synthesizing answers from its sources, and we don’t know what those sources are necessarily. Sometimes they’re cited, sometimes they’re not. 

I asked the chatbot something the other day, and it said it was something very straightforward like how old is somebody, like famous person. And it gave me an answer, and I said, cite your sources. And it said, this is just general knowledge. I’m sorry. How is this general knowledge? It it would not and then it said, but you know, it got kind of passive-aggressive. It was like, well, if you insist, I can give you a couple of websites that list this kind of information. but essentially it was like, how dare you question my knowledge of just the general universe? Well, I I use computers for a living, so I question everything.

All right, so the uninvited author is the AI, and now the chatbot is authoring content, accurately or not, whether we like it or not. So our subtitle then is AI Intent and the Future of Content. When we look at AI in the context of content, what are we looking at here? How does AI get involved in content operations, in the content process?

CE: Well, we have been chatting, ha ha, we have been chatting about chatbots so far, but the chatbot, it’s really only scratching the surface of what AI already is for content operations. I don’t even want to think about right now, let’s save it for the next section of the title of what it’s going to do or what it could do.

CE: And the chatbot is the easiest representation of it. And yesterday I was teaching, I’m teaching this semester a senior seminar in communication on the topic of what AI is doing to the profession of communication, for good or for bad. And something that my students tell me is that they use ChatGPT or a similar chatbot as a replacement for the Google search box. So they go there and they go ahead and ask and prompt without prompting, ask, they query things that up to two or three years ago, people would just ask Uncle Google.

SO: Now, in their defense, it’s getting very difficult to actually find the search box. 

CE: If you go to Google, yeah, you don’t know what’s Google, and you don’t know what’s Gemini. They’re all married and combined together. And I think that that is the very interesting part. But the chatbot in that box that resembles the Google Omni box is only one component of what we mean by AI. AI comes in many other flavors that I think my co-author in this book even has a fancy table inserted on page number here about the different forms of AI engagement in content operations. And at the end of that spectrum, we have agentic approaches to AI in which you, as the developer or you as the author of the content, are going to be sending out these AI agents to be taking care of processes or supporting processes that human beings are doing throughout the life cycle of your content. 

So I want to emphasize that what we’re talking about here is not just ChatGPT, not just Gemini or even Claude, but many in-house developed and maintained in a little or not so little computer in one organization implementation of not just a large language model, but many other machine learning and data mining approaches that could create something that smells or looks like artificial intelligence beyond basic automation. So AI means many things, and we have more than one section in the book that tries to address that AI is many things, even though for the majority of people who probably are listening to this AI is ChatGPT in that box.

SO: And one of I think one of the really tricky parts about this is that, as content people, we see AI in lots of different places in our in our job roles. So what I mean by that is that mean, we’ll start at the end. The content consumer, it used to be get your content on the website, do some search engine optimization, keywords, whatever, make sure that people find your content. Or you might be privileged that your content is ships with the product as online help or a companion document. Again, if it’s nineteen eighty five, but you know, it’s the supporting content that goes with the content, or you’re working on knowledge bases, that type of thing. So as a content creator, I’m thinking about what does it mean

SO: To get my content in front of the end customer. And if that is now mediated by a chatbot, how do I make sure that it survives the trip through the chatbot so that the content, the instructions, the information still reaches that end user instead of them getting, you know, something potentially inaccurate? So that’s the front end, right? There’s also the issue that LLMs and chatbots have the ability to create what we call synthetic content. Content that doesn’t previously exist, but when I ask the chatbot for it, it gets generated. There are lots of examples of this, but machine translation is one. Hey, can you give this to me in a different language, please? And it says okay, and it magically machine translates it and gives you what you’re asking for. Make it shorter, make it longer, give me more information, give me less information. Write it in a different style. Those are all cases where the chatbot is intervening and putting its own layer on top of that. And then as you work your way backwards, there’s authoring assistance, you know, fix my grammar, refactor my sentences, that kind of thing. And as a content creator, the availability of AI across the entire what you know, the text cycle.

The process of creating and editing and managing and delivering content, it affects every single one of those pieces. And we have to really think carefully about how and where and whether or not to integrate that into content operations. What are appropriate and inappropriate ways of doing that?

CE: I think you said something very interesting when you refer to a magical process. The assumption is that a magical process happens and then voila, you have something that the AI agent or the AI chatbot generated or assisted in the generation. If we go back to that separation of the backend or the front end. And that’s where I think that one of the things that we really want to invite people who end up reading this book is to engage critically with AI tools across the text cycle. And we haven’t even talked about the concept of the text cycle, which is a major component of the book, because it might be that you, as an author or you as a content reader, as a consumer of content, prompt a chatbot for information on how to do this, either to write something or to read something and solve a problem. But it’s not magic. It’s a collection of ugly computers in water-chugging data centers that work primarily on predictability approaches. And I truly think that we need to be critical in our engagement with AI as authors and as readers of content and not just about technical content. If you’re doomscrolling on Instagram, and let’s not even mention TikTok because I don’t use TikTok, I’m very old. And you see these AI sloppy videos from dozens of people fighting in like every Mortal Combat. Let’s ask why…

SO: You seem to know a lot about this for someone that doesn’t use TikTok.

CE: I doomscroll a lot. You’re like, what is this, and what is happening behind the scenes? How do we think critically about the concept of AI as it becomes an invited or uninvited component in communication processes? And it’s not magic. It does things fast. Sometimes it does it in an accurate way. The models are getting very interesting, and they tend to be way more accurate than they were just a year ago. But I think that’s an invitation that engage with this critically. And I want to peddle this book as an approach for people in our profession, particularly in technical communication, in content operations, to read this and start thinking in terms that allowed him to expand that idea of this is the oracle. I will post a question, and I hope I get something good in return, and my life can be better.

