"The end result is to create something useful and meaningful for other people. It's not about the tech; it's about how you get the tech to transcend itself—to the point where other people will say, 'Yeah, I want that thing, that thing can help me."
What do you learn after spending 15 years at Apple and demoing your work directly to Steve Jobs? Ken Kocienda, Co-founder of Infactory AI and author of Creative Selection, joins us to share the answer. As a former Principal Engineer at Apple who helped create the iPhone keyboard and autocorrect, Ken discusses his incredible journey from a history major to a key figure in building technology used by billions. He explains his core philosophy of bridging the gap between the liberal arts and technology to create meaningful products, and why he believes AI is the next frontier for this mission. (BTW – we sat down with his co-founder Brooke, so if you like this episode be sure to check that one out!)
The conversation dives into his disciplined, spec-driven approach to coding with AI and the power of "extractive AI" to unlock hidden value in data. Ken reveals the crucial lesson he learned from Steve Jobs—that "everything is provisional"—and how his "evolutionary design" process is perfectly suited for today's AI challenges. This episode is a deep dive into the timeless principles of design and a powerful argument for why the best technology is so intuitive, it makes technical literacy irrelevant.
Show Notes
- Learn more about Infactory AI: infactory.ai
- Connect with Ken on LinkedIn
- Ken's Book: Creative Selection: Inside Apple's Design Process During the Golden Age of Steve Jobs
Transcript
(Disclaimer: may contain unintentionally confusing, inaccurate and/or amusing transcription errors)
[00:00:00] Andrew Zigler: Welcome to Dev Interrupted. I'm your host, Andrew Zigler, and today we're sitting down at the Engineering Leadership Conference here in San Francisco, and my guest is Ken Kocienda. Ken Kocienda is this co-founder and CTO of Infactory ai. He's a software engineer, a designer, and an author who spent over 15 years at Apple creating technology used by.
[00:00:23] Andrew Zigler: Billions we're talking autocorrect, multi-touch keyboard and the technology behind the Apple Safari browser and so much more. And before Apple, Ken's path was anything but typical. After graduating from Yale with a history degree, he spent time in Japan, uh, before pursuing fine art photography, and then teaching himself programming and eventually working at Apple.
[00:00:45] Andrew Zigler: you know, our, For the Dev Interrupted listeners, if, if they've been listening for a little bit, they know that a lot of my background is similar to yours.
[00:00:51] Andrew Zigler: I, I also studied history and I also taught in Japan for two years. I wanted to ask about your path into technology. It wasn't direct. It's like my own. [00:01:00] Um, and, and how have your experiences outside of tech shaped the way that you stepped into it?
[00:01:06] Ken Kocienda: for me it's always been about doing projects. Project, uh, project when I was doing fine art photography was that there were, there were parts why I went to Japan because I wanted to build a portfolio of photographs from this fascinating place and, and, and culture that I was interested in.
[00:01:23] Ken Kocienda: And so to me, the connection of liberal arts to technology has always been, has been, has been about. it's almost like what this, this generation, this period of technology is about. We bring more things from the, the world of culture and liberal arts and, and the humanities into technology.
[00:01:44] Ken Kocienda: That's what it's been all, all, all about my career. I mean, I, I was, uh, a freshman in college when the first Macintosh was, was made. So, so graphics. Became a part of computing. Uh, and then, uh, pervasive networking became part of [00:02:00] computing with, uh, with the web and then of course then with mobile. And, and so, uh, one of the examples that, uh, uh, I, I think is also applies is that it's photography.
[00:02:11] Ken Kocienda: Is, is now such a big part of people's daily interactions with their phones, with their technology. a full circle experience for me was I was working at Apple when, uh, the portrait, uh, uh, effects were first being developed and I did some of the early prototype work there. So, so that's the journey.
[00:02:27] Ken Kocienda: Yeah, it's taking the experiences from a non-technical context and figuring out when and why and where, and how can that be incorporated into the latest sort of tech stack. It's to me, you know, we're gonna be talking about AI a lot. That's the opportunity for AI as well. That's the moment we're in.
[00:02:48] Andrew Zigler: Yeah, no, I completely agree. I think that right now there's a revolution happening within engineering and a lot of folks are rediscovering basics and Bri bridging into technology [00:03:00] things that never touched it before, and it's a really exciting time and it, you know, talking about your own experiences being back in college and the Macintosh dropping, I wonder about like in those hype cycles that you've lived through, you know, the Macintosh comes out, traditional graphic artists, revolt against the.
