Transcript: Navigating the Future: Gas Town and Bespoke AI Agents
0:00 Scott And I'm just kind of thinking about how that's going to go. Like if all of our companies are out there having to build our own software factories,
0:05 Scott our own agents,
0:06 Scott all this stuff, there's a lot of risk in that.
0:08 Scott I'd love to have the wisdom of the crowd.
0:27 Scott Hello, Brad.
0:28 Brad Hello, Scott.
0:29 Brad How are you doing?
0:31 Scott I'm happy to be at another week of How Many CTOs Does It Take podcast.
0:36 Brad How many CTOs does it take?
0:38 Scott It takes two,
0:39 Scott you and me. We
0:40 Brad There
0:40 Scott can solve
0:40 Brad you go.
0:40 Scott any problem together.
0:41 Scott You,
0:42 Scott me, and an AI agent can solve any problem in the world.
0:45 Brad Exactly. So welcome everybody to another episode of the How Many CTOs Does It Take podcast?
0:50 Brad I'm Brad Hefta-Gaub.
0:51 Brad This is my trusty co-host and
0:53 Scott Scott Porad.
0:55 Brad Scott, what are we going to talk about today?
0:58 Scott We're going to talk about a LinkedIn post that I saw of yours,
1:01 Scott Brad,
1:01 Scott that went viral.
1:02 Brad That went viral. It did. Actually, I've had a couple that have gone viral in the last week.
1:06 Brad So it's been a strange experience for me. I'm not used to my LinkedIn posts going viral.
1:11 Scott You're internet famous now.
1:12 Brad Oh,
1:13 Brad I don't know about that.
1:14 Scott Let me read to our audience what you had to say.
1:19 Scott And then I have a comment or
1:20 Brad Yes.
1:21 Scott two that I'd like to explore.
1:25 Brad Like the 56 other people that also had many comments on this post.
1:32 Scott Let's see how many comments are on this post.
1:34 Brad 57 comments on this post,
1:37 Brad 88 likes.
1:40 Brad So.
1:40 Scott Okay.
1:41 Scott Software companies, according to an author named Brad,
1:44 Scott have to go.
1:46 Scott Build generalized products because software was expensive to write.
1:50 Scott The labor costs only made sense if you could sell to a million customers.
1:55 Scott So you built configurable platforms with massive option services, then hired implementation consultants to bend them to fit each customer's.
2:05 Scott There's actual workflow.
2:06 Scott AI just collapsed that math.
2:10 Scott Satya Nadella, CEO of Microsoft,
2:12 Scott said it bluntly on the BG2 podcast.
2:16 Scott Is that a different podcast you have, Brad?
2:18 Brad That's not my podcast.
2:20 Brad That's not my podcast.
2:22 Scott We should get Satya on our podcast.
2:24 Brad Satya will definitely join the How Many CTOs podcast for sure.
2:27 Brad Hey,
2:28 Brad Satya, I know you're one of our 39 listeners,
2:30 Brad so just hit up our producer and we will definitely have you on.
2:35 Scott SaaS apps, according to Satya, are essentially crud databases with a bunch of business logic.
2:41 Scott Business logic is all going to these AI agents.
2:44 Scott Mark Cuban has been amplifying the same point,
2:47 Scott noting that 30 million U.S. solopreneurs and SMBs were never well served by enterprise SaaS in the first place.
2:56 Scott The math just didn't work. Now it does.
3:00 Scott Custom workflows for a regional law firm,
3:03 Scott a vertical specific CRM for the dozen companies in your industry that hate Salesforce,
3:08 Scott internal tools for every SMB needs.
3:12 Scott need but nobody could profitably build.
3:14 Scott SaaS got fat because generalization was the only way to recoup engineering costs.
3:20 Scott That's no longer true.
3:22 Scott The next decade of software is going to be a lot more bespoke.
3:27 Scott Okay, here is my reaction to that.
3:30 Brad Tell me.
3:31 Scott It's got a few parts.
3:33 Scott Part one,
3:33 Scott agree.
3:36 Brad There we go.
3:37 Brad End of podcast.
