This week on the Friday Deploy, Andrew Zigler is joined by Zapier’s Kelly Vaughn to dive into the sudden return of Anthropic's Fable model, the realities of multi-threaded agentic engineering, and why the lowly engineering backlog is finally having its moment. To wrap things up, they review Charity Majors' latest advice on empathetic leadership and explore why the best way to win a workplace disagreement is to stop arguing and let an AI build the proof of concept.
Show Notes
- Redeploying Fable 5
- It’s Time To Put Humans Back In The Software
- Three Ways to Give an AI Agent an Identity
- Benchmarking AI Agents for Real Data Science
- Why I Stopped Arguing With People
- Paging Charity! How can engineering leaders avoid becoming Bond villains?
- The backlog is finally getting its moment
- Follow Kelly:LinkedIn|Website|Substack
Transcript
(Disclaimer: may contain unintentionally confusing, inaccurate and/or amusing transcription errors)
[00:00:00] Andrew Zigler: So Kelly, have you heard the news, I'm sure it's impossible to avoid it, that, uh, Fab- uh, Fable has come back into our world?
[00:00:06] Kelly Vaughn: Fable is back in our lives again. Yes. It was, um, a bit of a... I, I say it was a bit of whiplash, but, like, I didn't actually get a d- a chance to use it that much before, and I haven't really gotten a, a lot of time to actually use it this time around. But I can confirm that Fable does recognize that there are three Rs in strawberry
[00:00:26] Andrew Zigler: Wow, incredible. So you were able to get to the bottom of it with the latest model
[00:00:30] Kelly Vaughn: Yes. I cannot wait for like my analysis of like how I've used the different models, and it's like, "You spent how much on this query?"
[00:00:38] Andrew Zigler: It's like the strawberry benchmark is really where you go to first. That's incredible. Uh, and, a- and, and you know, I think it's, it's funny that you comment on, like, having a chance to try it again. I remember when it came out and then it got taken away. Remember I w- I was in your DMs on LinkedIn and I said, I was like, "Kelly, did you try Fable?"
[00:00:55] Andrew Zigler: And then y- you said, "No," with a little sad emoji, I think, with, with... Yeah, [00:01:00] yeah. It w- it was sad. Uh, you're not alone. There were a lot of folks who, who, who I DM'd on, on LinkedIn. I was like, "Did you try it?" And a lot of people were like, "No," like, "I didn't." It was actually staggering to see the number of folks who, uh, had, like, I- they didn't get a chance to.
[00:01:12] Andrew Zigler: So to have it come back and, and they get to try it is really great. Uh, we do only get this one limited week of it being on our, uh, subscription tier pricing so, uh, what actually I think this talks about more than ever, and we'll dive into in a moment, is the importance of choosing the right model for the task.
[00:01:28] Andrew Zigler: ' Cause I think Fable is r- gonna be one of the first of many of these flagship models getting e- really, really expensive for highly specialized stuff. So what do we need to be learning from it? And that's what we're gonna be talking about today. And to those listening, welcome to the Friday Deploy. Wel- brought to you by LinearB.
[00:01:43] Andrew Zigler: I'm your host, Andrew Zigler. And Ben is out this week enjoying the great outdoors, whatever that is. But don't worry because we it does feel nice to go and touch grass, but, you know, here on Dev Interrupted we touch keyboards and we chat with friends. And so don't worry, [00:02:00] we have a past guest and, in fact, your favorite engineering manager's favorite engineering manager returning to the show, Kelly Vaughn.
[00:02:07] Andrew Zigler: Kelly, it's amazing as always to have you here. I'm so excited to run through this week's news with you.
[00:02:12] Kelly Vaughn: I am so excited to be back again. You know I love doing this. I love hanging out with you, and I love talking this, whatever tech news is on the plate for the week
[00:02:19] Andrew Zigler: Exactly. And it's, it's good to gossip about it out here in the open instead of in our DMs on LinkedIn, so let's get to the bottom of it. Because this week there's been a lot of interesting stuff going on. Obviously, Anthropic's control over, uh, Fable and releasing it to the market has changed, and we're gonna talk about what that means.
[00:02:35] Andrew Zigler: Uh, we're also gonna talk about things around agent identity and how you should be thinking about that in combinations with your workflows. We're gonna be diving into, uh, a data science benchmark from past guest Bryan Bischof. You might remember the Data Science America's Next Top Modeler that I participated in back in October.
[00:02:50] Andrew Zigler: We got a post retro on that that's really fascinating. We're gonna learn some stuff. And we're gonna talk, uh, a little more on the interpersonal side because as we all know, creating software is a [00:03:00] deeply, uh, communicative sport, right? It requires a lot of, uh, communication, team building, collaboration, ex- and understanding the perspectives of others and how you're working together.