[00:03:15] Andrew Zigler: Idea of creating computer technology even before that, um, when you had like computer assisted design, like CAD technology and no longer, you needed a room of architects constantly drafting. And these, these, uh, evolutions and how we solve problems, you know, they altered the work that those workers did, but it.
[00:03:34] Andrew Zigler: Unlocked for them the ability to do higher level work. And you know, you, like you said, we are gonna be talking about AI some in this conversation. And so I'm curious like what are some of the opportunities you see right now in tech that because we can bridge so much liberal arts into it, that there's just so much weight.
[00:03:51] Ken Kocienda: So, so here, here's how I think about this, is that for a very, very long time, we've had algorithms and heuristics, [00:04:00] right? that this is what, uh, technologists use to create software. So you write a little bit of math, and then you have a, a, a graphical user interface, like maybe an iPhone with an animation. Well, how does that animation slide to a stop?
[00:04:15] Ken Kocienda: You need to decide. It's kind of a heuristic. Something. Uh, my background autocorrect. When do you autocorrect a word and when do you not? Right? The algorithm will give you a number, but then it's a up to a human to decide where are the cutoffs, right? And so what AI presents to us now is a couple of new kinds of tools.
[00:04:34] Ken Kocienda: Generative tools, extractive tools, right? So then how do you take those tools and put together, build a new kind of machine? And that's the opportunity now, is that we have new and different kinds of tools that we're discovering how to use. and, and the generative aspect of it is the most obvious. The extractive one is slightly less, which maybe we can talk about in a little bit, but it's like [00:05:00] now you have this ability to say, to really to talk to the computer.
[00:05:03] Ken Kocienda: Whether you type at the computer, maybe it's not really actually talking, but you're, you're able to chat with the computer to maybe have the computer understand what you mean, and then go invoke an algorithm. Yeah. And that's the kind of path that then the, the, the chat, the, the chat interaction invokes an algorithm which outputs to, to, uh, to a heuristic, to another algorithm, which then draws you a graphic and gives you a visualization of a result that would not have been possible before because of that essential gap that the AI can help to bridge in understanding what you mean.
[00:05:40] Ken Kocienda: And, and that's, that's, that's the kind of opportunity that we're in now. That's the kind of opportunity that we're pursuing at in factory.
[00:05:47] Andrew Zigler: Yeah, and, and, and that's kind of the holy grail I see is that engineers have always been building, you know, they, they want to build with intent. They want to have impact on the users, but there's nothing more intentional than understanding very clearly what you want. [00:06:00] And then asking the computer for it and the computer being equipped with those algorithms, those tools, to then solve that problem for you.
[00:06:06] Andrew Zigler: And you remove so much of this middle step and it allows people to do really transformative work. Yes. And it's opening doors for folks that never before could do that work, can now even lead the charge on it. I think we're seeing that a lot at organizations within, within them, uh, when folks are like spinning up like AI experimentation groups or like, you know, who's doing what with ai.
[00:06:26] Andrew Zigler: Like you get these surprising anecdotes. All across the org. You know, uh, Suzy in accounting who's never used the tool before, has built this amazing workflow. And it's because she knows really clearly what she wants and she was able to convey it. Maybe she already had the email draft. Right. And that's like the power I think, too of, of, of AI for engineers is, uh, it, it'll, it is a extractive tool, but it then, it's also like a refractive tool.
[00:06:50] Andrew Zigler: You can take that intent and then you can shift it into all sorts of other intent using just your own natural language. And that's really, it's unlocking a. Lot of potential for [00:07:00] builders. And, and, and you touched on it just a moment ago. I'm curious to know, because we've talked a bit about with Brooke about Infactory and the problem y'all are solving and about putting power back in the hands of publishers for the content they have.
[00:07:11] Andrew Zigler: You know, what, what inspired you, Ken, to like, rise to that mission? What, what is your goal at Infactory and, and what excites you when you wake up every day?
[00:07:19] Ken Kocienda: Yeah. it gets back to this point that we've been talking about is I am excited on produ, on, on, on enabling human results, results for humans that they find useful and meaningful. That's what I'm interested in. And so we go to, uh, uh, uh, content owners, we're working with some that have long, long history of large, large catalog of information.