3:39 Scott Part two,
3:40 Scott sort of.
3:42 Brad There you
3:42 Scott We're getting a podcast.
3:43 Brad go.
3:45 Brad By the way, just to be clear,
3:47 Brad you know, whatever, this is a, you know, I think actually when I wrote this, like I wrote it a couple, I had to like, I had a version of it that I wrote and then LinkedIn was like,
3:56 Brad oh, that's too many words, you can't post that.
3:58 Brad So then I had to like figure out like, how do I cut some of this out?
4:01 Brad But there's a lot of nuance going on there.
4:03 Brad So I will say that, I will say that like,
4:06 Brad I will argue with, there's many interpretations.
4:09 Brad of this as evidenced by the 57 some odd comments that that have been a combination of there's definitely been a combination of haters and lovers of this post right so people have piled on with you're an idiot that's never going to work to this is exactly what I'm doing and I'm making money doing it so
4:27 Scott So the two examples that you gave are actually are perfect.
4:32 Scott like segue into the question I fundamentally have or the thing that isn't working in my head,
4:38 Scott but maybe you could answer it.
4:40 Scott Custom workflows for a regional law firm is one example.
4:44 Scott Vertical specific CRM for a dozen companies.
4:47 Scott Okay,
4:47 Scott so the vertical specific CRM makes a lot of sense to me.
4:51 Brad Yeah, like let me give an example what I mean by that, right?
4:53 Brad Like, I don't know anything about being a plumber, but I would imagine that
4:58 Brad A custom-built CRM for plumbers would have a lot of very specific features to plumbers that wouldn't matter to veterinarians.
5:09 Brad Right.
5:10 Brad But could be but to get that in Salesforce,
5:14 Brad like, yes, Salesforce has all the bells and whistles and you could you could definitely configure it and you can hire Salesforce,
5:19 Brad you know, deployment engineer to do it. But like the average plumber is just like, screw that.
5:24 Brad I just, you know, I need to be able to, you know, reach out to the people that I regularly clean the pipes of and and give me a version of that that's specific to my needs.
5:34 Brad That's that's the example I'm.
5:35 Brad I'm used that's kind of my core example there
5:38 Scott So there's, I think that's a workable example.
5:42 Scott And let me give you a few reasons why I think it's workable. Because you've got a fair amount of customers, a dozen, whether it's just one person or whether it's just a few people,
5:51 Scott they're going to be around to maintain and support that software for a while.
5:57 Scott And in addition.
5:59 Scott The plumber doesn't quite know what they need.
6:02 Scott I mean, they can make feature requests and say this is how I want it to work.
6:05 Scott But there is some value to the 13th plumber of having a platform which is.
6:15 Scott suits them out of the box as opposed to having to sit down from scratch and figure out what do i need in a crm it reminds me of a dealbert by the way where
6:26 Brad Yeah.
6:27 Scott uh i don't remember the name of the program manager in deal where the product manager but there was an intern named asok and the product manager was saying to to the intern what kind of software do you want me to build and the intern said well i don't know what kind of software
6:41 Scott I don't know what I want until you tell me what it's capable of.
6:44 Scott It's the same kind of thing in the sense of you could sit down with a plumber and say, I'm going to design a CRM just for you.
6:50 Scott But there are all sorts of things that a plumber might need in a CRM that they might never think of and you get some wisdom of the crowds.
6:57 Brad Yeah.
6:58 Brad Well,
6:59 Brad and just to clarify,
7:00 Brad like I am.
7:02 Brad not trying to say that the cost of building collapses so much that you could go build a completely bespoke CRM for each plumber, right?
7:14 Scott Mm
7:14 Brad Like I agree
7:14 Scott -hmm.
7:14 Brad with your point that like plumbers in general will have some needs that there's enough commonality across them that you'd be able to.
7:26 Brad build build the plumber crm and it would be cheaper for you to build it than it and cheaper for you to operate it for for this this niche audience of smes
7:36 Scott Mm-hmm.
7:36 Brad then it would be for each of them to get a salesforce license and a salesforce custom customization engineer etc so that's that's like the simple that's kind of like the simplest distillation of the that that point that i would make and and if you actually like
7:52 Brad Like the Cuban was on the,
7:56 Brad you know, the.
