Podcast: Play in new window | Download
Subscribe: Apple Podcasts | Spotify | Amazon Music | Android | Youtube Music | RSS
Torrey Podmajersky is uniquely well-prepared to help digital teams align on language and meaning.
Her father’s interest in philosophy led her to an early intellectual journey into semantics, and her work as a UX writer at companies like Google and Microsoft has attuned her to the need to discover and convey precise meaning in complex digital experiences.
This helps her span the “semantic gaps” that emerge when diverse groups of stakeholders use different language to describe similar things.
We talked about:
- her work as president at her consultancy, Catbird Content, and as the author of two UX books
- how her father’s interest in philosophy and semantics led her to believe that everyone routinely thinks about what things mean and how to represent meaning
- the role of community and collaboration in crafting the language that conveys meaning
- how the educational concept of “prelecting” facilitates crafting shared-meaning experiences
- the importance of understanding how to discern and account for implicit knowledge in experience design
- how she identifies “semantic gaps” in the language that various stakeholders use
- her discovery, and immediate fascination with, the Cyc project and its impact on her semantic design work
- her take on the fundamental differences between how humans and LLMs create content
Torrey’s bio
Torrey Podmajersky helps teams solve business and customer problems using UX and content at Google, OfferUp, Microsoft, and clients of Catbird Content. She wrote Strategic Writing for UX, is co-authoring UX Skills for Business Strategy, hosts the Button Conference, and teaches content, UX, and other topics at schools and conferences in North America and Europe.
Connect with Torrey online
Torrey’s Books
Resources mentioned in this interview
Video
Here’s the video version of our conversation:
Podcast intro transcript
This is the Knowledge Graph Insights podcast, episode number 39. Finding the right language to describe how groups of people agree on the meaning of the things they’re working with is hard. Torrey Podmajersky is uniquely well-prepared to meet this challenge. She was raised in a home where where it was common to have philosophical discussions about semantics over dinner. More recently, she’s worked as a designer at tech companies like Google, collaborating with diverse teams to find and share the meaning in complex systems.
Interview transcript
Larry:
Hi everyone. Welcome to episode number 39 of the Knowledge Graph Insights podcast. I am really delighted today to welcome to the show Torrey Podmajersky. I’ve known Torrey for years from the content world, the UX design and content design and UX writing and all those worlds. I used to live very closer to her office in Seattle, but Torrey’s currently the president at Catbird Content, her consultancy, and she’s guest faculty at the University of Washington iSchool. She does all kinds of interesting stuff, very accomplished author. So welcome Torrey. Tell the folks a little bit more about what you’re up to and where all the books are at these days.
Torrey:
Thanks so much, Larry. I am up to my neck in finishing the books right now. So one just came out the second edition of Strategic Writing for UX that has a brand new chapter on building LLMs into products and updates throughout, of course since it came out six years ago. But I’m also working on the final manuscript with twoTorrey Podmajersky co-authors for UX Skills for Business Strategy. That’ll be a wine pairing guide, a deep reference book that connects the business impact that you might want to make, whether you’re a UX pro or a PM or a knowledge graph enthusiast working somewhere in product and connecting it to the UX skills you might want to use to make those impacts.
Larry:
Excellent. I can’t wait to read both of those. I love the first edition of the Strategic Writing for UX book, but… Hey, I want to talk today though about, this is the Knowledge Graph Insights podcast, and you recently did this great post and we’ll talk more about it in detail in a bit about how you had discovered the Cyc project, which is a real pioneering project in the semantic technology field and really foundational to a lot of the knowledge graph stuff that’s happening today. But I want to start with one of the other things we talked about before we went on the air was your observation of the kind of common philosophical roots that we have in rhetoric, maybe not necessarily rhetoric, but the stuff that we do as word nerds, as meaning nerds, as all these different kinds of technology nerds that we are. Tell me a little bit about what you meant because you just hinted that and I was like, oh, good philosophy. I love philosophy.
Torrey:
Yeah, I love philosophy too, especially through my dad. My dad was a philosophy major at Haverford College and it has deeply influenced his life and his work in semantic knowledge spaces. And I got to grow up in that context thinking that everybody thought deeply about what things meant and how we represent those meanings. I mean, the Plato’s Allegory of the Cave was my bedtime story to the extent that we all knew Plato in the cave, geez, dad, just fine. Plato in the cave. We don’t really know anything. All we have is facsimiles and representations of meaning and representations of reality, and through that we construct meaning. And I feel like that’s all we’re ever doing is using language to construct meaning based on our inability to fully perceive reality.