[00:03:10] Andrew Zigler: So we're gonna be talking about why arguing isn't necessarily, uh, the best way to get about proving your point and avoiding some villain bond leadership, uh, based on some advice from our, uh, favorite Charity Majors as well. So Kelly, I'm really excited to dive into some of the things today, but, you know, I just wanted to start by revisiting just for a moment the, the Fable getting brought back out into the world because, one, I think this represents a really interesting change in how models are gonna be released moving forward.
[00:03:39] Andrew Zigler: I think you're gonna see more interference from organizations and entities in the models coming to market, at least in the West, which is, uh, starting to have more restrictions around the capabilities, uh, and concerns around things like internal cybersecurity and stuff. But also, too, on a practitioner side, having the model come out and then I [00:04:00] tried it, uh, you know, we talked about this extensively in our new segment.
[00:04:03] Andrew Zigler: I used, like, all of my tokens riding the dragon of Fable basically, and I, and I couldn't stop talking about how, how helpful it was. Uh, but the, the Fable has come back. It actually has a lot of model routing capabilities underneath. Uh, it'll actually send things like, uh, uh, coding requests in many cases off to a, an Opus model underneath.
[00:04:22] Andrew Zigler: It'll use things like Sonnet, the new Sonnet 5 that came out along with Fable 5 to do a lot of things like writing. So it kind of begs the question of like, what is Fable and what is Fable doing? And I think it has to do with like this organizational intelligence of how work gets done, and it represents the new kinds of models that we might have moving forward and that these models might get really expensive.
[00:04:41] Andrew Zigler: But, you know, Kelly, what were your thoughts on this thing coming back to market?
[00:04:45] Kelly Vaughn: Yeah, I think, I think we're gonna be seeing a lot more of this. I think the big splash of this model is n- not going to be something we continue to see in the future. Um, I think we're going to see even more interference and, and it's, [00:05:00] it's a weird, it's a weird time to be in this phase. It is...
[00:05:04] Kelly Vaughn: I, I would say it is probably predictable that we would've ended up here to begin with because we fear things that we don't understand as humans. Um, and we understand that, you know, we don't really understand what we're doing here yet. This is, this is a very fun exploratory period, but at the, as these models get smarter, we don't know what we don't know yet.
[00:05:23] Kelly Vaughn: So I do understand that, you know, I, I, I don't love the national security piece, so only rel- you know, release it to certain, certain very special customers that aren't Zapier, unfortunately. Otherwise, I would love to be in on it early. Um, but I, I, I tend to see more of, and more of this. But one thing I do kind of wanna touch back on is the, the choice of model.
[00:05:45] Kelly Vaughn: The model routing I think is actually a really, like, smart thing to do here because I think we also have a tendency of overestimating how difficult something might be. And so we're going to be immediately default to like, "Oh, I need to use the, the smartest model for [00:06:00] this, the most expensive model for this." Um, and if I'm foreshadowing for anything, I apologize in a- in advance here. But, um, I think it's important that, you know, we all want to kind of play with the, the new stuff, but if we default to using whatever's newest, going to run out of money really fast
[00:06:18] Andrew Zigler: Oh yeah. I think that's really great advice. The whole i- idea of being aware of what model you pick up and which ones you're using for what task is only gonna become more critical as these models, I think, become more specialized. Up until now, we've been seeing these, like, step level changes and f- at foundation level capabilities, but, and you're still gonna see those, you know, at an obviously slower rate moving forward.
[00:06:39] Andrew Zigler: And Kelly, I think you're really smart to call out that you're probably not gonna see the big splash of releases anymore because now I think the name of the game is gonna be, how can I get the intelligence out the door day by day? How do I, how do I, uh, I guess, like, you know, continuously deliver the intelligence and not ship these big models?
[00:06:57] Andrew Zigler: That way you would sidestep this whole, [00:07:00] oh, now there's a curtain falling on security and interference, and I, I think that might be a strategy we see, where, like, you just now see a latent increase in capabilities. But on top of that, I think you're also gonna see them split into highly specialized domain specific models, where you have that really smart flagship model or you have a open source way alternative.
[00:07:20] Andrew Zigler: There's a lot of them now that are open source, Apache 2, that you can build a business on top of, and you take them and you fine tune them on your domain expertise on synthetic and real data from something you're infinitely, like, knowledgeable about, and you build a highly specialized intelligence for handling things in that domain.
[00:07:37] Andrew Zigler: That becomes, like, the new frontier because if you trained that, then it's like, yes, sure, over here maybe the step level capabilities keep going up, but none of them will ever be as good at that specific domain task as this one that was trained off of this one. And then if we ever want to move it along with it, then as open source gets better, we train along with it because the data set is modular.
