Podcast: Play in new window | Download
Subscribe: Apple Podcasts | Spotify | Android | TuneIn | RSS
Education often lags behind tech trends. Not in the case of AI. And not when Lance Cummings is involved.
Lance conducts academic research on AI content operations and has worked both with technical communicators and with content entrepreneurs in the creator economy.
Along the way he has discovered concepts and practices around structured content that apply across prompt engineering, tech writing, and influencer content creation.
We talked about:
- his work as a rhetoric and writing professor and research on the creator economy
- his view of content operations and workflow, especially new practices around AI
- how the introduction of the idea of “AI content operations” clarifies the writing process for content creators of all kinds, including the technical writers that he teaches
- how a structured-content approach can help writers of all kinds cultivate a garden of ideas
- how the real value around your content lies in interactions with your community, not necessarily the content itself
- his approach to collaborative prompting, knowledge management, and development of AI tools
- how standards and practices like DITA and object-oriented knowledge management
- how structured content can actually make us more creative
- why creative writers generally excel in the tech writing field
Lance’s bio
Lance Cummings is an associate professor of English in the Professional Writing program at the University of North Carolina Wilmington. Dr. Cummings explores content and information development in technologically and culturally diverse contexts both in his research and teaching. His most recent work looks at how to leverage structured content with rhetorical strategies to improve the performance of generative AI technologies and shares his explorations in his newsletter, Cyborgs Writing.
Connect with Lance online
Video
Here’s the video version of our conversation:
Podcast intro transcript
This is the Content and AI podcast, episode number 10. We are quickly discovering that AI can help content professionals across the span of their work. Lance Cummings is a consultant and college professor who is exploring intersections that most content folks haven’t had time to ponder. For example, he has found that his approach to AI content operations can clarify and improve the writing process for both technical documentation authors at big enterprises as well as fiercely independent members of the creator economy.
Interview transcript
Larry:
Hi everyone. Welcome to episode number 10 of the Content + AI podcast. I’m really delighted today to welcome to the show Lance Cummings. Lance is a professor of English in the professional writing program at the University of North Carolina in Wilmington. He does a lot of interesting research, and we’ll talk about that as we get going. But one of the interesting things in the intersections of his research and academic interests is this notion of applying structured content, looking at structured content, rhetorical strategies, and AI technologies and workflows around that. I’m really excited to talk about all this stuff with you, Lance, but welcome to the show. Tell the folks a little bit more about what you’re up to.
Lance:
Yeah, so I’m a professor in rhetoric and writings, which generally just means that we study how people write, make meaning, get things done with text. And more recently I’ve been researching the creator economy, actually before AI. That’s how I stumbled across AI in 2021. And if you don’t know what the creator economy, it’s what this podcast is. It’s people creating content directly to audiences using the various digital platforms out there, and oftentimes either making some money or a lot of money or making a living even off of doing this. I would say different from influencers, I would say creators are creating useful content for their audiences that they can use and very specific audiences. And since COVID that has risen 50% every year, but when you get deep into the creator economy, they really think about content in terms of workflow and how do you create a process to develop content consistently, and how do you be creative?
Lance:
Because as a content creator, you have to consistently build content for your community. I stumbled upon AI and I thought, “Well, we’re all going to be using this in two years,” and here we are. And so I’ve been exploring then how AI works into the writing process, both in my own content development and also among creators. And then thinking about that in terms of technical writing, content and content management. One of the things that I think content specialists or tech writers have to offer us is a more structured conception of content and how that works into this idea of workflow. I was at a conference, I go to a conference every year in Krakow called SOAP, and last year the topic was content operations, which it seems like that’s a term going around a lot. And we just simply defined it as the people, processes, and things that are around content creation.
Lance:
So thinking about writing as a networked activity of relationships between us and people and the technology, and then thinking about how that shifts and changes. And that’s what we would call a workflow, rather than thinking about, “Okay, here’s step one of the writing process, step two, three, four, five,” thinking of it, “Okay, here’s the network of things that are happening to make this content work.”