7:57 Brad tbpn vlog video podcast and this was like back in i think it was actually in december so it's not like this is brand new and he was basically like saying hey if you're like a young scrappy entrepreneurial you know fresh out of college go go get embedded in small businesses learn their learn their businesses and then bring your bring ai skills to bear to basically
8:24 Brad solve problems for them and there's and that's a healthy business that's not going anywhere is what his point was and and so i'm kind of just riffing off that point a little bit
8:34 Scott Totally get it.
8:35 Scott Okay,
8:36 Scott so the other example,
8:37 Scott custom workflows for a regional law firm.
8:39 Scott This is the one that puzzles me a little bit.
8:43 Scott So let's say I'm a guy.
8:44 Scott I'm an independent software developer.
8:47 Scott I get hired by
8:49 Scott a reputable firm of you know poor Adam has to go to build some custom workflows and so I go in now I've got it I've actually got to have some real product management skills to go in there and understand what they need then I got to build it for them and you know then it's there
9:11 Scott And maybe it's doing its thing.
9:13 Scott I suspect the industry is moving so fast that it's going to need to get updated quite frequently.
9:20 Scott And, you know, am I going to be around to continue to support this law firm or in another 18 months?
9:29 Scott are they going to come to me for support and say hey we want you to do something or this is stop working all of a sudden and
9:36 Brad Yeah.
9:36 Scott where am I where am I going to be am I still going to be doing this thing of making software out for little companies or will that trend passed and I went and got a job at meta or um you know who knows what so
9:48 Brad Yeah.
9:49 Scott I just that's the one the the the relatively bespoke software for like
9:54 Scott everybody getting their own software at their own firms for their own things and that firm that they're going to start doing their stuff whatever they use for this custom workflow is going to be some wacky way and all there's going to be all this differentiation
10:05 Brad Yeah.
10:05 Scott across the regional law firm community and it's going to be a mess so i just that's the part i'm having a hard time getting my head around what about that one
10:14 Brad And to be fair, that was definitely a thread in some of the comments of the haters.
10:19 Brad on the on the thing saying oh this will be just total chaos and like why you know you know if you think sass is bad then imagine like all this bespoke stuff that'll just be chaos and i think i think that they are leaning into that my now my only defense of my comment would be simply my defense of my post would be well
10:36 Brad I'm making a I said the next 10 years,
10:40 Brad right?
10:40 Brad So I just think like, I
10:42 Scott Yeah.
10:42 Brad mean, there's a big picture here. And the point I think the point that I'm making is that or the point I feel confident in is that this stuff has changed so it's gotten so much better in the last two years.
10:58 Brad that you and i've been paying super close attention to it that there's no doubt in my mind that the the build cost is going to continue to collapse and therefore the idea that um you can build these custom things and it's a lot you still got to have good strong engineering best practices but it just is much cheaper to build things
11:24 Scott Yeah, I'm having a hard time even conceptualizing what it's going to be like in five years.
11:31 Brad Yeah, agreed.
11:32 Scott I can't imagine it really.
11:34 Scott I mean, I can kind of imagine some things,
11:36 Scott but.
11:36 Brad I mean, we could talk more about this question of like the post that went super viral, but there were two other posts that I posted this week that were in relation to this topic that also went viral themselves.
11:47 Brad Not quite as much as that one,
11:49 Brad but still pretty big numbers from my perspective. And those were more engineering focused posts.
11:56 Brad And one of them was very specifically kind of.
11:59 Brad kind of pushing back on the i run my 20 agents overnight and they they write they make all this magical stuff for me and i'm you know and i you know it's production software and yay and i'm pushing back on that saying like hey in my fractional cto work that's not what i'm seeing i am seeing teams that have fully adopted ai um
12:21 Brad coding and they've got it built into their kind of AI oriented SDLC or their ADLC as you and I have called it a couple pods ago and they are cranking out lots of business value you know thousands of lines of code per developer of business value a day and of course you know I always joke about clock we all know clocks is a total
12:45 Brad Bad metric,
12:46 Brad right?