[00:07:58] Andrew Zigler: So, like, these [00:08:00] become the new strategies I think people turn to. Uh, I think Fable is gonna be, like, an event that causes folks to really wake up to that reality. Speaking of waking up to the reality, uh, our producer Adam, who's not here today, uh, he's-- was on the ground this week at AI Engineers World Fair, uh, recording some really cool stuff, capturing some things on the scene, but also hearing from HumanLayer co-founder Dex Horthy, who's also a past guest on Dev Interrupted.
[00:08:26] Andrew Zigler: And, and Dex, you know, he, he made a lot of news and folks were talking about his presentation, uh, about how, you know, teams are over-relying on poorly trained models and they're having a fast throughput of code that maybe goes through some s- facsimile of a review and delivery process. But then, you know, days or weeks or months later when there's incidents, when there's outages, when there's critical flaws in the software, being unable to turn back to the work that was done and understand the legacy of how you got there.
[00:08:55] Andrew Zigler: What were the decisions? What were the artifacts? What was the code and the tests? And, you know, that [00:09:00] level of auditability, observability is different for everybody. But, you know, he's really calling out here the importance of putting the human back in that loop of being cognitively aware of what is happening at stages of this process.
[00:09:11] Andrew Zigler: That way it doesn't take months for these AI-generated flaws to surface in your product and what you're delivering to customers. And, uh, really he was attacking to the idea that, oh, just optimizing your harness is everything, that just getting the loop is everything. You know, getting the loop and getting really good skills is one element of being a really effective agentic worker, but sharing context and aligning with others and their agents is actually the, like, the differentiator for teams that are delivering durable software.
[00:09:41] Kelly Vaughn: Yeah. No, I, I love this topic because it's something that I s- I firmly believe as well. You know, I, I, I am a, a strong proponent of, you know, multi-threaded agentic engineering. I think there's a lot more that we can do at the same time, but that doesn't mean that every task is one size fits all. I have seen [00:10:00] product teams ship a whole new product in, let's say, four weeks, four months, whatever, and what they're capable of doing now is amazing.
[00:10:07] Kelly Vaughn: But I've also seen what happens when those incidents arise and we're like, "Okay, we're now using AI to diagnose a problem that AI wrote, and AI reviewed, and AI shipped." Like, are the humans in this conversation? Um, and it is... You know, there's a reason why I'm also a big fan of, you know, making sure engineers stay employed.
[00:10:29] Kelly Vaughn: Engineers serve a very important role in, in, in engineering. Like, we are the ones who do hold the context and nuance, and really being able to understand the systems that we're building is what keeps us in engineering. And so I, I, I love this whole take, and I, of course, was not at the, uh, the presentation, but I'm, I'm bummed that I did not get to see it in real time.
[00:10:53] Andrew Zigler: I know. I'm excited to dig into more. Everything from Dex, I think he's really spot on with how folks should be thinking about their [00:11:00] engineering practice. So more to come always from Dex. I recommend folks, uh, follow him on LinkedIn if you're not already. Uh, and, and our next, uh, topic is getting a little more granular around some of the problems of having agents roaming around without where all your code is in the first place.
[00:11:17] Andrew Zigler: And this was a really interesting article that dove into different ways that teams are giving their agents identity. Um, the idea of the identity being borrowed from the human user or being something distinct and token-like to the workflow, or being something cohesive and durable across sessions like an agent identity.
[00:11:35] Andrew Zigler: These are all just different ways that folks are tackling the idea of how do I understand who did what and under whose authority and with whose permissions, which I think is one of the biggest dangers right now lurking with AI inside of large enterprise organizations, especially those that are still figuring out how do we, uh, share, uh, these durable AI practices across the team.
[00:11:56] Andrew Zigler: And, also too, what I love about this article, we'll share it because [00:12:00] it, it gets technical in terms of like the level of ways that you'd go about instrumenting and actually applying these three different things. But critically at the end, uh, it does a really great job at comparing like why would-- When, when would you pick up one over the other?
[00:12:13] Andrew Zigler: We know these three exist. Why do some orgs fall into bucket three where they have to build a very complex agent identity system where everything has an ID that goes back to an age? It's like, for me, it makes me think of like, oh yes, because like huge, large sprawling enterprises, there were times where they all had glowing eyes for building microservices or like, " Let's just be on Kubernetes."
[00:12:35] Andrew Zigler: And it's like, why are we on Kubernetes? We have 500 users. So it's like and, and so like, um, th- these kinds of re- That's what it makes me think of when I look at the agent identity thing of it's like, is this an over-engineering? Is this seeing a, is this s- is this wanting to hit, is this, you know, wanting to hit the nammer with, hammer with a nail or whatever the metaphor is?