SO: Yeah, I think one of the most useful things you can do with AI is sit down and ask it a question about something that you are an actual expert on. That might be a hobby in your life. It might be that you have an interest in, you know, eighteenth century literature. It could be a lot of things, but pick something and ask the AI a question about something that you truly know a lot about. And pay attention to the results you get, and you know it’ll say, would you like me to give you more information about something? And just kind of follow that trail for for a bit. What I found in doing that is that nearly always the first answer, the high-level answer, the sort of overview is pretty accurate. And the farther I chase it, the worse it gets. As I ask it for more and more detail, the details degenerate. It’s still very confident. But it starts just going completely off the rails. Now, then you try the same thing with a topic you don’t really know anything about and you’re like, well, this looks pretty accurate. So essentially, it will get you to a sort of mediocre level of expertise, but if you need to go deeper than that, you run into all sorts of problems. So intent. We have intent in the title. What is intent, and why do we care?

CE: I’ve been thinking about this for a very long time, and to a degree, this is something that I wanted to write even back in the early 2000s, not about AI, but in the context of single sourcing of content and how we were embracing, in the early 2000s, approaches for reusing pieces of content that will appear in different deliverables and will adapt on the fly to the needs of different audiences or different versions of a product or something like that. I started thinking about in the tradition of, I’m gonna say a bad word that Sarah doesn’t like: hermeneutics, which is the study of interpretations. 

SO: Boo.

CE: And it’s not Herman Munster. Hermeneutics. As an author, as a human author, I write something, and I imprint in that something my intentions, my intent. I want to say something. If you compare it to the rhetorical tradition, that’s your purpose. You have a purpose when you send something out to the world. You have an intention when you put something out in the world. And at the other end of the spectrum of the communication model, there will be somebody who, up to a few years ago, it was most likely a human being and not a machine, who was going to receive that message that you were sending with your intentions and was going to make an interpretation of said message based on their environment, on their cultural background, on their languages, and extract something that will make sense for them.

So that is what we’re talking about here when we mention intentions or intent, because surprising nobody, if we go back to that communication process that today includes the human author, the human reader, and the possibility of a human, sorry, not human, of an AI author or co-author in an AI reader or assistant to the human reader, well, those AI players bring their own intentions. And you mentioned this when you were talking about where is the information that they have coming from? And there are many layers of the training data, models that go out and perform web searches on the fly, models that are looking at your memory and your previous interactions with them, all of those components create the intentions of these AI authors or readers. So we think that intent or intention is a very complicated topic when it comes to AI in content operations, because it can really take things on a completely different path of what that traditional approach of a human talking or a human writing to another human is conveying. But at the same time, also, intention is a good thing from the author’s perspective, because if I imprint my intention and I set some guardrails on my communication processes, that might be my only hope, my only way to battle the production of AI slop. 

That is completely taken over by the intentions of the “AI authors.” And I am still not super comfortable calling the AI authors, even though in the book we call them the AI authors. And that’s what we mean by intentions. It’s going to that very basic fundamental concept of I write something, I publish a video, I publish a picture that I took; I have a purpose, I have an intention. What is my intent in publishing that? And what happens when that message gets to a human receiver and that human receiver makes the interpretation out of it? That cycle is truly affected by AI players at all points in the cycle.

SO: Yeah. And then, you know, the last chunk of this is the future of content, which is, you know, pretty much what we might expect. I think I’m gonna wrap it up here because this is getting too long already. We have a lot to say, and much of it we’ve captured, but we’re trying very, very hard to provide a roadmap to, you know, as Carlos is saying, to engage critically with AI, with the tools that are now available to us as authors, as content creators, as content consumers, and to understand, you know, what does it mean to use AI? What kind of biases does AI introduce? We’ve seen a lot of discussions about, it uses too many em dashes and, you know, now I can’t use em dashes anymore because people see that as a proxy for AI-written content. 

But what else is it introducing? What kinds of biases are in the training data? What are the ethics of using data that is largely English-centric, biased towards things that are available online, not just biased towards if it’s not available online, then the AI can’t consume it, right? Which is why they’re buying up books and shredding them and scanning them wholesale, which is a whole other thing. 

CE: Mm-hmm.

SO: But the digital footprint of what an AI has ingested is different from reality. It’s the AI’s reality. And then you have to ask the question of how far does that deviate from actual reality? And does it do so in predictable ways that we can potentially remediate? So we’d have a fair amount of discussion about algorithms and bias and what it means to work in an environment like this and, you know, are there ways to remediate it? Are there ways to bring this under control? And then finally talked, you know, a fair amount about what it means to live in a world where your chatbot has access to, you know, truly a stupendous amount of information, which means it’s at your fingertips and you can potentially automate and agentify these workflows. what does that mean? Our last sort of section is currently called the next 30 years. We’ve debated changing it to the next 30 months, or I feel like the next 30 days is the most accurate way to portray it. But we are trying to step back and take that longer view of where is this going and what are the implications of all of what’s going on here? So with that, we are mostly done.

CE: Optimistic.

SO: Our goal, our plan is that this book will be available by the end of October, which is to say for LavaCon. if you want to get more information about it, I would say follow this podcast series or sign up for our newsletter. We’ll be sending out updates that way. And I expect there will be some fun special offers as we launch. We expect this thing to be in the vicinity of probably 300 to 350 pages. And we’ve tried hard to make it an actually fun and entertaining read as opposed to something that you have to slog through. And I hope that you will find information in there that you currently cannot get from your chatbot

CE: And it’s not written by AI, it’s written by us in painful writing sessions and lots of online meetings and what have you.

SO: We have suffered greatly, and I would really like for people to read this stuff, and I don’t know about agree with, but at least engage with and have that conversation. I am actually much more interested in finding out what other people think about all these developments than I am in asking the chatbot. So so I hope it’s useful and I look forward to being done.

CE: Me too.

SO: That’s the most exciting part of all of this. We’re gonna do a couple of these podcasts to talk through some of the pieces and parts that are there. I would like to state for the record that we are not going to generate synthetic podcasts off the book content, although we totally could. 