[00:07:43] Ken Kocienda: There's a tremendous amount of latent value in all of that work, how do we get to it? And, and, you know, and in some ways, I, I, you know, in, in the conversations that you had with Brooke previously with, you know, talked a lot about data. Yeah. Trying to find the value in the data, uh, and, uh, [00:08:00] both through the generative, uh, uh, uh, path of AI and the extractive, uh, capabilities that AI offers, we can then point the AI at, at these, these content archives, at these asset catalogs and levitate above it.
[00:08:15] Ken Kocienda: What's in it? What's useful, what do I have? Create tools that, that can understand what's been extracted, right? And then make them available to the, the person in accounting. Make them, you know, available to the, you know, the person who has a question that has some workflows that they need. To, uh, uh, accomplish and yet have those workflows enriched by this greater substrate of data.
[00:08:41] Ken Kocienda: This great, this, the, the more value that is already in the organization and raising it up using AI to explain it to software so that tools can come along and, and, and make new applications and experiences for people that are useful.
[00:08:59] Andrew Zigler: Yeah, [00:09:00] I, I, I'm curious too, Ken, you know, uh, are you, are you vibe coding these days?
[00:09:04] Ken Kocienda: I use AI to code all day, every day. Yeah. Okay. But I, I don't vibe code. No, I don't. What I do is I write very, very detailed specifications. I write paragraphs of paragraphs to the AI and I monitor everything that it does because it's amazing. It's very, very powerful technology, but it doesn't know what my intent is.
[00:09:28] Ken Kocienda: I try to communicate my intent, but I have to. Keep it on the narrow path for what I want. Um, and so it, it is an extraordinarily powerful tool, uh, and allows me to, uh, write thousands of lines of code instead of hundreds. Um, but it takes a, at the end of the day, I'm tired because it takes a tremendous amount of concentration to keep these conversations that I'm having with the computer on track.
[00:09:56] Andrew Zigler: You know, we've talked a bit about like the vibe coding experience on Dev [00:10:00] Interrupted. I, I, myself, am a practitioner. I, I've, I, I write code every day at my job as, as Dev, and I'm using AI every day. In, in a collaborative way, and I'm very much like you. I, I'm very spec driven. I, I always start with that really clear markdown document, Hey, you and me and the ai, let's brainstorm.
[00:10:15] Andrew Zigler: Let's make sure you understand really clearly what I want here, because that's the power is that it can do so much and it's ultimately going to be kind of a. Working its way back to like a baseline, a medium, right? If you wanna create excellence, then you have to take that excellence in your mind and you have to con, you have to get the AI to understand what it is you want.
[00:10:33] Andrew Zigler: If you just say the most plainly of ways, it's gonna give you the most plainly of results. And the cool thing about like spec based vibe coding or spec based coding with AI really is that, uh, you spend so much time gathering that information into one shared place, you really kind of like nail it. A world of determinism in a very probabilistic system, right?
[00:10:52] Andrew Zigler: And, and by doing that, you create these like, uh, artifacts of the creation process that I never even had before that are really exciting when I [00:11:00] build things now. And I, and I'll like turn around a project in a day or I'll create something and throw it up on a website in an afternoon, and then it's like, sure, great.
[00:11:07] Andrew Zigler: I have that like result at the end. But what I always am most proud of is that spec document that I worked on at the very
[00:11:14] Ken Kocienda: You know, it, it's, it's interesting because I was just having a conversation with a coworker the other day about, well, we need to save these documents, these documents that, that we. Make and, and, and produce in collaboration with the ar part of the development process. Yes. and so we have a new kind of resource that we need to track and give.
[00:11:33] Ken Kocienda: Yeah. Um, because it's just like, well, why did it turn out this way? Well, we have this, it's not really a, a specification document. It's, it's an exploratory document. Uh, that, that explains part of the why for how things turned out.
[00:11:46] Andrew Zigler: Yeah. And it's like a catalyst. Yeah. Too. Really? Yeah. And it's like, that's why it's important to include it. With source code because it becomes a catalyst for other people to work with your same code and get those same results. Yes. Um, okay, great. Well, you know, we talked a little bit about, [00:12:00] uh, AI and using it in coding world, but I wanna actually just like rewind a little bit going back to your time at Apple.