[00:12:54] Andrew Zigler: I feel like that's kind of what it starts to feel like. You know, Kelly, what do you think about how even within your own [00:13:00] team, you have a, you have a lot of folks and work that happens underneath you, and the permissions and scopes that they have are all varied. How do you think about it as an engineering manager?
[00:13:08] Kelly Vaughn: Yeah. I mean, the, the governance piece of this is critical. And, you know, we've, uh, at Zapier, this has always been a conversation. You think about automations running. Automations have, um, like a- applications, like integrations connected to it. Who i- like who owns that Zap versus who owns that, that integration be different. And you're al- like the governance piece al- is always a question that has to be answered. And so like I'm just seeing the same thing in a different flavor.
[00:13:36] Andrew Zigler: Yeah
[00:13:37] Kelly Vaughn: when I'm thinking about attribution for who is working on what and who is responsible for this, if everything goes through an agent's ID and there's no actual human tied to that, that becomes, you know, worrisome for me because I don't know who to talk to.
[00:13:52] Kelly Vaughn: And like my, like the other EMs that I work with are seeing the same thing. Um, you know, given these three, like, as you were saying with the, the [00:14:00] possibility of like over-engineering this, I completely agree. Um, one of the things that kind of stuck out for me is this, or with this, was that it very much feels like it should be like a stepladder in a way.
[00:14:11] Kelly Vaughn: Or like you should, you should work through the rungs, and when you start feeling pains, explore the next option, as opposed to immediately being like, "Well, you know, one day we're going to, you know, need this, this massive, massive thing, so we're gonna go ahead and build it now." Good luck like having to support that in the near term. Like we all have a tendency of over-engineering, and I know it's exciting to think through like the, the, the wide- the broader widespread like agent identities, but like it's okay to start small.
[00:14:36] Andrew Zigler: Yes.
[00:14:37] Kelly Vaughn: start small
[00:14:37] Andrew Zigler: Yeah, you should scope it. I like it's... And, and by scoping it, they say, you know, step one, start by borrowing the user's credentials and their, and their permissions, and be scoped about it, and have auditing and logs, which you should already have for every agentic call anyways. And so, yeah. And so it's like we're just talking about baseline instrumentation to achieve the identity, and then the rest of this becomes things that we're already familiar with, like [00:15:00] API tokens, which at this point everyone just assumes are compromised the moment that they're generated.
[00:15:05] Andrew Zigler: And so, uh, really, uh, it's like w- when you dive into this article, you'll see this, uh, thing about like SPIFFE and SPIRE and like all these different systems for setting it up. And I will agr- I will, uh, say that like my engineering brain was like, "Ooh, fascinating problem," and I could definitely hear the cogs turning, but that was the danger for me is I was like, I could spend a long time trying to build this answer.
[00:15:27] Andrew Zigler: Um, and I don't think anyone has the real answer yet, but the, just doing it, treating it as rungs on a ladder, it's a really smart strategy so you don't overextend, I think, in the meantime.
[00:15:36] Kelly Vaughn: Totally. Totally
[00:15:38] Andrew Zigler: So our next story is a recap from a hackathon that happened last year. This is America's Next Top Modeler. Yes, it's an incredible name.
[00:15:47] Andrew Zigler: This is hosted by Bryan Bischof. He's the head of AI at Theory Ventures and friend of the show. Most recently was with him at AI Council, where I presented. He was also a guest on the show. Uh, and he had this hackathon, America's Next Top Modeler, and [00:16:00] he really was kind of like this crazed villain running this hackathon.
[00:16:04] Andrew Zigler: And, uh, for those of you who've been listening since last year, you might remember the premise was that he brought 150 engineers together and one real analyst at, like, an analyst company, uh, to be given, like, a huge, uh, dump of enterprise data that was made up for a shipping company, had all these products.
[00:16:22] Andrew Zigler: There was, like, SQL tables and system logs and, like, literally, like, 800,000 PDFs. There was even a physical dusty binder that represented a binder sitting in a warehouse somewhere for the shipping company. Like, he went through all means of being like, information is messy, and it lives in a bunch of places, and it's not-- wasn't ever created with the intention of an AI built using and doing stuff with it.
[00:16:42] Andrew Zigler: And he challenged us to, as, you know, nascent data scientists, AI engineers, to build a system or a practice that would be able to answer this syst- this set of eval questions. So you build, like, an eval system. And really what this article is, is it's a benchmarking and diving deep [00:17:00] on how that process unfolded from the person who designed it.
[00:17:03] Andrew Zigler: I personally found this very fascinating because I spent six hours maddeningly, like, turning my brain over in Cursor trying to get, you know, the right results for the different eval questions. And there were folks that were doing all sorts of different w- brute force methods of trying to actually get the right answer, including someone who was running, like, 30 Claude Code sessions in parallel, and at one point his computer froze.