CE: Tempting, tempting.

SO: Not very tempting, but it is possible. Given the shape that my voice is in this week, it’s actually, yeah, the listeners might have appreciated that. But I think that’s it. We’ll see you on the next one. And Carlos, thanks, and I’ll talk to you in our next torture meeting.

CE: Thank you very much.

SO: Okay, bye.

Conclusion with ambient background music

CC: Thank you for listening to Content Operations by Scriptorium. For more information, visit Scriptorium.com or check the show notes for relevant links.

The post The Uninvited Author: AI, intent, and the future of content appeared first on Scriptorium.

What are the limits of automation and AI in content systems? In this episode, Sarah O’Keefe and Bill Swallow dive into traditional formatting, workflow challenges, and what happens when AI is introduced.

The limit of automation here is not really the automation. It’s the people who say, “I don’t like the way this looks, and I’m gonna find a way to fix it. I know all sorts of ways of bending this stuff to my will.” If you’re generating content at scale, you can’t afford to do any of this stuff.

Related links:

Digital sovereignty in the age of AI

From ad hoc to autonomous: The AI content ops maturity model

Subscribe to our newsletter for updates on Sarah O’Keefe and Carlos Evia’s book: The Uninvited Author

LinkedIn:

Sarah O’Keefe

Bill Swallow

Transcript:

Disclaimer: This is a machine-generated transcript with edits.

Introduction with ambient background music

Christine Cuellar: From Scriptorium, this is Content Operations, a show that delivers industry-leading insights for global organizations.

Bill Swallow: In the end, you have a unified experience so that people aren’t relearning how to engage with your content in every context you produce it.

Sarah O’Keefe: Change is perceived as being risky; you have to convince me that making the change is less risky than not making the change.

Alan Pringle: And at some point, you are going to have tools, technology, and processes that no longer support your needs, so if you think about that ahead of time, you’re going to be much better off.

End of introduction

BS: Hi, I’m Bill Swallow.

SO: And I’m Sarah O’Keefe.

BS: And today we’re gonna talk a bit about automation, and more specifically what the limits are for automation.

SO: Yeah, they let us out of our cages. And so here we are. And I think that in this world of  I’m not going to get through the first sentence without saying AI. In this world of AI, we are suddenly facing, you know, increasing automation across every facet of everything that you could imagine. And I think it’s important to take a step back and talk a little bit about limits and what automation cannot do and maybe more importantly, why it cannot do certain things.

So before we get to, you know, the AI in the room,  Bill, what are the limits when we talk about generalized publishing in the pre-AI world where we’ve done a ton of formatting automation and we talk about all those kinds of things, what are some of the limits that we’ve run up against in terms of automation?

BS: Yeah, automation is something that we’ve been doing quite a bit of  for the past, what, twenty years, I think, or more. I’ve only been around for thirteen years. I’m thirteen years young,  so…

SO: Yeah,  this is lies.

BS: But no, a lot of our work around automation is around publishing.  That is, I think first and foremost, the most common case.  And with automation and publishing, you can save a lot of time and save a lot of effort, but a lot goes into building that capability because you can’t really work around edge cases or you know, fancy hand-cobbled formatting,  hand page breaks,  all of that thing. You have to kind of rely on the software to understand the content that you’re feeding it and it’s going to produce something that you know is a finished product: a PDF, a web page, what have you.  And you know, if you deviate from the structures and conventions that it’s expecting, then all bets are off as to whether or not your automation will be successful.

SO: Right. And so, from our point of view, doing lots and lots and lots of structured content work,  i setting aside the tools and the technologies, what structured content really does is limit variability. Right? It limits the variability of the information or of the markup really going into your system, which then means in turn that the system can be automated and can automatically output all the outputs, all the deliverables, all the file formats that you need. And so  when you have weird edge cases, and I am of course the worst offender in terms of actually finding ways to bend the software to my will,  but only when I’m an author, right? As a system configuration, I’m, yeah, I think you should all follow the rules. Yeah. 

So here we are, and we basically say we’re gonna limit the variability of the input and standardize the input and therefore we will get standardized output. Cool. But as you said, that only works if you don’t have so what is a weird edge case or what are some of the things you’ve run into that just bollocks up automation?

BS: One good case is working with content that maybe has valid structures in place. So they’re not, you know, the content itself validates against a validator. So there’s nothing wrong with it. But they’re using, let’s say, different in this case, DITA elements in a let’s say creative way. You know, so they’re you know  I was on vacation last week, so that wasn’t me. 

SO: I see you were looking over my shoulder last week again. Yeah, that’s true. Well,  what I actually ran into was I had a DITA map; it was valid, it validated, and then I used Oxygen’s validator, which you know really goes a little bit deeper and looks at things. Everything was fine, but it crashed. And eventually what I realized or what I found after some digging was that somebody who was definitely me had inserted a draft comment and the draft comment was in a table, maybe under the title, but before the table group kind of thing. It was in an unusual location and it just the processor just died. It just laid down and gave up.  now I don’t know exactly whether that was because of the, you know, the core processing or something that we did in the the  plugin that I was running. It doesn’t really matter. The point is it was it was valid. But it didn’t pass the processor because the processor was like,  Why would anybody put a draft comment in this location? This is dumb. And then I, you know, felt berated by the processor and I moved it and then it all worked.

BS: Interesting. Yeah. I would have enjoyed being there for that. 

SO: Yeah. Mm hmm.  So anyway, we fixed it, and it was fine, and you know, and off we go. Let’s talk about pagination!

BS: Pagination’s a fun one. 

SO: Pagination’s my favorite.  I get very upset with bad line breaks or bad page breaks.