12:50 Brad They are really, really, I mean, the costs for building is plummeted for them and that's causing them to build really fast. And when they're doing high quality engineering techniques around the building, they're getting amazing results.
13:04 Scott Yeah,
13:05 Scott that's right.
13:06 Scott And that is where I'm going with TaskRabbit right now is what you talked about in this post,
13:10 Scott which is getting the environment set up.
13:14 Scott to really do the real deal and that's it that's going to be the new world and that'll actually that'll be i think what separate the good teams from the great teams
13:21 Brad What I think is interesting about that is that set your environment upright.
13:25 Brad Like that's got nothing to do with AI.
13:27 Brad That's actually just got to do with like good software engineering techniques.
13:32 Brad And I do think that
13:35 Brad I mean, I'm not seeing people really I'm not seeing a lot of people be successful with this sort of dark factory or to say like, you know, like there's not humans watching the robots.
13:45 Brad I'm not seeing anybody do that yet myself in my experience.
13:48 Brad There's a lot of people claiming that they're doing it. Here's my guess,
13:52 Brad pretty strong expectation.
13:55 Brad The ones that are actually succeeding at that have built the harness around their agents in such a way that it's the same safeguards that would have guarded against humans writing code that fast.
14:07 Scott Yes, that's right.
14:09 Scott Imagine if you had a new employee show up on the first day and submit a 70,000 line PR,
14:13 Scott what would you do?
14:14 Brad Yeah.
14:16 Scott Can we talk about the dark factory thing for a
14:18 Brad second? Yeah, totally.
14:19 Brad Let's do it. Cast town,
14:20 Brad baby.
14:21 Scott Gastown, did I talk to you about Gastown?
14:23 Brad I mean, it's all over the place.
14:25 Brad Tell me about your, you just learned more about Gastown, right?
14:29 Scott I did a two-day intensive hands-on workshop with the founder and co-founders of Gastown.
14:35 Brad Nice.
14:36 Scott Do you think Gastown is ready for primetime?
14:39 Brad Well,
14:39 Brad I haven't tried to use it myself,
14:41 Brad but I was reading articles about it.
14:43 Brad Actually, this morning I was reading some of the more detailed articles about it, and I'm intrigued.
14:50 Scott Well, I spent two days with it and it was very intriguing.
14:57 Scott I have Plodits and what's the opposite of Plodits? I have compliments and complaints.
15:06 Brad Okay.
15:06 Scott It's cool.
15:07 Scott I mean, it opened my eye. It brought my mind to a new level.
15:11 Scott what this could be right and so like it was mind expanding for me and just for context this was a two-day workshop organized by the AI tinkers meetup which is a meetup group organized by my friend Joe Heitzberg and he's got chapters all around the globe and they organized this thing with
15:34 Scott gas town the the founder the two co-founders of gas town there's like a ceo and a cto and that's why i keep on saying founder and co-founder but they're just two guys together so that was cool and i gave it a simple spec and i set about 15 agents about i kicked it off and it worked away for about 20 hours and it came back with seemingly a functioning product for what i wanted which was basically just a fantasy football
16:01 Scott mobile app game um it didn't work perfectly because i didn't there were some things i didn't understand about how to use gas town or really even how to use a software factory i just gave it the spec and i gave it the command make the mobile app and then it went to work for 20 hours and i gotta you know that's not the way it turns out that's not the way you should do it i should have done it iteratively one step at a time just like we've done just like plan mode right
16:28 Scott But I had on my machine running a planner agent,
16:32 Scott a PM agent,
16:33 Scott a designer agent,
16:34 Scott five builders,
16:36 Scott two reviewers,
16:37 Scott and a deployer. It brought my machine to a screeching halt at times.
16:43 Scott So we've got to figure out that problem.
16:44 Scott That's a new problem we're going to have.
16:45 Scott Like I couldn't run five gas towns at once on a MacBook Pro.