[00:17:27] Andrew Zigler: And so it was just everyone was doing something, and it was really, really, really fascinating. So this article dives in on some of the things that stand out for data scientists that are pitfalls in AI. Like, data science is often a matter of sequencing together operations and changes and data to get your final transformation that you're looking for.
[00:17:46] Andrew Zigler: Uh, and each of those are very susceptible to having the wrong parameter or the wrong kind of keyword, and suddenly your end, end result is wrong. And so it, and it can become much messier and harder for the agent to backstep and understand it. So they even created this [00:18:00] really cool grid where commonalities of agents and their approaches would break down when trying to do these joins and sequences.
[00:18:07] Andrew Zigler: Really interesting data deep dive for anyone who has tried to throw an agent at data. And I'm wondering, Kelly, is that you? Have you ever tried to use an agent to roll over lots of data?
[00:18:16] Kelly Vaughn: Uh, to some degree. I mean, with the amount of data that we have in Databricks, for sure. We've-- I've, I've tried to parse through a lot and try to create a story out of that, with medium success. Mostly because, and I think this is important for like one of the takeaways from this is like, what vague goal are you actually translating into something to be really precise and verifiable and step-by-step?
[00:18:39] Kelly Vaughn: And that, uh, it's, it's an interesting takeaway for like the sake of this study, like this, this, this hackathon, but this is a takeaway that should apply across the board. You know, it's the same thing of like throwing a very vague like Jira ticket at a, at an agent and saying, "Do the thing."
[00:18:58] Andrew Zigler: Mm-hmm.
[00:18:58] Kelly Vaughn: if it's, if it's
[00:18:59] Andrew Zigler: So [00:19:00] wish casting.
[00:19:01] Kelly Vaughn: Exactly, yes. And so
[00:19:03] Andrew Zigler: Yes
[00:19:03] Kelly Vaughn: is an interesting takeaway. Like this-- I'm, I'm glad you participated in this. Amazing name for sure. Um, I think the takeaways are just, they're so, uh, applicable across all different facets of engineering beyond just AI
[00:19:19] Andrew Zigler: Yeah. I even think of the, of the Andrew who was sitting in the chair in October doing that hackathon and what his engineering practice looked like, and I don't even recognize that person. So that also speaks to how fast... 'Cause I'm like, oh, wow, if I did-- I read, I'm reading this article and I'm like, oh, wow, if I could do this again today, it'd be a piece of cake.
[00:19:35] Andrew Zigler: And I know I'm still wrong, but it's just crazy how much that cognitive, uh, stuff has grown since then. Um, but you know, I, I wanna jump into our next article, which is a really interesting reflection on a reality of anyone that's in a workplace, which is most of us listening to this, is, you know, you, you're in a classic conundrum where you and someone else, maybe it's a close coworker, maybe it's someone you don't work with very [00:20:00] closely at all, you disagree.
[00:20:01] Andrew Zigler: And it could be a fundamental disagreement on something related to the product or direction or alignment, and it could be something where there's a lot of ego and skin in the game. Maybe, like, also some sunk costs as well. And so all of that attributes to, you know, sometimes when there are disagreements, we can be prone to arguing about those disagreements as opposed to working together to find the real solution.
[00:20:25] Andrew Zigler: And something that's really smart for anyone who's ever dealt with this problem of like h- someone's disagreeing with me, and the more I try to prove them wrong, the more they dig in. How do I actually go about, uh, proving my point or being correct? And this article's really great. It tells you, reminds you that you're not-- the point isn't to be correct.
[00:20:42] Andrew Zigler: The point is to find the right way forward with what the right solution is for you and that person and, and what y'all are working on together. And in today's day and age, one of the mo- amazing things you can do is that if you feel so right and so convicted and so aligned with what needs to happen, okay, [00:21:00] say that to your agent.
[00:21:01] Andrew Zigler: Make a spec. Build it out from top to bottom. It doesn't have to be an argument anymore. Now you don't have to get in an argument with the product manager or the, the t- the team lead about what the team's gonna prioritize or that this isn't important enough to be on the roadmap or whatever the case may be, uh, because you can just do it over, uh, you c- if you have that idea so firmly from top to bottom, you could spec it out, you could get it built, you could build it yourself, you could show them the art of the possible, and you could just get people on your side by showing the right way to be done and proving it.
[00:21:32] Andrew Zigler: Uh, I thought it was really just, like, obvious, but also too, like, really great advice for folks
[00:21:37] Kelly Vaughn: Yeah. No, I completely agree. You know, reading the topic, I was just gonna be like, "Oh no, that's a horrible idea," because if you stop arguing and just accept whatever, you know,
[00:21:46] Andrew Zigler: I know. They were like, "I just shrink into the... I just give up on the thing." Like no, that's the opposite. It's like you don't wanna, you don't wanna argue either. It, it becomes like you, you, you damned if you do, damned if you don't kind of situation. There's actually a hap- there is the happy medium and [00:22:00] I think that this one strikes a happy medium
[00:22:02] Kelly Vaughn: And, and you know, we all know when it comes to a disagreement, data drives the agreement.