Larry:
And just for folks who aren’t familiar, I love Plato’s Allegory of the Cave. It’s these poor people chained to a wall and behind them is a projector projecting stuff on the wall in front of them. So all they see is this projection of an imitation of reality, which is much like what we’re doing with either both UX writing and I think ontology design and semantic engineering. So that’s the perfect analogy to come into this. But your job for the last, I don’t know, because you made the transition from teaching to Xbox, what? 10, 12 years ago or something like that?
Torrey:
In 2010, I joined Xbox and before that I had a short stint in internal communications in a division at Microsoft working for a VP there.
Larry:
But you’ve been in the word biz and the meaning biz for a long time because UX writing is, how did you say it? You have to convey meaning. That’s the whole point of UX writing is to just get past random words to actually, what are we talking about here?
Torrey:
It’s to make the words that people understand so quickly while they’re in an experience, they’re just trying to use it. They’re not there to read. So we want the words to disappear into ephemeral meaning in their head that they don’t even remember. They just knew what to do and which button to press and where to go next to get done what they wanted to get done.
Larry:
And one of the things about that is getting to that language to do that in an experience, that’s a team sport. One of the other things that really struck me about that post you did was the role of community in language and meaning. Talk a little bit about that.
Torrey:
Yeah, it is a team sport because in general, even if it’s the person doing the UX writing or that content design is also the product designer is also the interaction designer. What they’re trying to do is take a wide variety of people who might be using this product that might be an incredibly diverse set of people, or it might be a very narrow set of people, let’s say all IT pros. We want to sell this product to big corporations that have IT pros that want to manage their data centers. It’s a pretty narrow slice of humans, but it’s still hugely diverse in terms of from what language they’re speaking and what kind of resources they have inside this company to the kind of background they have, to all of the different reasons they might need to manage their data centers right now.
Torrey:
From, hey, something new came online or there needs to be a new partition or new admin management of access to it or security patch updates to things like, oh, there was an earthquake at a data center and I need to and secure and audit any damage that might’ve happened. So there’s a huge number of reasons. Let me back up of that deep analogy. There’s a huge number of reasons even for a tiny population relative to the scope of humanity, a small population doing a relatively well-defined job still has a huge number of reasons they might need to be in an interface doing a thing. And what we have to do when we are designing the content for that and designing the experience itself is anticipate those and try and make sure that we’ve indicated that whatever reason they’re coming there for, if it’s a valid reason to use this piece of software, whatever reason they’re coming there for, they see it reflected in the text and they understand what to do.
Torrey:
That is a team sport because I can’t, and no individual person can anticipate all of those things simultaneously. We need to think them through sequentially. We need data to base it on. We need to understand, we need to hear from people who will use it or people who would use it to hear about how they think about it and specifically what language do they use, what’s already in their head that we can use to reflect on that screen. So it’s about understanding that space well enough, coming to understand that space well enough by communicating with other humans to know what are the right things to represent and in what hierarchy or embeddedness or relationalness, and then use some grammar and punctuation and other tricks up our language sleeves.
Larry:
Yeah, no. I’ve done so much conceptual modeling over the years. I did a lot of content modeling back in the day. Well, I still do, and it’s always that. And wherever I get grumpy and want to explain to people why my job is so hard and everybody has a mental model of the world, and as soon as you put two people together, that’s hard enough, and then you put diverse populations like you’re just talking about agreeing on, not a shared conceptual, but understanding everybody’s mental model enough to do the things that you need to do to make everybody feel heard and included. Kudos to you for being able to do that. But it’s also that there’s both the task of getting that, arriving at some kind of shared understanding and ability to convey the meaning of a situation. There’s sort of like that and then there’s each individual, how they’re interacting with it. How do you balance that?