16:49 Scott maybe if i had like 64 gigs of ram right now or something i learned some i learned some cool ways how to nudge it um like it would get stuck and so like i told it stuff like okay i want every i started to build up this i know it was a cron job under the covers but i started to build up this thing like every five minutes i want you to do x and at first i was just like i just want you to tell me your status and then it was like tell me if you got any questions you need anything to block you either or you need
17:16 Scott you need me to help you move you forward and then i noticed sometimes some of the agents would just stop and so um i said hey i want you to just nudge the agents every five minutes and be like get back to work kind of thing you know and so it was all really cool it was all really neat to see how this is all going to unfold um i thought two or three negative things i mean the gas sounds super raw so i got to give it a break i mean they released it on march 1st or something
17:41 Scott or something like that so i
17:42 Brad Yep.
17:43 Scott think version 1.0 came out last week was beta like three weeks i mean they're using gas town to build gas town i'll say just as a personal preference they're using this city metaphor with the mayor and rigs and all these different words and i just think that's that's a turnoff for me because i'm having to do this translation what's a rig
18:04 Scott oh rigs is the app that you're building okay then why don't you call it your app right what's the what's the mayor well the mayor is kind of like the supervisor of the whole thing it's like okay like why don't you just call it the supervisor you
18:14 Brad Right,
18:14 Scott know so
18:15 Brad right.
18:15 Scott um so i've never been a big fan of like the sort of cutesy
18:21 Scott nomenclature for a thing and i think that'll be an i actually think that'll be an impediment to gaston because i think across the industry you know big companies won't want that kind of nomenclature in their environments and then the other piece is like how long before all this stuff is just in cloud code cloud already has this thing called agent teams
18:43 Brad Yep
18:43 Scott Actually, I don't know if you've used it. I haven't used it yet.
18:46 Scott And there are many other competing factory frameworks out there.
18:50 Scott But it showed the skeleton of how it's going to work. There are going to be agents,
18:54 Scott there's going to be a harness for them with an orchestration between them, and there's going to be a communication mechanism between them.
19:02 Scott I think those are going to be the puzzle pieces.
19:04 Scott And then, you know, you'll be able to customize all your agents and customize all a million different things.
19:11 Scott It's going to take time to set up your factory. I think that's the last thing I learned.
19:15 Scott There are factories out of the box,
19:17 Scott but then you're going to have to go about building your own.
19:23 Scott factory customizing that factory your front-end agent and my front-end agent are going to be well this factory I had just had a builder agent and someone might make a front-end agent and a back-end agent that are more specialized
19:35 Brad Well,
19:36 Brad and I can imagine a world where you had two reviewers,
19:40 Brad but maybe you're going to have a security expert reviewer and then you're going to have another red team.
19:48 Brad reviewer and you're going to have a compliance
19:50 Scott Yes.
19:51 Brad officer reviewer and you're going to have a you know design reviewer or whatever
19:55 Scott I thought it was really cool.
19:58 Scott It really helped me see.
19:59 Scott We've talked about learning here.
20:02 Scott it you know the ways people learn I'm really a very much a kinetic visual learner and
20:07 Brad Yeah.
20:07 Scott so just seeing it seeing you know the guys who did it put it on the screen and say this is how we did it getting to go through a lab and just you know build something on my own was really helpful it really helped me just like oh okay I see where the future is going with this thing like I saw it before like intellectually but now I get it like in my kishka's like oh I get this you know like
20:27 Scott like here's a question for you i know your personal perspective on this because we've talked about it so much like that you
20:35 Scott uh believe that this is the trend is happening and you're gonna you gotta get on the bus or or not um but here's my question for you
20:44 Scott The three posts for me that went viral this week all had this notion of talking about really using AI in production code.
20:53 Scott I did express some skepticism of the are the agents really ready yet, right, to be just let free.
21:03 Scott You know, and I've obviously talked about like with this small business thing, I talked about how, you know, cost of building is collapsing. And so, you know, that just opens up more opportunities.
21:12 Scott Okay.
21:13 Scott So that was kind of the themes of my posts this week.
21:16 Scott I was genuinely surprised by the number of
21:25 Scott very experienced senior operators in my LinkedIn network and that got that caught this on LinkedIn who were still completely poo-pooing AI as being able to write production code I was shocked by that and I'm kind of curious I don't know what do you
21:50 Scott What are you seeing?