[00:22:08] Andrew Zigler: Yeah
[00:22:09] Kelly Vaughn: more you can bring data into a conversation, the easier that conversation becomes. You know, in, in, in my role, one of the most important things that I see as I, you know, I have escalations brought to me, I raise escalations, is have to disagree and commit at some point. I think, I think it's mentioned in the article somewhere of like, it's okay to just let something ride out, and if it doesn't work, it doesn't work.
[00:22:34] Andrew Zigler: Yeah
[00:22:35] Kelly Vaughn: of those things I often see, especially with new managers, for example, who are like very prescriptive about how they want something to be built and they don't agree with what one of their ICs is recommending they do.
[00:22:44] Kelly Vaughn: I'm like, "Let them build it that way." If it doesn't work, it's a learning opportunity.
[00:22:50] Andrew Zigler: Yeah.
[00:22:51] Kelly Vaughn: agree with this. Like,
[00:22:52] Andrew Zigler: Yeah
[00:22:53] Kelly Vaughn: healthy disagreement, but understanding where that healthy disagreement turns into arguing for correctness is probably the most important line that [00:23:00] you need to identify in yourself
[00:23:01] Andrew Zigler: Right, exactly. Before that would've been you in that, or someone in that position of being like, "Oh, I don't even have to w- work to prove myself right because they will prove myself right by going down this wrong path and discovering this is not the right way." Now you can just immediately illuminate the right path that you see, and they are still allowed to follow down that, that path, and in fact, in many environments, they should be encouraged to.
[00:23:23] Andrew Zigler: You should figure out maybe you're wrong, and we should figure out which one is the right path forward. I think that's the benefit of just, like, being able to iterate quickly and that the work just has to be based on, like, alignment. We just need to understand what has to happen.
[00:23:35] Kelly Vaughn: Totally
[00:23:37] Andrew Zigler: and speaking of alignment and knowing what has to happen, you know, who can say it better than Charity Majors, the CTO of Honeycomb, uh, who has now an advice column on Stack Overflow, which I hope she has for all time because I wanna read advice columns from Charity for the rest of my life.
[00:23:54] Andrew Zigler: Uh, Charity has been a guest on the show, uh, many a times in the past, is a good friend of Dev Interrupted. [00:24:00] Uh, and in this, advice column, she, answers somebody who's asking about, like, the real kind of like, uh, problem plaguing engineering leaders around almost becoming Bond villains in a way.
[00:24:12] Andrew Zigler: Uh, this, problem that happens where our culture, where our culture of success in particular tends to have a survivorship bias of, of praising and putting of, uh, those who do make it to the end or have a certain accreditation or, or have a, like, a really big accomplishment, of putting them on a pedestal and being like, "They worked really hard.
[00:24:31] Andrew Zigler: They did that. They achieved that," and in some cases, not acknowledging all of, like, the, the work that came to that point, uh, the ups and downs in their journey because it wasn't always, you know, rosy and starry the whole way, but then also all of the people and efforts that make it possible. And I myself am really passionate around this topic.
[00:24:49] Andrew Zigler: I don't know if, for those of you who know, like, I don't have a software engineering background from college. I have a humanities degree, and I studied classics, and actually, I wrote my thesis on hero cults. And so the [00:25:00] idea of people getting all of this glommed up attention from people who attribute their success and their organizations and their outputs and everything underneath them to that one singular human is, uh, something that has actually been chronically affecting just humanity since we've existed.
[00:25:17] Andrew Zigler: It's a fundamental part of society. It's what's driven the creation and fall of every major civilization that we've ever written in a history book, and that's really fascinating to me because you see the same microcosm play out even in industries, even now within, like, places like, uh, tech where, for example, uh, the CEO of a huge tech company, you get this, like, singular idea where all of the success of Meta is Mark Zuckerberg, right?
[00:25:43] Andrew Zigler: They become inseparable in terms of their identity. And so Charity here, she gives us some amazing advice for how to navigate that reality within our industry and, uh, ultimately explains how that phenomenon comes to be. But then also gives some really amazing strategies for folks [00:26:00] on how they can be more empathetic leaders, how they can lean away from that natural in- inclination within human nature to fall into those ways of thinking about our leaders and the companies we work within.
[00:26:10] Andrew Zigler: And then she gives some really solid advice on trying to move up the ladder to become a director, um, as well. And so this is a really heartfelt, uh, article from Charity. Charity has this amazing ability to write something, and it feels like she's sitting right, uh, down right next to you having a really good heart-to-heart, and you're getting the best advice that's specific to you, and this article delivers the same thing for me.