[00:12:05] Andrew Zigler: I'm kind of curious to know, uh, from your own perspective, you know, apple has had an incredible impact on the world and all the technology we use. Uh, but what do you think is maybe the most misunderstood part of Apple's design?
[00:12:18] Ken Kocienda: I think people focus a lot on the hardware. That's the exciting thing when Apple releases a new phone or a new watch, or a new tablet, or a New Mac or what, uh, uh, but it's, it's the software that is the real key to the whole experience. It, and, and it's how the software interacts with the hardware and interacts with what people wanna do with it.
[00:12:43] Ken Kocienda: I, and again, I go back to this, this idea of making things that are useful and meaningful and, and, and, you know, and I think that people have this, this real focus on the gadget, but that's not really where the magic is. The magic is in the software.
[00:12:57] Andrew Zigler: [00:13:00] So if you think that the most misunderstood part of Apple. Design from outside looking in is how much of the, how much work goes into the software versus the hardware. Um, but I'm curious too, like in that Apple world that you were in, what's like the most stressful demo that you ever had?
[00:13:18] Ken Kocienda: Well, you know, uh, I, I had the opportunity, uh, several times to, to demo directly to Steve Jobs when he was, um, still on the scene. Um, and that was extraordinarily stressful because he was, um, so direct
[00:13:37] Andrew Zigler: Yeah.
[00:13:37] Ken Kocienda: and so clear. Whether when he liked something and when he didn't, and his standards were extraordinarily high, and so you could show him something and it would be, well, in no uncertain terms, he would tell you that he didn't like it.
[00:13:51] Ken Kocienda: You can imagine that sometimes this got pretty colorful. Um, but it was never personal. I remember one time where, um, we were, [00:14:00] um, it was the first, uh, retina iPhones were coming out. So the first time that we had pixels that you couldn't see. The pixels were be, uh, you know, beneath the, the, the resolution of your, your eyes.
[00:14:11] Ken Kocienda: Uh, and so we wanted to make a new, uh, system, font for, uh, for the Mac, uh, uh, excuse me, for, for the iPhone. Uh, BA based on, um, uh, well now we can draw these characters more clearly. And so I brought him some mockups and he thought they were all terrible. And so he told me it's just like, these, these are all junk.
[00:14:29] Ken Kocienda: What are we gonna do? And so it's like in, in one breath he said, you know, in that slightly more colorful terms, this work is junk, what are we gonna do? And so, you know, I think a lot of people feel that he was very much looking down at the people who brought him work, but in that moment it was like, what are we gonna do?
[00:14:52] Ken Kocienda: And so it was, it was very, very easy in that moment to take that stress and, and turn it [00:15:00] into, uh, a focus for whatever the next step was going to be. And this is part of the magic that Apple had as well. And part of the magic that I've tried to bring along with me in my work and other projects and then try to bring through to the work that we do now at Infactory, is that everything is provisional.
[00:15:16] Ken Kocienda: Things change very, very quickly, and so we need to plan and account for the kind of change and use the work that we do as the stepping stone for the thing that we do next.
[00:15:29] Andrew Zigler: And so that is the opportunity you see right now as an engineer working A CTO, working in a field that's being radically transformed by ai is that everything is provisional, everything this is, there's a sea change event happening. Yes. Right?
[00:15:43] Ken Kocienda: How do you manage change?
[00:15:44] Andrew Zigler: Yeah. what it down to at the end of the day is what we talk about every week here on Dev Interrupted right now.
[00:15:50] Andrew Zigler: The extraordinary change that's happening within organizations, that it can flip them upside down. And so really getting to the root of that has been really like a powerful thing to learn more about. [00:16:00] Um, I want, I wanna also, uh, spend a moment just to ask about your book Creative Selection. It's on my bookshelf.
[00:16:07] Andrew Zigler: I've read it. It's one of my favorites actually. And I wanted to ask you about your idea of evolutionary design. You talk about this a lot in the book, uh, and, and as part of like your demo driven process, I'm, I'm, I'm curious, like how did you iterate as somebody outside of tech to then create, be like, um, how, how did you iterate from being outside of the world of tech to being inside of the world of tech and using that to inspire that evolutionary design?
[00:16:34] Ken Kocienda: Yeah, so it, it really is all about, um, going one step at a time. Generation of work, one generation of an idea that that, that you just build step by step. That's what it is. It's says, you, you, you try, you get an idea and you try to create some concrete artifact that represents that idea, and then you step back and [00:17:00] you look at it, yeah, is this good?