Larry:
One of the things we talked before we went on the air a little bit about, that workflow, I think anybody who has done any content operations has a conception of workflow in their head, but there’s a specific meaning to workflow in the academic world, which I wasn’t aware of. Can you talk a little bit about, well, first that academic meaning of workflow, like when you’re teaching professional writers or professional writing skills, how you think about workflow and then how that is applied in your current work in AI.
Lance:
So workflow is really, we’re trying to make a shift from thinking of writing just as a process. So the traditional way of teaching writing is actually based on the canons of rhetoric, but you brainstorm or come up with ideas, you organize those ideas, then you draft, get peer review, and then publish, right? Well, I guess thinking in terms of workflow is thinking about content much more from the software development side where content is actually constantly changing, shifting, and people who create content or write are constantly thinking about how to change or tweak their workflow. So it’s not like a number of steps set in stone, but rather this network of actions or interactions that we have with people and things that are constantly changing on their own, but then we can also find points where we can tweak those to make it more efficient, more creative, more interesting.
Lance:
And I think that tech writers or content specialists have been doing this for a while. The best content writers that I know are constantly tweaking their workflows and adapting, and I think that’s why you see a lot of content creators, tech writers, adopting AI fairly early because it’s an easy next step to think about AI as where does it fit into this workflow, rather than how does it take over this part of writing? So integrating AI in a way that extends what we’re doing and enhances our workflow, but doesn’t necessarily take over.
Larry:
Yeah. That’s a great way to think of it. I think some executives just think of it, “Oh, we’ll just replace people,” but it’s like, “No, we can extend and enhance the work that we’re already doing.” As you talk about that, some of the specific ways that AI can fit into this, because conventionally, I just think that AI is, I think Sam Altman said AI is really good at tasks, but not very good at jobs. And so are you looking at it that way, as what are specific tasks in these workflows that AI can help you with? Is that where you start?
Lance:
I think task is an important way to think about AI because if you don’t give it a clear task, it doesn’t necessarily know what to do, but then you have to think about writing your workflow as a set of tasks. So when you start to think about what you’re going to create for this blog, what is the task that you’re technically doing in this workflow? I think a lot of times, especially good writers, a lot of what we do is intuitive, implicit, but we don’t necessarily always explicitly can say what we’re doing as writers. And actually, I think this is one of the best things that AI can do for writing education, is to force us to think about, “All right, what exactly am I doing when I’m creating this piece of content? What are the tasks, and can AI do this task? Should AI do this task? Will AI do this task?” And I think that’s part of what I would call AI content operations, is actually deciding what AI can do or should do and when, and I think task is probably one of the better ways of thinking about it.
Larry:
Yeah, I’m really curious now how you tease that out, because as I think about that, so much of writing used to be perceived as magic, just like you just think and magical things happen. But like you’ve mentioned, both the creators and the creator economy and tech writers are really good at analyzing what they’re doing. Are they exemplars or just lucky in the kind of work that they do requires them to be reflective and curious about where did that intuition come from? How can I tease that out and get better at that? Does that make sense?
Lance:
Yeah, I think tech writers are forced to do that in their … Obviously it’s going to depend on the context, but if you’re working with people, you have to make your workflow explicit to them if it’s going to be successful. If you’re working with AI, actually, you have to make your workflow explicit. And I would say good writers still can explicitly talk about their workflows. It’s not like it’s not a thing, but I think tech writers are just used to doing it. I suppose also, you’re also used to explaining things clearly in a structured way, so that helps as well.
Larry:
Yeah, I’m really curious about that too, about the application of … Because I think don’t think a lot of people would tie those two communities together, the creator economy creators and tech writers, but it sounds like there’s a big overlap that you see and how they extract that out. And then does the way that they use AI in their workflows, does that look pretty similar or do those two different categories of content work entail different AI workflows or different AI elements in their workflows?
Lance:
Well, I think the essence of a workflow is that it is contextual and individual and specific, but I do see an overlap. I’ve put it under the term information and content development. So if you’re a creator online, you’re creating information, you’re creating content, actually if you’re writing anything, you’re creating and developing content, not just generating text. I think that’s really the key distinction that I’m trying to make there. But in the creator economy, they call it the creator flywheel. And when you look at it’s very similar to agile processes or lean. In fact, one creator, Nicholas Cole, he calls it lean writing, but basically writing in small chunks online in public places, and you’ll see me doing this on LinkedIn, so you post often on LinkedIn testing ideas. So you write about one idea in a very clear way and see how people react to it.