[00:26:30] Andrew Zigler: Um, w- what did you think of this one, Kelly?
[00:26:33] Kelly Vaughn: Yeah. I, I absolutely love this article, and, and I also like, I don't wanna paraphrase this. I think it's, it's just worth reading the article itself because I- I've always loved Charity's writing. I always love how like just o- open and honest and like experienced she is.
[00:26:48] Andrew Zigler: Yeah
[00:26:49] Kelly Vaughn: very trustworthy in what she brings because it's backed by experience.
[00:26:53] Kelly Vaughn: And at risk of sounding like I am doing the same thing for her, lifting her up, there's a difference [00:27:00] because she brings so much humanity into it. And I have worked at enough companies with enough leadership to see the, the other side of the coin, to
[00:27:10] Andrew Zigler: Yeah
[00:27:11] Kelly Vaughn: especially the survivorship bias and how that kind of changes the way somebody is viewed. And as somebody who takes pride in being able to read right through that, um, you know, similar- you have a very different, uh, background. I don't know if I told you, I'm going back for my fourth degree
[00:27:29] Andrew Zigler: I know
[00:27:30] Kelly Vaughn: for
[00:27:30] Andrew Zigler: you're very educated. Yes
[00:27:32] Kelly Vaughn: of which are also in engineering. Um, you know, it's social work, it's public health, and two psy- I'm about to get my second psychology degree.
[00:27:39] Kelly Vaughn: Like very much same thing. And so like the human, the human side of this is so incredibly important for being successful in a way that doesn't feel like you're like becoming just that authoritative figure and losing, losing sight of what it means to be a leader within an organization.
[00:27:56] Andrew Zigler: Totally. And the really powerful takeaway here, I think from Charity too, [00:28:00] is that she hits on a powerful thing, which is, you know, at the end of the day, you still can't sidestep being a good business person. You have to be good, you have to be good at business. You can have a big empathetic heart and know how to lead a whole team and get people aligned around a vision and, and do so with, like, just the, the hugest amount of empathy.
[00:28:17] Andrew Zigler: But then if you're just a horrible business operator or you're not strategic or you aren't able to take your team through those opportunities and those downfalls and all of the things that are going to affect your company, then, it doesn't matter how good those morals are, it'll be really hard for you to weather that storm.
[00:28:33] Andrew Zigler: Because the reality is, is that like 90% of, you know, VC-funded, you know, startups, they don't succeed. That's the survivorship bias at work. Uh, but also I think this becomes a powerful rally for folks where it's like, this is your call to action of if, like, you are a business person and you're like, "But I don't wanna be that tech CEO, I don't wanna be that," is that you can be something better.
[00:28:55] Andrew Zigler: You can be your own thing. You can be like Charity Majors. And so there's a lot of role models [00:29:00] out there, uh, and this is a good place to start. And speaking of role models, uh, you know, Kelly, you're here on the show and you're one of my role models, and you dropped us a re- really great article recently about the backlog.
[00:29:11] Andrew Zigler: And this is a really cool blend of understanding, like, how your team works, but then also the realities of agentic engineering and how, like, teams are having throughput these days. Uh, I wanna hand it over to you. Why don't you tell us a little bit about this article and, and what came into writing it?
[00:29:26] Kelly Vaughn: Yeah. Yeah. So I have been spending a lot of time thinking about, um, how, how productivity has been shifting within an organization, like within my, my engineering org, for example, and how engineers are adopting AI to change the way they work in, in very different ways. But there's one common thread here, and I've heard it in multiple conversations, where if I'm doing multi-threaded agentic engineer- engineering, as in I'm working on multiple things at once, as in my agents are working on multiple things at once, am [00:30:00] going to run out of work in the backlog. And that would be such a beautiful thing for you to come to me and be like, "We have run out of work. What do we do next?" gonna happen, but we can focus our backlog on things that actually need to be done. And that's why I'm talking about, like, the backlog is finally getting its moment here. Because over time, we constantly have new issues come in.
[00:30:23] Kelly Vaughn: We have technical debt we accrue. We have package upgrades that we need to have done. We have paper cuts that come in. We have projects we've scoped out very, very beautifully. We deliver the MVP and we're like, "All right. We're gonna fast follow with these things. Oh, wait, there's a new thing we need to build." And that just continues to build up the backlog. And we never really spend enough time cleaning up that backlog and making sure we can keep things moving along. It's become even more important now to be able to do that because what I tend to see working as far as multi-threaded engineering goes is like you have one big thing that you're spending a lot more time on, but you have the little wins along the way as well.