BS: Yeah. And you know, we can build in rules that say, you know, only, you know, to control widows and orphans, that type of thing. You know, tell it, you know, break a table leaving X many cells. If you don’t have X many cells to break, then move the entire table to the next page, all that fun stuff. But if you have, you know, specific places where you need to break to a new page for whatever reason, that always can’t be necessarily automated, depending on what the rules are for producing your output. You know, the processor’s not going to know that, you know, you may arbitrarily want to break a page at this particular location. So you know, in many cases we cobble together a little tag that says, you know, essentially break the page here,  and the processor knows to you know, when it sees that to say, okay, stop processing this page, move to the next one.  And you know, it works most of the time. 

SO: I would never. Yeah, the problem with inserting page breaks, as I’ve learned to my great sorrow, is that, of course, later you add more content and now you have a page break a third of the way down the page because you hard-coded it in. So this is bad, and you shouldn’t do it. But if you insist on doing it, do it l as late in the process as possible. Don’t try to fix your pages when you’re 80% of the way there, because you will have to reinsert them over and over and over again.  also.

BS: Right.

SO: Inserting empty tags that have a non-breaking space in them to introduce vertical space is wrong, and you shouldn’t do it.

BS: Ha ha. I will agree with that one. Also, I mean, doing these types of things to force a page break or to force extra space, it really flies in the face of automation because technically you have to create the output in order to know where you need to insert your page breaks and then go back and add them and then automate your output again.

SO: Ha ha. It looks bad.

BS: Yeah.

SO: So yeah. So really the limit of automation here is not really the automation, right?  It’s, well, it’s me, right? It’s the people who are like, I don’t like the way this looks, and I’m gonna find a way to fix it. And I have lots more demented tricks up my sleeve. I know all sorts of ways of bending this stuff to my will. And if you’re generating content at scale, you basically can’t afford to do any of this stuff, right? It’s one thing if you’re producing, you know, one document and it’s short and/or it’s marketing content, and we’re really concerned about the appearance because of people making buying decisions. But if you’re producing, you know, ten, twenty, fifty thousand pages a year, then you just need an engine that produces this stuff. So

BS: Mm-hmm. Yeah. And the page break problem is actually a good one to speak to at scale because if you’re in an environment where you’re sharing a bunch of different content and you’re reusing pieces, if you insert a page break for your own personal preference, suddenly that’s going to be in everyone else’s document that also uses that particular topic.

SO: All right. So I’m hearing that page breaks are bad and I shouldn’t do them.

BS: No, they’re great. It’s just that you have to be smart about it.

SO: Okay. Sneak them in. Don’t get caught. Got it.  So, while we’re on the subject of recalcitrant authors. Such is definitely not me. What about automation in a scenario where your content production system is not being used by the authors?

BS: Yes. That’s a completely different problem. Yeah, that’s an entirely different problem because then you’re in a situation where essentially you need a production team that are also, you know, data entry people, you know, and they need to somehow bring the content that’s being produced into the system in order to produce the output.

SO: Okay, but can’t we just use AI for that?

BS: Sure, why not? AI’s great for that, right? 

SO: Huh. Right. Yeah. So ultimately, I mean, sure. If the authors are authoring and they follow some sort of reasonable template or or they’re reasonably consistent in some way, we can bring the content in automatically.  I hope you heard the first part of that about the reasonably consistent part because that’s where this breaks, right? You’re gonna get all sorts of things.

BS: Mm-hmm.

SO: And our experience on this has been that this is a problem or a challenge across a variety of different factors.  Are your authors volunteers or are they paid? If they’re paid, you have, you know, some degree of leverage to say you need to work in the system. So are they volunteers or are they paid? Is content their full-time job or is it a small part of their responsibility? So, you know, 90% of the time I’m an engineer and 10% of the time I’m a writer. Or 90% of the time I’m a subject matter expert of some sort, and 10% of the time I’m writing content. The less time a given person is spending on content production, the more likely it is that they’ll push back on learning your weird content system. Right. 

BS: Mm-hmm.

SO: And then the third question, the third factor that goes into this is sort of level of expertise. I mean, we make jokes about rocket scientists, but it’s kind of that question. If you have a person who is responsible for contributing content and they are a world expert in their field,  unless that field happens to be something like content markup and formats, they’re not gonna be that interested in spending their time learning about content. They’re focused on,  you know, curing cancer. And I’m not prepared to argue that, you know, learning some tags is actually a useful use of their time, right? So you take the content that this world expert produces in whatever format you get it. Scribbled on a napkin, yucky Word file, whatever. We’ll take it. And you find a way to bring it into the system. Now, I will say there are some subject matter experts who are actually very interested in the content production process and will jump right in and kind of, you know, play around with it and learn what they need to learn and contribute directly in the system because they think it’s interesting and fun. But when you start talking about volunteers versus people that are being paid and/or experts versus, you know, people who are dedicated to this role and/or it’s part-time, the intersection of those three, the Venn diagram or actually the anti-Venn diagram of those three things is where you will find people that will not be working in your system.

BS: Yeah. And you know, with any kind of an external contributor to content, you also run the risk of having content that doesn’t necessarily follow the conventions that you’re expecting, you know, or that your automation pipeline is expecting. So you may get something from someone who absolutely knows their subject matter inside out and sideways, but they’ll give you a document that has, I don’t know, three levels of nested lists, and your system only accounts for two; then you have to figure out how you’re gonna get that content to play well within the construct that you have. Otherwise, you have to reengineer your pipeline.

SO: And then you have to balance the cost of reengineering the pipeline for the edge case against the value that the edge case brings to the situation.  And, you know, very early in my career, I ran into somebody who has since passed away, unfortunately,  who was terrible and I mean awful at  I I shouldn’t say it that way. He wasn’t terrible at following templates. He followed the templates until it didn’t suit him. And when it didn’t suit him, he would come up with some workaround to do what he was trying to do. So your nested lists are a good example, stuff like that.  And I was, I don’t know, 20-something,  and now I’m slightly older than that. It was my job to push back on this guy and say you didn’t follow the templates. And he would literally yell, which was a fun experience. 

BS: Mm-hmm.