Lance:
And you do this basically every day, and you’re testing that. And then once you see what’s working, you create something longer, like a Substack post or a blog post or a newsletter, either by putting together those chunks of ideas or expanding one of those ideas. So thinking about basically your content as a garden that you’re constantly cultivating and growing, making better. And I think that’s what content specialists and technical writers do, at least in the ideal situations where they’re given the resources to develop and grow and prune content for their audiences in a way that is personalized and useful, and not just writing content that we think should be there, but writing content that we know our audiences, our users are finding useful.
Larry:
So I love that, the writing itself as part of the research. Usually you think of, it’s not hard to think about doing the research first and then crafting something, but you get a thought, an idea, and that’s part of your research process, is posting these small snippets to test and then working with them. Yeah, I love that. I also, I love the idea of you’re cultivating your content garden, but as soon as you said that, I was like, “That notion of workflow optimization seems very 20th century management optimization kind of stuff, and cultivating a garden is not the opposite, but it’s a way different thing.” Is that just me being pedantic and about the metaphors we’re using? Or have you thought about that, the cultivation versus optimization?
Lance:
Yeah, if we want to get real academic, but you can think about the several shifts in economy that we’ve already had. The Industrial Revolution changed how we thought about content. The printing press changed how we thought about content. The web then changed it. I’m trying to actually think of a term. It’s Web 2.0 technologies really changed content in that we can actually interact and create content on our own and not send it to a publisher. And I think the creator economy is actually a new kind of economy that’s emerging, that optimization is part of that, but it’s not about thinking content in terms of factory, where once you get those steps in place, you just automate it. And it’s all about just getting as much content out there as possible, the more money. If you think about education in terms of optimization, it’s like, “How can I get as many students through this class as possible with these outcomes or whatnot?” Whereas I think the creator economy, it looks on surface that content is where the value is because everybody’s creating content.
Lance:
But really, I think the value is in the interaction in the community around that content. And that’s where the value is, especially with AI now, where you can create decent content pretty fast without even thinking about it, but the successful creators actually have a community of people that are interacting around their content, you can actually get most of their content for free. And I think businesses, corporations, nonprofits, are going to have to start thinking about content in those terms. How can we cultivate community around our content, not just deliver this list of content that we think should be out there, but actually how do we deliver a content experience to our users? And many people are already thinking about that in those terms, but I think the shift isn’t just for creators, but it’s going to be for everybody, especially with the rise of AI.
Larry:
Yeah. You’re reminding me, I don’t know if you listened to it, but you probably know Sarah O’Keefe, she’s in your neck of the woods at Scriptorium. I had her on the podcast a few episodes ago, and we were talking about, because she’s really concerned with precise, accurate, good content to support products, but she was talking about the guy fixing tractors and just taking videos with his iPhone and probably giving as good of advice as whatever. So this is where you’re making a tidy little bow on that little part of that conversation. But yeah, is that a classic example of a creator, like the guy just shooting videos of how to fix a tractor on his iPhone? Because I always think of the creator economy is like, I don’t know, digital nomad travel enthusiasts or fashion people or something like that.
Lance:
Well, yeah. People who are selling the creator economy are going to sell you the digital nomad. There’s a lot of people buying into the creator economy. One could see some aspects of the creator economy as somewhat of a pyramid scheme, but I would say the guy doing repair videos for tractors is for me, the ideal creator because what he’s doing is he’s creating content that he cares about in ways that’s useful for his specific audience. And he is probably not that concerned about how professional it looks. It probably gets better as he continues. And I think that’s one of the key aspects of the creator economy. It’s not so much, we call it ethos and rhetoric, but the persona or the character that you’re building online, it’s more about being authentic than it is about being polished and professional.