[00:30:59] Kelly Vaughn: [00:31:00] It's funny because, like, that's the same way I model my to-do list too. I have one major thing, like if I get this one thing done today, it's been a good day. I've got my two things below that that are like, cool, great, and then my three like very, very tiny tasks, respond to this email kind of thing.
[00:31:14] Andrew Zigler: Mm-hmm.
[00:31:15] Kelly Vaughn: We're kind of seeing the same thing in engineering, but I have to have enough things on my to-do list to keep up with those tiny tasks.
[00:31:20] Kelly Vaughn: It's much more important to keep up with that list when you're thinking about an engineering team, because they can move a whole lot faster when an agent is able to take a very well-described customer bug, just run with it and fix it, and you've got the proper AI tools in place in your CI pipeline to be able to check for, you know, do all the linting and, and automatically make the adjustments that you may have missed a test that's failing or something, you know?
[00:31:43] Kelly Vaughn: There's so much that you can do now that we just really need to make sure that we're nailing the backlog at this point.
[00:31:49] Andrew Zigler: Yeah. This idea of s- it's smart how you would kinda like split out the capacities of work and the idea of, like, you could have these big things on your plate, and then you have all these, like, smaller things, these, like, [00:32:00] throughput things where if they were well-aligned and well-specced, and we had a really durable delivery system that we can trust for reviews and getting things out the door, then this should just be a matter of figuring out exactly what we need and staging it up somewhere.
[00:32:13] Andrew Zigler: And then this becomes a matter of engineer focuses... And this is why I like how the diagram you gave us. Engineer focuses on, like, the big, the big rock task of the week or whatever their main focus is, and then in the side channels there, a review or, like, you know, things are coming to them for review, uh, things that they're not really doing an- spending any cognitive time on other than maybe initiating or being pestered to put their eyes on it at the very end.
[00:32:37] Andrew Zigler: And then just acknowledging that those are two different lanes of capacity, and you can't, like, uh, you can't maybe, like, overfill that big lane of the big stuff and expect them to be super successful and agentic across really big things simultaneously, because that's a lot for an operator to keep in their mind.
[00:32:54] Andrew Zigler: But you could certainly think of a world where if all of the cognitive work was already done making the ticket, [00:33:00] then it should be relatively straightforward for you in your capress- professional capacity to, to, to do these, like, almost, like, micro reviews. But you have to be really smart and make it really small and make it really, like, a, uh, bite-sized for folks.
[00:33:12] Andrew Zigler: Um, but obviously it becomes, like, a really great opportunity, too, for you to harden your, uh, SDLC, 'cause I think most folks aren't even gonna be able to trust everything downstream necessarily to be able to go that fast. Sounds like y'all have, like, a durable practice around understanding when the AI-generated code is created, what happens to it, and, and where it goes.
[00:33:31] Kelly Vaughn: And we're continuing to invest in this, these tools because it's, it's such a critical part. Like the SDLC is so much more than the humans involved in it, and we really need to be investing in tool, tools that support the human side of the development process because we can't expect humans to, you know, double, triple their output without assistance
[00:33:51] Andrew Zigler: Yeah, amazing. And that's exactly what we always talk about here at Dev Interrupted and LinearB is that exact problem of just being able [00:34:00] to have a grasp on, like, your PRs and your agents and, and what are they doing and touching, but then also too what's getting delivered. And then when it's getting delivered, is it getting reworked?
[00:34:08] Andrew Zigler: Is it causing incidents? How fast are we going? And then specifically being able to granularly understand this on a per team basis. N- if you look at AI on aggregates, you get nowhere. AI normalizes itself really well when you try to, like, just do an org-wide view. But then you zoom in on a team or, uh, a department or, uh, one particular end of your SDLC, and you get a p- a picture painted if you're able to have that data on hand.
[00:34:36] Andrew Zigler: And, um, that's something that we're really passionate about. You know, if, if you're listening to this and you're definitely somebody who's trying to get a grasp on how your engineering organization is actually being successful with AI and if you're building a durable practice with sustainable code, and how do you take, um, you know, things that work really well for one team and bring it into another?
[00:34:56] Andrew Zigler: You know, that's what we focus on at LinearB. Uh, we're an engineering productivity [00:35:00] platform. Definitely recommend that our listeners check it out. But, uh, as for today's Friday Deploy episode, that's it for today's news week lineup. If you enjoyed everything that we talked about today, please be sure to give us a like and subscribe wherever that may be happening, as well as dropping us a comment on LinkedIn.
[00:35:15] Andrew Zigler: Kelly and I would love to hear from you on LinkedIn. Please come pester us. Uh, we love hearing from folks who hear us gab, and I'm sure you'll be hearing more of us later this year as well. Uh, and so thanks again, Kelly, for joining us today on the show
[00:35:29] Kelly Vaughn: Yeah. As always, thanks for having me
[00:35:31] Andrew Zigler: Thanks so much