SO: But the thing was that in every single case, he had thought about it. He never deviated from the templates by accident. It was always, I need it this way because of this other thing. I also learned the hard way that he had thought really carefully about word choice. And so if I ever changed any of his words, we would have well, we would have words.  And he would explain to me why I was wrong and why changing his word to my word or, you know, follow the style guide, whatever, was wrong in that instance. And he was always right. Always. Now, I’ve been doing this a really long time, and I’ve only run into one person like that in my entire career.  But I have not forgotten that at least once I ran into somebody who would work outside the provided, you know, color outside the lines in order to make his document better, and always had a defensible reason now. Do I wish he had yelled a little bit less? Yes, but you know, that’s life.

BS: Mm-hmm. All right, so we talked a bit about the automation pipeline and what people can inject into it. Should we turn our attention back toward our good friend Mr. AI?

SO: Mm. All right. So it’s interesting because a lot of the edge cases that we’re talking about can actually be addressed and flattened out by AI. So AI and AI tooling actually provide a potential solution to all of this. But I wanted to focus a little bit on a different problem with AI and automation. So when we talk about the limits of automation in, like a scripting workflow or a traditional non-AI workflow. A big part of the response to that is, well, the AI could actually address what you’re describing and solve for those things. Okay, fine. But now let’s talk about what AI can’t do, the limits of automation with AI. And it’s actually a really different problem than what we’ve been talking about. We’ve been talking about sort of following the template, don’t color outside the lines. With AI, what we’re running into is that.

BS: Mm-hmm.

SO: AI and AI systems only have visibility into the digital world. And so if there’s information floating around an organization that gets passed around in a hallway conversation, typically, and I say typically with great caution, the AI is not listening. And so if I, you know, if I run into Bill in the hallway and I say, which would be unusual because we’re always remote, so but never mind. We run into each other in the hall, and I say, hey, don’t forget to update that one thing. Or  I ran into so-and-so at lunch, and they told me this other little tidbit of information. Okay. Well, I’ve now transmitted that information to you and you’ve got to get it into your whatever you’re working on, right?

BS: Right.

SO: But the AI is not aware of that because it didn’t make it into a JIRA ticket or anything else, any sort of digital workflow. Now,  this is also in many cases, it’s similar to the problem that you actually run into with remote employees that they miss out on the so-called water cooler conversations, right? Like the conversations that happen on break or at lunch or this or that. But so the AI can only see what it has.

BS: Mm-hmm.

SO: And what it has access to is digital content. So your existing documents, your meeting recordings, your digital footprint, your email. I mean, it’s super creepy,  but what it doesn’t have access to is the person-to-person interactions that are not being recorded,  or conversations that are out there, or a note scribbled on a piece of paper or a couple of these Post-it notes that are sitting in front of my laptop, right?

BS: Yep.

SO: The AI doesn’t see those and therefore it can’t automate them. And because it can’t automate them,  they don’t get injected into the workflow.  And all of that sort of detritus, because if it’s important, I’m going to pass it on, right? I’ll put it in an email, or I’ll put it in a Jira ticket, or I’ll put it somewhere where it belongs.

BS: Right.

SO: In some sort of defect tracking. But it’s those little like, hey, I just saw this kind of side conversations. That cannot be automated. I mean, unless we move into an always-on surveillance cap surveillance world, which I mean I’m sure somebody’s working on it, but at the moment, if it’s not captured digitally, the AI can’t see it. And I think that we underestimate the amount of work and the amount of information that is sitting out there in the not-yet-digital world.

BS: Mm-hmm.

SO: So that’s the limit of AI automation, which is very different from “It can’t do really nice page breaks.” It probably actually can do really nice page breaks.

BS: So basically the quality and the efficiency of what you’re gonna get out of an AI automated workflow really depends on whether or not the information itself is available and being captured.

SO: Right, which is really quite different. I mean, AI is much better at taking sort of questionable inputs and doing things with them, right? Because it’s not a pass-fail script,  but it can only see what it can see.  And so we have to understand that there’s still limits there. And and it’s it’s a different limit. It’s a qualitatively different type of limit.

BS: Mm-hmm.

SO: And I think that’s important to recognize as we move forward.

BS: Right. And of course all that stuff that does need to be captured, it needs to be done in a way that AI can access it and can access it in the right way. So if it’s input wrong or whatever, then AI is not gonna have the right info.

SO: Yep. And so,  yeah, this is where I’ve been spending a lot of my time because, as you probably know, in the world’s worst-kept secret, Carlos Evia and I are working on a book on content and AI. 

BS: That’s my shocked face. 

SO: And yeah, I know, please contain your shocked face. It’s coming soon. She says hopefully, with many fingers crossed. We’re getting there. And what we’re hoping to do is get something out there that talks about some of these issues, right? We’re not gonna write a book that tells you how to optimize for a specific AI model or specifically how to build agentic workflows.

BS: Mm-hmm.

SO: What we want to do is give you the tools to ask the right questions so that you can start looking at how to put these things together and how to move forward with a reasonable content operations approach that also involves AI as appropriate.

SO: I look forward to being done. Also, for the record, the AI is not writing the book.

BS: Like, yeah.

SO: That seems important to say in this context today.

BS: That is quite important to say, given all of the AI-generated stuff we’re being force-fed at this point.

SO: No, I can assure you that my pain is human and personal when it comes to this writing. It has been real. It has been a slog. As perhaps it should be, because the process of putting something like this together forces you to really think carefully about what’s going on.  And the process of doing that with a co-author really forces you to think carefully about what’s going on. 

BS: And real? 

SO: And so it’s been great working with Carlos and also extremely painful because that’s just how books are.

BS: Yep. Cool. I think we’ll leave it there. Thanks, Sarah.

SO: Thank you.

Conclusion with ambient background music

CC: Thank you for listening to Content Operations by Scriptorium. For more information, visit Scriptorium.com or check the show notes for relevant links.

The post The limits of automation and AI in content workflows appeared first on Scriptorium.