Lance:
So most of the creators started out with really terrible quality videos, but people found it useful, and then they just continue to grow from there. So yeah, I actually would definitely consider that guy a creator and maybe an ideal one because he is building it on stuff that he’s already doing. Everybody’s an expert in something, everybody has something useful to share. This is one of the things I would try to communicate to my students who aren’t usually used to people telling them, “You have expertise, even as a college student.” It’s just a matter of figuring out what that is and what people need from that expertise. And you can get an audience online pretty easily.
Larry:
Hey, I want to shift gears a little bit, because I want to make sure we get to this basically. We were talking, I think before we went on the air, about your approach to structuring prompts, and there’s a whole thing about the knowledge management around how you curate them and keep them. But one of the things I was most intrigued with is how collaborative you think the most effective prompt engineering is. Tell me a little bit about that, your approach to collaborative prompting.
Lance:
Yeah, so really, I think the best writing is collaborative and done in teams or in diverse groups, just like problem solving is best done in diverse groups. And so I actually think developing AI systems, not just prompt engineering, but developing AI systems, developing a prompting process is best done collaboratively. I think we often are shy about sharing our prompts or the things that we’re doing with AI, at least I know, I think in the education field that’s true. I feel like it’s somewhat true in other areas, but we’re either ashamed to admit that we’re using AI or we think we have some sort of secret sauce that we can sell sometime. And I actually think that especially when you’re thinking in terms of the workplace, that working together on prompts is going to deliver better outcomes because you have more perspectives on that, more people testing it, more different ways of thinking about it, and also making it more structured.
Lance:
So what will not only help the team think about the prompting process, but also probably help the AI be more consistent. One of the things that I’ve been thinking about is you can throw a bunch of prompts in the library, you can tag them or whatever, but how do you make it in a way that’s reproducible or usable across teams? And I think knowledge management definitely is going to have a lot to do with AI in the future. But even just thinking about the prompt process from that perspective, what’s the ontology behind our prompts? What’s the framework that we’re using? What’s the taxonomy of tags, I think can really improve how a team is using prompts, especially within AI system. Because really developing content with AI, it’s not just about prompting, it’s about developing a system. It’s about operations, right?
Larry:
Yeah. Yeah. No, and as you’re talking about this, you invoked the phrase knowledge management, and you’re talking about ontologies and taxonomies, that implies quite the system. I’m almost picturing the design system in the design world or content management system or something like that. How organized are you? Do you have spreadsheets or databases or how organized are your prompts at this point?
Lance:
So I’m actually still exploring myself. And so I’m actually testing several different tools that aren’t necessarily industry or corporate tools, but tools that would be accessible to everybody, including creators, because really any tool that you use to organize content can be used to organize prompts. But one of the things that I’ve done is use the simplified taxonomy standards. I don’t remember the name.
Larry:
SKOS, the standard knowledge organization.
Lance:
I actually have AI generate, because you can randomly tag things, but then you get this tangle of tags that you don’t know how they all relate to each other. And so I’ve actually played around with having AI help develop a taxonomy using SKOS, and then either creating a map or a system of folders or slip boxes and putting the prompts in there. I also use TextExpander where you can actually, you have just a keyboard shortcut and it expands a block. So sometimes when I write a prompt, it’s not writing anything, it’s just putting blocks together and then writing a task. And so I wouldn’t say I’m formally using knowledge management. I would say I’m informally using knowledge management to better think about how I’m structuring things and still exploring that.
Larry:
Yeah, I’m intrigued because what you said makes perfect sense, that prompts or any other kind of content you can manage however. I’m sure people are doing stuff in Notion and spreadsheets and who knows what other ways, but that’s super interesting. I want to circle back, and that gets at the structure. We were talking a little bit before we went on, two of your worlds that overlap are the really precisely structured content in DITA in the technical content world, and then is it hacks or procedures that the creators are figuring out to structure their content? Are you finding, is there a learning going back and forth, or how is structure manifesting in each of those realms?
Lance:
You mean are they informing each other, between the two?
Larry:
You’d think that the creators might learn from the structure, but DITA is inaccessible if you haven’t actually worked with it. So I don’t know. But you’ve mentioned structure many times today, and I just want to picture and the fact that you have a knowledge management mindset, if not a fully developed system at this point, just the role of structure in these AI workflows you’re developing.