[00:17:01] Ken Kocienda: Is this what, what's good about this? What's bad? Get rid of the bad, keep the good, do the next. So that, that's, that's, that's the evolutionary step right there. Yeah. You can see it in one step, but none of the, the, the projects that I've done, none of the pieces of work that I'm proud of, were able to be accomplished in a single step.
[00:17:22] Ken Kocienda: So how do you then maintain some continuity? How do you create, uh, an arc over those iterations? And that's what it is to try to see where am I trying to head with this? You know, and, and, you know, look, I'll say it again. It's the, you know, the, the end result is to create something useful and meaningful for other people.
[00:17:41] Ken Kocienda: It's not about the tech, it's how do you get the tech to transcend itself. To be, to, to, to get it to the point where other people will say, yeah, I want that thing, that thing can help me. And that's what it's, so it's, it's ev evolving the tech and this, this desire to, [00:18:00] to, uh, to a, a accommodate and, and fill the needs that other human beings have.
[00:18:07] Ken Kocienda: And, and it's those, those parallel getting them to converge on, on, on, on end result.
[00:18:13] Andrew Zigler: Yeah. And as, as you describe that, I immediately go to what ha what is something that you designed that's used by so many people auto correct. You have to guess the intent of something that people do every single day on their phone with all sorts of varying degree. And you're also fighting all sorts of, uh, edge cases, like trying to keep the user from accidentally swearing and or like saying things that they didn't intend.
[00:18:37] Andrew Zigler: And then Apple has since like, you know, that technology is embedded into. Everything that we use in the world today to where the technology is always guessing your next step, guessing your intent, and then this becomes a bridge almost like, uh, into what we're seeing with AI hitting the scene that's always trying to guess your intent or go one step beyond.
[00:18:57] Andrew Zigler: What are, what are some mistakes that you learned in [00:19:00] autocorrect that you think could apply to people building with AI
[00:19:02] Ken Kocienda: Well, it is, um, I, I think remediation is, uh, is a big lesson, um, because as you're saying, uh, and starting all the way back with autocorrect, uh, a much, much simpler system than what we have now with AI is that you are trying to divine, you're trying to understand what people's intent are. Well, what if you get it wrong?
[00:19:23] Ken Kocienda: How does then the person understand that? Well. Going from this is not what, what the system did not produce my desired effect. What do I do now? Yeah. How do I get from where I am now to this, this, this, this undesirable outcome very, very quickly to a desirable out to, to, you know, to what I want to the desired outcome without frustration, without where the person goes.
[00:19:51] Ken Kocienda: If you, if, if you flubbed this enough. People will just go away. Yeah. They'll take the, your gadget and throw it out the window. Right. [00:20:00] And so it's this kind, it's, it's, it's not about technology. It's very much more about psychology. So giving people the comfort. To understand the system that they're working in and understand how to navigate through it to get what they want.
[00:20:18] Ken Kocienda: Even when they don't take a step back, and I can go this way, I can pivot really easily. And that, you know, having things be understandable and explainable and coming up to the level of humanity rather than just leaving it off at the level of the machine is, is, is how, how that's done.
[00:20:35] Andrew Zigler: Yeah. And you're talking about a technology that's used by people from all walks of life and all levels of technol technological literacy, right? And so being able to even not frustrate them and offer, offer opportunities for them to convey what they really mean, you know, this is something that looks simple on its surface, but if you get it wrong, like you said, people are gonna turn it off.
[00:20:58] Andrew Zigler: People are gonna throw it away. It's not gonna catch [00:21:00] on in the way.
[00:21:00] Ken Kocienda: So, so, you know, you say this, you know, technology literacy, it's a, I. Feel that it's my job to make that not matter.
[00:21:08] Andrew Zigler: That's exactly.
[00:21:09] Ken Kocienda: It has to not matter. There, there, uh, there are people out in the world who are experts in what they do. We work now with companies in the enterprise that they're experts at what they do and have been doing it in some cases for many, many decades.
[00:21:26] Ken Kocienda: And so how do we make. AI now available so they can continue what they're doing only better. Right. That, that's, that's the challenge. That's the opportunity. That's what those companies want. Yeah. Right. And we're still at the beginning of figuring out how that can, uh, work, uh, you know, uh, most efficiently work best.