Torrey:
Yeah, a lot of it is about, and I’m going to use an education word here, it’s about prelecting. Prelecting is about, which is a word I didn’t think was a word when I went to education school, and they’re like, “No, no, no, this is totally a word I promise.” Cool. Prelecting is about framing a concept before people really encounter it. Usually it includes sort of seeding that language in, like I just did by saying, I’m going to use this word called prelect. That was a little bit of meta prelecting right there, because here I am introducing a concept so that you are clearing a little space somewhere in your mental model knowing that something new is about to come. And so doing that context setting so that people have an entry point to it so that we can say, “Hey, I’m going to tell you a thing and it’ll connect to these concepts you already know.” And as long as you have a trust relationship there, people will tend to at least start to form a connection to that part of their internal knowledge architecture and you have more access there.
Torrey:
So in say, a UX flow, what I might do is say, oh, here in this 20-screen flow that’s deeply important, and let’s use IT pros as an example again, because it’s that concept of people who need to manage big data systems. I personally am not one of those people. I have worked on some of their tools. What I do understand is that they have a lot to keep in mind. It is massive systems and they are pretty robust systems, but if you screw up along the way in doing any of these things, it can have massive consequences that take days to fix and recover from. Nobody wants that. People want to be doing exactly the right thing and never take a false step. So in that context, so let’s take these IT pros. Here on step 20 in a 24-step sequence to do a thing, they need to understand some concept or they need to have already had some piece of information so that they can make the right decision in that moment about it.
Torrey:
Well, if it’s a sufficiently distant idea from that, like, oh, right, you’ve been setting up this data center in Kansas and you also need to know about the security keys for your data centers around the world right there so that you can give it a unique one. I’m making something up. It actually would never happen that way, but just something that is distant that you wouldn’t be in that corner of your mental model right then. So then what I do as a UX pro is I come in and I say, “Hey, can we hint to them earlier that they’re going to need that, that they’re going to need to be able to access that part of their mental model, even though it probably feels very distant.” And I might not hint to it on screen 1 of 24 when they don’t need it till 20, but I might think about how are these things chunked up? Where is the earliest point that it would be meaningful to bring up that they will need access to this distant information and can we seed it in right there?
Larry:
I love that word, prelecting. I’m going to add that to my vocabulary, but also the way you were just describing that, it’s like I’m trying to figure out the analogy because I think there’s something similar that happens in a semantic engineering project. The whole point, and this is another thing you mentioned in your post, is to capture implicit knowledge and tacit knowledge in people’s heads and implicit information that people have so that you can do stuff with it, so that it’s not just in somebody else’s head, that you have a shared understanding or a shared ability to act on that information or that knowledge. Does it make sense to try to stitch that notion of prelecting to that capture and sharing of implicit knowledge?
Torrey:
Yeah, yeah. In that context, I would connect them by saying that the implicit knowledge is sort of the internal framework that we tend not to be aware of. We tend to ignore it. It’s the plumbing in the buildings or the electricity coming through the walls. Unless we are the plumber or electrician, we just think it’ll work. And sometimes we have to go looking for an outlet or look for the bathroom, but we expect it to be there. We depend on it. We expect it to work in a variety of ways that is extremely routine. Now, our implicit knowledge is something that most people don’t think about most of the time. That’s what makes it implicit. It is the stuff we don’t talk about. Here I live in the Puget Sound and the Pacific Northwest of the U.S., and we have a ferry system to cross Puget Sound from various locations to various locations.
Torrey:
You can drive on most of the ferries. You can also be a walk-on passenger to most of the ferries. How to engage with those ferries is intimidating. I have definitely met people who are scared to engage with this because it looks intimidating, because it is poorly communicated how to do the things. You drive into some lanes, you might be given some information if you’re driving on, you drive up to a kiosk and that follows a regular mental model. You drive up to a window and somebody is there and asks you how many people in your car, and you give them money and they pay you. You probably as a driver have that implicit knowledge but what happens after that?
Torrey:
If you live in the area and you ride the ferry regularly, you know that you drive into a lane that may or may not be near the front or the back. The lanes are numbered, but does that have any meaning? Nobody knows. The person at the kiosk may tell you, oh, go to lane 9 or 10. Is there a difference between 9 or 10? I don’t know what’s happening here. You go to a lane, you park and everything seems to be fine. If you leave your car running, people might give you dirty looks. There’s so much implicit knowledge there. Eventually somebody might come and eventually cars will start moving and you go, “Oh, should I start my car? I don’t know.” And you go with the flow. You get directed maybe well, maybe poorly into a spot on the ferry. It’s your first time there. You will definitely leave too much space in front of you on the ferry, and then you’re just there and there’s announcements that you can barely understand over the loudspeaker. So I will quit because-
Larry:
I love that analogy though, because I think it points to, there’s so much implicit knowledge, like the ferry guy, the people in the reflective vests guiding you. They’re just like, come on, you’re an idiot. So the idea is somehow get that tacit knowledge out of their head about, no, here’s how you behave in a ferry line and somehow convey that to people. So I think maybe the big lesson here in both UX work and in ontology design, any kind of modeling the knowledge in a domain, you have that discovery project and a lot of those cues, you mentioned 9 or 10, does it matter or what do I do? Why are people staring at me? Oh, my engine’s running.