Are you in control of your digital destiny? In this episode, Alan Pringle and Sarah O’Keefe define digital sovereignty. They break down what organizations need to consider as they bring AI into content operations, from data leakage and competitive intelligence to shifting international regulations.

Sarah O’Keefe: The working definition that I’m using is that digital sovereignty is control over your own digital assets, digital destiny. That could be you personally, it could be you as an organization, or it could be you as a country or as a group of nations. And when I say group of nations, probably 98% of the time I’m talking about the EU, which has some laws in this regard. Digital sovereignty is your ability to control, own, and manage your digital assets and how they are used, reused, processed, resold, repurposed, and all the rest of it.

Related links:

AI in the content lifecycle: three years later

From ad hoc to autonomous: The AI content ops maturity model

Upcoming AI book: The Uninvited Author

LinkedIn:

Alan Pringle

Sarah O’Keefe

Transcript:

Disclaimer: This is a machine-generated transcript with edits.

Introduction with ambient background music

Christine Cuellar: From Scriptorium, this is Content Operations, a show that delivers industry-leading insights for global organizations.

Bill Swallow: In the end, you have a unified experience so that people aren’t relearning how to engage with your content in every context you produce it.

Sarah O’Keefe: Change is perceived as being risky; you have to convince me that making the change is less risky than not making the change.

Alan Pringle: And at some point, you are going to have tools, technology, and processes that no longer support your needs, so if you think about that ahead of time, you’re going to be much better off.

End of introduction

AP: Hey everybody, I’m Alan Pringle.

SO: And I’m Sarah O’Keefe, hello.

AP: Hey there. And today Sarah and I want to talk about something that’s really starting to come to the forefront with all of the AI things that are going on in our world. And that is digital sovereignty. And before we get too deep in that, I need to throw up many, many disclaimers. Sarah and I are not lawyers, nor do we play them on television.

And we are absolutely not lawyers or experts on anything in regard to international intellectual property. So with those disclaimers out there, Sarah, if you would, would you define what digital sovereignty is?

SO: The working definition that I’m using is that digital sovereignty is control over your own digital assets, digital destiny. That could be you personally, it could be you, the organization, or it could be you as a country or as a group of nations. And when I say group of nations, probably 98% of the time I’m talking about the EU, which has some laws in this regard. So it is your ability to control, own, and manage your digital assets and how they are used, reused, processed, resold, repurposed, and all the rest of it.

AP: And I’m going to give a very basic example from my personal life in regard to email. Years ago, actually decades ago, when I got set up with an internet service provider, they provided me with an email address. It had their company name in the domain.com. And I used it for years. But when I switched my ISP, guess what? I had to make a decision.

Do I continue to pay that old ISP, basically rent, to maintain that old email address? Or should I move to one of maybe the free email providers? So I did a little research, and my ultimate decision was I created my own domain with my name, and I kind of just decided not to ever use again the email provided by an ISP because if you switch it, you’re going to possibly lose control of that email address. And at the time that I made the switch, a lot of the free providers, they would scan your email to provide targeted ads and some other things that was kind of unsavory to me. 

So I ultimately made the decision I was going to own the domain and set that up myself and pick my own software that I hooked up to it to use to to read it. And I did not use a third-party email provider to basically pull in or reference my account. I am using an open-source standalone email client to kind of minimize who can poke into my email. So that’s one very basic example of how I kind of took control of my digital life as it were.

SO: Right. And if we apply that to content ops, again, staying pretty general, you think about cloud systems, like the cloud universe versus on-prem.

AP: Yes.

SO: And when you talk about, let’s say, a CCMS, a component content management system that is on-premises, the the argument was always, well, that way all of our content lives on our servers, in our organization, we have complete control over it.

Along come the cloud services, the cloud-based CCMSs and everything else. And they say, well, yes, but it’s much cheaper for you to put this into the cloud on our systems, which are shared. And you know, there’s advantages of upgrading, and there’s all sorts of advantages to cloud systems, mostly around IT overhead. from a digital sovereignty point of view.

You are delegating to that cloud system and you have some sort of a contract or a service level agreement. And again, we are not lawyers, but you have this agreement that says we the cloud provider promise to not scan your information or not use it for evil or not, you know, there’s a bunch of stuff in that contract that governs how cloud provider is or is not allowed to handle your content, your personal information, your credit card information that you might be putting in there and all the rest of it. And with software as a service, with cloud systems, we have for the most part cut over into cloud. You know, that’s that’s kind of the default these days. There’s hardly anybody that is still putting their content, their content and their content management systems on their own proprietary in-house servers.

AP: Yes, correct.

SO: So we have decided that for cloud, you know, cloud writ large generally, that the advantages of cloud outweigh the disadvantages. Now, moving this a little bit more towards content and slowly towards AI, where things get really interesting with digital sovereignty, if we talk about machine translation for a minute.

There are a couple of different ways of doing machine translation, obviously, but big picture, you can have your in-house machine translation system and database, and you can control that and govern it and do things with it. Or you can take your content and you can throw it at a public-facing machine translation system. And the risk that you run when you throw something at a public system is that they will take your proprietary confidential content.

And use it. So I throw at it a sentence that says, the XYZ company has developed a special new thing, right? And I need that translated into various languages and I get it translated. But as a result of that, I am leaking information. I am leaking my confidential, potentially information into the machine translation services. And there are some really interesting security issues around that and how you might be able to.

As a competitor, extract that back out. But just dialing it back for a for a minute, we understand the concept of leaking information by using public-facing machine translation, right? Publicly available machine translation. But one thing that I think is very often overlooked is that machine translation, the fact that I ask for a specific language, never mind the content,

But the fact that I am now asking for a new language provides competitive intelligence in the sense that that means that I or my organization now cares about that locale, that that language. So let’s say that I’ve been consistently submitting European languages for machine translation, right? If you but if you look at my record of what I’m asking for, you will see that all of a sudden, about three months ago, I started adding a bunch of Asian languages.