Lance:
So I would say there’s, as far I know, as not much dialogue and creators don’t use the term “structure” process generally, I think they’re doing a lot of this intuitively. There is a lot of talk about knowledge management, but they’re not referencing the field of knowledge management when they say knowledge management most of the time. That’s why I think there’s productive dialogue to be had between technical writing and content development in the creator world and academia and teaching. Since I encountered, honestly, I encountered structured content just by, it wasn’t really my focus as an academic, but I encountered it when I started developing partnerships in Krakow, Poland. And you may know Patrick Bosek, he makes a pretty good case that most content needs some sort of structure and that we should be taking more structured approach even without AI. And so I’ve actually been playing around with that even in the classroom, even in my own teaching.
Lance:
How do I structure my teaching content in a way that makes it more reusable, easier to use, and now to generate better AI content when I need it? And then teaching students too, I think need to … When you teach a student how to write a science paper or science report, teach it in a structured way, here’s the structure. We call it IMRAD, introduction methods, research, data analysis and discussion.
Larry:
Discussion.
Lance:
And here’s the structure, approach it in a structured way. Now, how can you organize your workflow around that structure if that’s the kind of content that you’re creating? And I do think while DITA is complex, hard to access if we’re not experts, I think it has a lot to add to help us think in those terms, even if it’s just adapting the idea of this topic in reference, or even, I like object-oriented knowledge management. So thinking in terms of what are the objects in my workflow, and how do I structure them in a more manageable way? So yeah, that’s why I find these intersections so fascinating because I think that it’s a clear direction that I think our understanding of writing needs to take now, especially with AI in all fields, but not necessarily always dialogue between those different disciplines, especially in the university where we’re pretty siloed.
Larry:
But I love how you’re busting silos too, between academia and the business world. But hey, Lance, I can’t believe that we’re coming up close to time already. This always goes way too fast. But before we wrap up, is there anything last, anything you want to revisit from the conversation or just want to make sure we share before we wrap up?
Lance:
Well, I think maybe I’ll just add to this. I think a lot of times I end up talking about practicalities. You mentioned optimization. How do you optimize the workflow to make things easier and faster? Well, I think that is definitely an important aspect of AI operations, and especially as content developers, creators, even as teachers, I would argue, and even students are thinking in terms of how can I optimize my workflow to make things easier? I think we don’t want to miss out on thinking about how structured content can actually make us more creative. So how it helps us generate new ideas, new content. I think the misunderstanding about tech writing oftentimes, especially from students, is that, “Oh, it’s boring. It’s not interesting. There’s nothing creative about it. I want to write Harry Potter novels, not instructions.”
Lance:
While there’s elements of that that is true for sure, there are boring things about tech writing, I think there are creative elements, and that’s why creative writers generally excel in the tech writing field. And also there’s creative elements in tweaking and managing a workflow. That is a creating creative endeavor. And you can use AI to be creative, to come up with new ideas, if used in the right way, and incorporated in your workflow in a way that enhances your creativity and doesn’t necessarily take it over. So while I think there’s definitely use cases for taking over mundane tasks so that we can focus on more creative, more important things as writers, I also do think AI has a role in helping us generate new ideas and content. But again, it comes down to learning how to decide when, where, and why to use AI. And I think the only way to figure those questions out is to experiment, and that is why I do most of what I do with my thoughts about AI online.
Larry:
No, I appreciate it. It’s fun to follow you online. And which leads me to my last question. What’s the best way for folks to follow you, Lance, if they want to connect online or just follow your work?
Lance:
So I’ve been sharing my experimentations and some thoughts on Substack. You can get there, www.isophist.com. You can follow me on LinkedIn. I’m pretty active there. Those are the two main places.
Larry:
Great. I’ll get those in the show notes as well. Well, thank you so much, Lance. I really enjoyed the conversation.
Lance:
Yeah, it’s really exciting to see a podcast called Content + AI, so right up my alley, and I’ve been enjoying them so far and look forward to more interesting ones.
Larry:
Thanks. I didn’t have a persona in mind when I created it, but maybe you’re it, now that I think about it. Anyhow, thanks so much, Lance.
Lance:
All right, thank you.