Larry:
Seeing those kinds of little glitches in the matrix of your environment as cues, because if you hear when you’re doing conceptual modeling or knowledge modeling, if somebody says, “Well, just ask Jill, she knows that.” And you’re like, ooh, your antennas go up, and you’re like, okay, we got to not just talk to Jill, but her contemporaries and all that stuff as well. So is that those insights you just shared, and I love the ferry example. Are there lessons out of that that you apply in your discovery work about what is our shared meaning here? What does it mean if you leave your engine running?
Torrey:
Absolutely. There’s this thing that happens when I’m talking with a team in a discovery process or even working deep within the UX where I’m saying like, oh, okay, so the problem here is low adoption or low understanding or high support costs. And I’m coming in going, okay, which parts here might be confusing? And I am rarely the intended user for the thing. So I listen to the engineers, I listen to the PMs, I listen to the UX designers, I listen to users, if I have those available to me and I go, I am listening for those little cues, those little signal words, and especially when I hear, say, my engineers or PMs use words that are, especially, they’re saying using a word, that maybe I think I know this word, but they seem to be using it in a special way, and especially they seem to be frustrated that other people don’t get it.
Torrey:
And the real tip-off is when they’re using a word and nobody else is, and I think, oh, here is a break in the mental model between people in this group. And so it’s not being reflected. This is a semantic gap in the UX itself where this is not being communicated. This is not being conveyed. And in those cases, I most frequently use the word, “You keep using that word. I think I know that word, but I might not be understanding it the way you intend. Can you walk me through or explain to me like I’m five?” And usually people are either very willing to explain it right then or are just exasperated, how could you not know this obvious thing? And I say, “Oh, I’m very sorry. I don’t know this very obvious thing, but let’s walk through and I promise I’ll do better in the future.” And in general, those are the moments. Listening for those little things is tough.
Larry:
And the role we both occupy in that world gives you permission, a lot more permission to do that than if you’re the guy and the person in the next cubicle who just assumes you know what it means. That’s kind of our job to tease that out. But that notion of shared meaning, and I want to go back to your dad and the Cyc project because that was one of the things that was in there and that excitement you had when you discovered the Cyc project. And I was like, why is she so worked up by this? Oh, her dad was a philosopher. But also the connection between language, semantics, meaning, accomplishment, it’s like the reason we align around these things is so we can do stuff better, navigate a UX experience or organize a bunch of knowledge. You heard about Cyc from your dad? Is that right, or?
Torrey:
I did, and just a little bit before I sent out that newsletter because it struck me like a ton of bricks because I had been thinking about community and worldwide community of people working in these knowledge and content spaces and how we have barriers within that community. Whether they’re language barriers or location or status or access or all of those. Then we were talking about AI and various AI things that become available and the affect of AI usage on people and how that is just barely being studied right now, really. But those effects are very interesting. Some are alarming, some are just fascinating. And he brought up, “Well you know the Cyc project.” And I went, “What is this thing?”
Torrey:
And it really put a pin in connecting all of these ideas that LLM’s, for example, are built on understanding. And by understanding I mean creating vector relationships based on how different tokens within language are represented and used in repetitive ways. So by consuming an enormous quantity of content, it “learns”, and by learns, I’m using air quotes with my fingers right now, it constructs a probability matrix to understand that. And here’s where language just isn’t adequate because it is not an understanding. It is a construction. Cool construction, incredibly powerful, wow, but it’s built on things that we actually are willing to talk about. There are hundreds of things you can look around your space right now and think about. I wouldn’t talk about that, the molding around my window and how I feel about it, right?