[00:21:50] Ken Kocienda: Um, and, uh, you know, that that is, um, you know, I, I still feel that we're still, we're very, very young in, you know, in the history of just computers, [00:22:00] nevermind just ai. And so we're still figuring it out, but I think that there are some very, very good ideas using some of these, uh, ideas that we've already talked about, that, that show the way for how AI will become in integrated into, uh, you know, people's everyday interaction with the tech that they use.
[00:22:18] Andrew Zigler: And talking about that beginning. I, I want to know, curiously, having now spoken with you and Brooke, where did in factories start from? Like what kind of conversation then led to the creation of this company?
[00:22:29] Ken Kocienda: So, so Brooke and I met, um, at Humane. Um, and so the, uh, the, the challenge there was, um, you know, to make a new style hardware device that would, uh, open up, uh, and make, uh, the, the potential of ai, uh, uh, available to, uh, to, to, to people, to consumers. Uh, and, and what we found, you know, the part that I got into was, uh, trying to do that, that, that AI [00:23:00] portion of it.
[00:23:00] Ken Kocienda: And, and we wound up talking to some, uh, uh, outside companies, uh, very, very large, you know, data providers. Yeah. Um, and there was this gap. That existed, um, in the sort of the humane stack that was company sized. This, this, this, this moment where you sort of left the Humane Cloud and went off into somebody else's cloud to fetch a piece of information and then bring it back, and that was a part.
[00:23:28] Ken Kocienda: That we didn't maybe understand as well as, as we, uh, uh, as we might have. And that when, you know, when, when Brooke and I, uh, you know, started talking about, you know, what would come next for us after Humane, we looked at that. Point to say there are people that, that are producing intents in the enterprise, not with now a consumer piece of hardware, but now just these intents exist in the enterprise.
[00:23:53] Ken Kocienda: There are jobs that need to be done, um, and, and a relatively small number of, you know, very, very common, [00:24:00] well understood jobs that, that people in the enterprise want to do. And then there's the data. And so what can we do to close that gap? How can we make a company that fit into that spot that picks up from the intent and somehow gets through to these vast data resources, these, these enterprise, uh, data lake houses that just have everything that the company ever did, but what are, what are the nuggets of gold?
[00:24:29] Ken Kocienda: Yeah. How can we get people through to the things that they wish they had? Um, and they wish they could bring to bear on the problem that they're working on right now. And how do we build a suite of tools that breaks that problem down so that we can apply engineering rigor to it?
[00:24:45] Andrew Zigler: That's exactly right. You're building a primitive that we're all going to need in order to build and use these systems, and it's kind of like you're crossing an abyss that that wasn't abyss until you started working on the Infactory problems.
[00:24:56] Ken Kocienda: So, so, you know, you see you're say in abyss, but what we have, I mean, there's no way that we [00:25:00] can spend, you know, get into these in detail during this conversation. But we have prepare, connect, build, deploy, and explore as different modules in our software and. Every one of those enables an engineering touchpoint.
[00:25:15] Ken Kocienda: And then it's where those different modules interact with each other is where the programming comes in, where you might have some AI assistance, where we can orchestrate, where we can have an agent participate, but it's those solid, those solid foundations that enable us to build applications, to make experiences possible, to get through to that human result that we're trying to deliver.
[00:25:39] Andrew Zigler: So fascinating to hear you talk about the problem, because I think at the end of the day, data is our biggest problem with ai. You know, we're ultimately having access to those nuggets of gold. We talked about a that a lot with Brooke about fi like in your huge data lakehouse or whatever repository. How do you find in there what's actually really useful for your [00:26:00] workflows?
[00:26:00] Andrew Zigler: Because if you treat it like, oh, we're just gonna dump all this into whatever never works. And so I I, I'm curious too, like. When you are, when Infactory is talking with a large enterprise, someone like sitting, someone's sitting on a lot of like data and publication history, how do you start to navigate that conversation with them to figure out what is important?
[00:26:19] Ken Kocienda: So, so one of, uh, uh, the, uh, means that we is.
[00:26:30] Ken Kocienda: Enterprise and one of the main ways that we do it is not with generative ai, but with extractive ai is that what we try to do a lot is we, we have custom models and custom techniques where we can like levitate this, this layer of new data up. Above the primary source data, and we can show here is the value in some of the, some of the technology.