Well, what does that tell you about what I’m up to? Either I’ve decided that Asian languages are interesting and fun, or my organization, I mean, presumably I’m doing this for work and not fun, or my organization is launching into Asia. And I don’t actually need to see the content to sort of get that piece of competitive intelligence out of it. So essentially.

The way that I’m using the machine translation, even if we protect or have a contract that says you you are not allowed to look at what I’m processing, but if you can look at the parameters of what I’m processing, that might give you enough information to tell you something about what I’m up to.

AP: Yeah, so basically what you request or don’t request, as the case may be, can give away clues that you may not want floating out in the world.

SO: Right, exactly. So now we take this to AI and we think about digital sovereignty for AI, and it gets very much more complicated. So t first, taking this example of machine translation, if you think about AI chatbots and prompting and public-facing models, then in the same way that requesting a particular language so well, let’s back up. 

Let’s say that we have a contract with XYZ model provider and it says we will not use your input as training data. We will not use your output as training data. Cool. But are you going to use my prompts as competitive intelligence? Because think about what I’m prompting on. Hey, tell me about the intellectual property laws in Vietnam.

Tell me about how to go to market in a particular country. Tell me about strategy for pricing tiers, right? If I’m doing those kinds of prompts, then you, as my competitor or adversary or whatever we’re dealing with here, can get an awful lot of information out of what I’m up to, right? You can figure out what I’m up to just by looking at my prompts. So we have to worry not just about the protection of the input and the output, but also the actual prompting that I’m using to get the inputs and the outputs, because the prompting itself has competitive information in it. So then when we start thinking about digital sovereignty, you say, okay, well, then what we should probably do is have a restrictions on usage of input, output, or prompting data by the vendor, right? The vendor who’s providing the AI model should have a contract that says we are now not allowed to use this stuff.

But then we take that another step forward. Nearly every contract I’ve seen in the past, you know, whatever years, decades says we promise not to use this unless we’re required to by law. So in other words, if a government subpoenas us, we will cough up this information as we are legally obligated to do, that sends us right down the road to something called zero data retention. Which is the idea that you process your AI prompts in such a way that they are not retained, that the inputs and outputs are not retained by the provider, so that if they are subpoenaed, they cannot in fact cough up the information because they don’t have it.

And then if you’re more paranoid than that, and some of you, you know, depending on what industry you’re in, should be, you start thinking about bringing the model in-house. So instead of using public-facing with a an enterprise contract of some sort, you think about bringing the model onto again, in-house on premises in the same way. This is right back to cloud versus not cloud.

And then we have some questions about what model are you using and do you know what’s going on in the internals of that model, which points you maybe at using something open source or maybe not. It depends. But there’s all these layers of decisions that you have to make around how you’re going to use AI and how concerned you are about leakage from your use of AI to you know your competitors or something else. 

Now, over the top of that, we start thinking about nations rather than organizations. And we have some of this with just generalized cloud systems. GDPR, the European Data Protection Regulation, says a lot of things about how you process personal information and what the requirements are and what you are and are not allowed to do. Now

If you’re a European company inside the EU, you’re clearly subject to GDPR. But many non-European companies are also subject to GDPR because you have a server in the European Union, or you have customers in the European Union, or you operate in some way in the EU, which then that’s enough to have you sort of folded into GDPR.

On the AI side, we have something very similar going on where companies are looking at AI models and making decisions based on what jurisdiction does that model belong to. Now, the most prominent of these is that, for example, currently, as of right now, as we’re recording this, the American models, like a ChatGPT, a Claude, that kind of thing, are largely not available in China. and it’s a little bit tricky in terms of is it actually banned or is it just restricted, but broadly not available. The Chinese models are available in the US and are open source, but if I’m an American or actually, let’s say I’m a European company and I’m trying to figure out my AI strategy. Do I use an American model? Do I use a Chinese model? What happens if I’m using a Chinese model and then the US government bans that model in the US and I have operations in the US? And I’m suddenly now what? 

In reverse, if I’m a an American company and I’m using American US models, and I have, let’s say, a chatbot, and I go to market in the EU. I am now subject to the EU AI Act. And the EU AI Act, with some complications for when it goes into effect, et cetera, has rules that say things like: if you put up a chatbot, you have to disclose that it’s AI. You can’t pretend that people are talking to a human. You have to say this chatbot is AI. This image was generated by AI. there are disclosure requirements in the EU. That are much more stringent than the disclosure requirements, which are none in the in the US.

AP: Yeah. In the US. And again, if you were making decisions about what model to get, where you should place your servers, etc., we highly recommend that you speak to your intellectual property attorneys and do not take advice from the two of us. Thank you very much. 

SO: Right. This entire podcast is just an ad for IP lawyers. You’re welcome, IP lawyers.

AP To me, this whole thing is so interesting. You know, we talk about the digital world and globalization and you know, there’s no boundaries anymore. Guess what? They very much apply here because, like you said, if you have customers in the EU, and you may be a US-based company, but that does not give you clearance to absolutely ignore GDPR. So we still have to be aware of geographical boundaries and the laws of all the nations inside those boundaries.

SO: Yeah, the thing that keeps me awake at night is the question of what if I build out an entire thing on some model? It it kind of doesn’t matter which one, but I build an entire infrastructure based on some AI vendor and then and then that AI vendor gets banned by a government whose jurisdiction I or my operations are subject to. 

AP: But there are significant costs.

SO: Right. And I’m not picking on any particular country. It it could go every which way that you can imagine. So then as a as an organization, especially if you’re a big international organization, you start thinking about well, maybe we should bring all this stuff in house so that we can control it.

AP: And infrastructure involved with that decision.

SO: Right, because now we’re talking about you operating your own data center, and that makes you, you know, not so beloved by literally anybody. So I mean, this is a really hard problem. And what’s fascinating to me is that we generally in software, software as a service, generally cloud has pretty much won with some minor exceptions for air-gapped systems, high security systems, network operations centers, or you know, software that runs utilities, that kind of thing. Things where you really, really, really do not want it taken down by external things. So you have this idea of secure systems, air-gapped systems, systems down at the bottom of a mine that are cut off because they’re literally down at the bottom of a mine.