Larry:
No. And when the threshold to want it does become worthwhile to tease it out or to even call it out. Like you said, there’s so much implicit knowledge. And that was one of the things in the Cyc project was this attempt to capture common sense knowledge and just facts about the world. And I think they got up to a million and a half representations of knowledge in the world, concepts that you could do something with in a system, which is what knowledge engineering is all about. It’s just fascinating stuff. And go ahead.
Torrey:
I am fascinated with just the way they had to construct the axioms. How do I tell a computer that this is a fact? How do I tell a computer that this is an object and this is a fact about its relationship to another object? And those are problems that is, I think the water you swim in right now, and it’s been worked on in part by this project, the Cyc project, and establishing how to codify those things in a way for it to be useful to computers is the foundation on which these LLM vector spaces could be built?
Larry:
Well, I was at the Semantics conference in Vienna last week, and that’s all… This has been a topic of conversation in the knowledge graph world since, well, the last three years, and it’s been sort of in the air, but this was the first conference, I’ve been to most of the conferences the last four or five years, this was the first time where every single session and every single hallway track conversation was about this complementary nature. A lot of what you’re just talking about. And you really articulated well both the power and the limitations of LLMs, how they observe and make predictions about the world, and then the benefits of organizing knowledge about the world. And so anyhow, the two turn out to be extremely complementary. That’s literally the whole theme of that conference.
Larry:
We won’t figure this out in this conversation, but I’m really curious about how these kinds of insights, this kind of back and forth between those two things and the back and forth between the evolution of UX practice and UX writing and content management and content design, and it just feels like there’s going to be a productive relationship there as well. My fingers are crossed that there will be more attention to meaning. And this is one of those things as a craft, as a discipline, I feel like we just need to tease out your implicit knowledge about imbuing meaning in user experiences and get that in an ontology, and then we can have better UX systems out there.
Torrey:
Well, right now I’m working on the knowledge graph of connecting UX skills and what those can do to business impact. I wish that I could make the same book just about that semantic knowledge. When we do semantic design, it has effects on every level of the interface and every level, not just of an interface, but of an experience. That was one of the skills I was writing, like look at all of this design, semantic design, and it was too big for one UX skill. And right now we have it captured as design for structure, design for the implicit structure within the domain and experience and actions that need to be taken. But it feels like itself only a pale shadow of what it could be.
Larry:
Yeah. We’re coming up on time, we need to wrap up. But one thing I want to say, I hope you know Andy Fitzgerald in Seattle. Did you meet him? Yeah.
Torrey:
Yeah.
Larry:
And in terms of the link between the UX world and the semantic world, you two should collaborate. I’m just going to throw that out there because-
Torrey:
I don’t know him well, I think we’ve been introduced a couple of times.
Larry:
Well, one of the projects he did to play with, to experiment with and show the benefits of semantic technology, he did a website called uxmethods.org, which I hope you’ve discovered it because you can add the business layer to that. I think that was more about practice. But anyhow, but hey, we are running close to time, but before we wrap up, is there anything less, anything we haven’t covered in the conversation or that you want to revisit or just want to share before we leave?
Torrey:
Yeah. When you had reached out to me initially, you were like, “This thing you said in this post, I want to make sure we mention it.” So I’m going to bring it up that I had written again about LLMs, that the LLM word generation, the generation of content, is all about sequencing the next word to include. And this is why so many of them gave such long responses in their early days because like, oh, I bet that there will be something in here that is exactly what you want, but as a professional content creator and user of content to create experiences and create business impact … most of the work, absolutely, a huge percentage of the work is about deciding what to leave out. I don’t want to just keep sequencing the next word in a line in case I might cover the topic someday. I want to leave out everything that isn’t germane to this moment for the populations that need to see it.
Larry:
I love that. I’ve seen many observations about the capabilities and limitations of LLMs, but that’s one of the best ones that… And especially in contrast to what humans bring to the writing process. That’s lovely. Hey, one very last thing, Torrey, if folks want to connect or follow you online, what’s the best place to find you?
Torrey:
Best place to find me is on LinkedIn where I’m the only Torrey Podmajersky on LinkedIn. They can also come to my website catbirdcontent.com, and there’s a variety of ways to get in touch with me there.
Larry:
Excellent. And your newsletter is great, and it led to this conversation. So thanks for that.
Torrey:
Yes.
Larry:
Well, thank you so much, Torrey. It’s always great to chat. This was a particularly good conversation.
Torrey:
Thank you so much, Larry. Always a pleasure.