[00:26:54] Ken Kocienda: Uh, you work with a publisher where they, uh, uh, they publish news stories and so they have multiple revisions of the [00:27:00] news stories. Here is the through line, uh, across these stories, and what we do is we cite the stories themselves. We're not producing anything that. Isn't in the stories, but we say, well, this revision had this, which changed to this, which changed to this?
[00:27:15] Ken Kocienda: Did you know that? And it's just like some eyes open, right? And so then we might have a generative process, which then summarizes that. But it's like going and extracting chapter and verse, right? This document, this line, this is the piece that is actually in common through this revision of, of different stories or is maybe changed.
[00:27:39] Ken Kocienda: Yeah. Pivoted at a certain moment. And if you can do that in the aggregate. Um, over maybe a topic area, maybe a big world event where that, where there has been maybe, uh, news reporting that's been going on over some period of time, we can, again, what I like to think about is just levitating this new data layer above the source data. [00:28:00] That provides addit additional insight and understanding, but always maintains the connection to the source data. And that is eye-opening for a lot of enterprises because again, we're, we're not, we're not telling them something that isn't already there. We're just making it visible. We're surfacing, um, uh, content that is, um, something that they know that they themselves produced and that they can trust.
[00:28:28] Andrew Zigler: This is amazing. I, I, I, I love the idea of how you've, this even goes back to when we talked earlier about like coding with AI and those, those artifacts that you get along in the process and why they're important, why they need to be included with things, and this is all, this layer that you're describing is.
[00:28:42] Andrew Zigler: Like, uh, it's very similar to that. You're taking information that's already there, that's already like, firm and written, and then you are basically, uh, turning it into this middle layer that extracts really unique insights and elevates the value of all of that corpus underneath it. Without making [00:29:00] things up, it it, it dials up the determinism to give you that really critical building platform that you need.
[00:29:06] Ken Kocienda: So, you know, a a, a big part of what we do is to find structure. We try to find. And understand structure, um, in either unstructured data or structured data, but to identify new kinds of structure, new kinds of metadata that then we can write programs against, you know, so one of the, the, the chief, uh, uh, uh, means that we, we have for, this is a, a technology we call query programs.
[00:29:33] Ken Kocienda: They're not queries and they're not programs. They're queries and programs together. So we query a particular piece of data and then we run algorithms over it. It's getting back to what I'm saying before. We have algorithms, we have
[00:29:43] Andrew Zigler: It's a primitive,
[00:29:43] Ken Kocienda: have generative, we have extractive and orchestrating all of those together to produce again, the kind, the new kinds of effects.
[00:29:51] Ken Kocienda: Finding new insights. Uh, uh, identifying new pieces of metadata and then searching over it, doing computation with it and producing results. [00:30:00] How many of this did we have during this time period? Um, and, uh, and, and it's like that information is there to be found, but is very, very difficult to extract when.
[00:30:12] Ken Kocienda: You have a data lake house that where, where things are just as they are or you have your CMS and no, uh, data scientists came over and, and, and wrote a specific application for that. What we're offering is the opportunity to make. This application development a lot simpler, a lot more direct, and putting it in the hands of people who maybe are relying on some fun fundamental work from data scientists in the organization that use our software to uh, uh, uh, make some tools, but make it available to people who are not data scientists themselves.
[00:30:45] Andrew Zigler: Wow. Ken, it's been amazing to sit down with you and learn about how you're creating the building blocks of AI that are enabling organizations to actually get value out of it. We've been following the story for a lot on Dev Interrupted, and I'm a personal, [00:31:00] huge fan of, of you and your background and the impact that you've had on the world.
[00:31:03] Andrew Zigler: So I can't thank you enough. For sitting down with us in our very iconic Dev Interrupted dome to do this interview on site here at Engineering Leadership Conference. And, uh, we're gonna include lots of information in our show notes in our newsletter so folks can go learn more about this conversation and continue to follow the transformative work that you're doing on the world.
[00:31:20] Andrew Zigler: Is there any other final notes you wanna leave our, our
[00:31:22] Ken Kocienda: I, I, I wanna thank you for the opportunity. You look, I'm, I'm an optimist about the future, so I think the future is bright.
[00:31:29] Andrew Zigler: I share the same. Thank you so much for joining us.