AP: Yes, inside the earth, correct.

SO: We used to talk about airplane help, but that’s much less of an issue anymore because now, for better or for worse, we have Wi Fi on the planes.

AP: Yes.

SO: Mostly for the worse. Anyway…

AP: At least I haven’t heard a meeting yet, an online meeting. I’m sure it will happen at some point, but I have yet to see that happen. Thank goodness. 

SO: On a plane? Yeah. Hmm.

AP: Yeah.

SO: So anyway. So cloud, the risk-reward for cloud versus on-prem has pretty much tilted towards the cloud systems in general, with you know, very specific kinds of exceptions for I would say unique use cases, but it’s kind of like a ninety ten or an eighty-twenty kind of split.

Back in the day, it was everything was on-prem and cloud was the exception, but it’s it’s very much shifted. And now with all this AI stuff, everybody’s using currently big picture. As everybody’s adopting AI, they’re using public-facing models, public-facing chatbots, maybe with like some sort of an enterprise license. But I just have this feeling that a lot of this stuff is going to be brought into in-house at least managed models. 

AP: Exactly. Yeah.

SO: So still sort of cloud software as a service, but with a big enterprise contract wrapped around it that says, here’s what you you, the vendor, the AI vendor, can and cannot do with our data. But it’s a it’s just a really interesting problem because we in content we don’t deal with these sort of national issues that much, like sovereignty at the national level. And I think that with AI systems, we’re seeing a lot of concern around, well, what does it mean that this might be regulated differently in different countries? And how do we manage that? I mean, how do you put together an AI content ops strategy if you are not sure whether your model will be available in that country over there next week.

AP: Yeah, and I’m just thinking, think about audits are often a component of a contract, and you add AI on top of this, and all of the jurisdictional things you’re talking about, all of the facets of those audits just got even more complicated with AI than they already are, which that is probably a whole other discussion. Again, not a lawyer, don’t want to be, but I can see that being a very contentious something that’s gonna have to be ironed out in the very near future.

SO: Yeah, so digital sovereignty, it’s it’s very hard to say and even harder to spell. but I think that it’s something that we should be thinking about as content people and we should at least understand the big picture of what’s going on so that when we go to our corporate legal team and say, Hey, we’re worried about this, we can at least have a reasonable conversation about where this is going.

AP: And again, we don’t know where it’s going, but it’s definitely something to keep an eye on. This is a great place to wrap up. Sarah, thank you very much for a conversation that I frankly haven’t heard a lot about in the content world.

SO: Well thank you. Not a lawyer.

AP: Nor am I. Until the next time everyone, thanks. Bye.

SO: Bye everybody.

Subscribe to our monthly newsletter for more insights on AI, content ops, and more!

var gform;gform||(document.addEventListener("gform_main_scripts_loaded",function(){gform.scriptsLoaded=!0}),document.addEventListener("gform/theme/scripts_loaded",function(){gform.themeScriptsLoaded=!0}),window.addEventListener("DOMContentLoaded",function(){gform.domLoaded=!0}),gform={domLoaded:!1,scriptsLoaded:!1,themeScriptsLoaded:!1,isFormEditor:()=>"function"==typeof InitializeEditor,callIfLoaded:function(o){return!(!gform.domLoaded||!gform.scriptsLoaded||!gform.themeScriptsLoaded&&!gform.isFormEditor()||(gform.isFormEditor()&&console.warn("The use of gform.initializeOnLoaded() is deprecated in the form editor context and will be removed in Gravity Forms 3.1."),o(),0))},initializeOnLoaded:function(o){gform.callIfLoaded(o)||(document.addEventListener("gform_main_scripts_loaded",()=>{gform.scriptsLoaded=!0,gform.callIfLoaded(o)}),document.addEventListener("gform/theme/scripts_loaded",()=>{gform.themeScriptsLoaded=!0,gform.callIfLoaded(o)}),window.addEventListener("DOMContentLoaded",()=>{gform.domLoaded=!0,gform.callIfLoaded(o)}))},hooks:{action:{},filter:{}},addAction:function(o,r,e,t){gform.addHook("action",o,r,e,t)},addFilter:function(o,r,e,t){gform.addHook("filter",o,r,e,t)},doAction:function(o){gform.doHook("action",o,arguments)},applyFilters:function(o){return gform.doHook("filter",o,arguments)},removeAction:function(o,r){gform.removeHook("action",o,r)},removeFilter:function(o,r,e){gform.removeHook("filter",o,r,e)},addHook:function(o,r,e,t,n){null==gform.hooks[o][r]&&(gform.hooks[o][r]=[]);var d=gform.hooks[o][r];null==n&&(n=r+"_"+d.length),gform.hooks[o][r].push({tag:n,callable:e,priority:t=null==t?10:t})},doHook:function(r,o,e){var t;if(e=Array.prototype.slice.call(e,1),null!=gform.hooks[r][o]&&((o=gform.hooks[r][o]).sort(function(o,r){return o.priority-r.priority}),o.forEach(function(o){"function"!=typeof(t=o.callable)&&(t=window[t]),"action"==r?t.apply(null,e):e[0]=t.apply(null,e)})),"filter"==r)return e[0]},removeHook:function(o,r,t,n){var e;null!=gform.hooks[o][r]&&(e=(e=gform.hooks[o][r]).filter(function(o,r,e){return!!(null!=n&&n!=o.tag||null!=t&&t!=o.priority)}),gform.hooks[o][r]=e)}});







Name*



First




Last




Email*



Data collection*

I consent to my submitted data being collected and stored.


Review our privacy policy

Consent to subscribe*

I consent to the use of my submitted data for marketing emails. I understand that I can unsubscribe at any time.


Review our privacy policy

Submit


















The post Digital sovereignty in the age of AI appeared first on Scriptorium.