21:51 Scott What's your take on this?
21:53 Scott How is that still a thing?
21:56 Scott Well, I've got a few answers to that.
21:58 Scott The first is I'll start with something potentially a little humorous.
22:02 Scott There's a famous quote by I think the author H.L. Mencken.
22:06 Scott Right.
22:08 Scott But it could have been by Upton Sinclair,
22:09 Scott I believe.
22:10 Scott Actually, I believe it was by Upton Sinclair,
22:12 Scott now that I think about it.
22:13 Scott And for those of you on this podcast who do not know who Upton Sinclair is,
22:17 Scott he wrote a book called The Jungle,
22:18 Scott which actually,
22:20 Scott going back and reading that book, might be highly relevant to the times in which we are living.
22:24 Scott Yeah, good call.
22:26 Scott The Industrial Revolution, it was about the Industrial Revolution and the impact it had on workers during the Industrial Revolution. And we're going through an AI revolution.
22:33 Scott And what he said, he had a quote that's attributed to him, which is, it's hard to get a person to understand something when their living depends upon not understanding it.
22:49 Scott Yeah
22:50 Scott That's my first thought.
22:51 Scott My second thought is I run into people all the time who are naysayers.
22:57 Scott they don't believe it's going to happen and they don't think production ready code they don't think it's ready and almost all of them I think almost all of them have not actually used it they've not really
23:10 Scott They genuinely sat down with an open mind and tried to engage with it and said, can I make this work?
23:17 Scott And when they did engage with it, did not follow the best practices for doing
23:21 Scott Yeah,
23:21 Scott so.
23:21 Scott they were sort of like pre-biased to want to see it fail.
23:26 Scott So they did stuff with it that they themselves wouldn't do themselves kind of thing.
23:31 Scott Or, you know, they just did a little bit and they're like,
23:34 Scott it isn't really working.
23:35 Scott And I know that the people who I think most highly of and who I think are most talented with it, and frankly, Brad,
23:42 Scott I include you in that group.
23:43 Scott I know the people who are the most who are getting the most out of it have spent hundreds of hours trying to figure it out, working with it, learning how to work with it. Those people.
23:56 Scott are submitting 70 000 line prs that are flawless all generated by ai right
24:01 Scott Yeah.
24:01 Scott which is insane that someone would do that but they've got the quality they've got the process and procedures in place they've got the quality gates in place
24:10 Scott I'll tell you a fun story. For the first time, I've actually,
24:13 Scott it wasn't 70,000 lines, but I was working on a tiny little, a tiny project on a side project I was working on and I had a
24:21 Scott Basically had a agent write a B2C style like monthly subscription stripe integration,
24:30 Scott you know.
24:31 Scott thing for me so had
24:32 Scott Mm
24:32 Scott a very clean spec that i wrote and then had the agent go off and build it and um you know had that had the framework that i'm always preaching of having like you know strong quality gates and stuff and one of the quality gates i'm very used to is like i always give i always always always always always always let copilot run a code review on anything and the first time ever i had a pr
24:56 Scott that was 24 000 lines of code and i found out that copilot has a limit of 20 000 lines of code to do to do copilot code reviews so
25:07 Scott That's interesting.
25:08 Scott i had to like go oh okay hold on a second well half that half that pr was actually unit tests so it was a pretty easy fix like okay like split split the unit tests off as a separate pr and
25:19 Scott And I don't think we want huge PRs. I think we still want small PRs.
25:23 Scott PRs.
25:23 Scott So one of the things I'm very much seeing for real in the teams I'm working with is they're pretty much all pretty much the smallest PR I'm seeing at this point is like a small PR is now a thousand lines of code.
25:39 Scott And most of them are more like averaging closer to three thousand lines of code.
25:50 Scott they wouldn't want to split those up into 3,000 line PRs.
25:55 Scott because the work product of what they're able to get done has grown to the point where you can essentially implement a whole epic.
26:05 Scott Now, you still want to be iterative, and you still have broken it down, and you've still challenged the agent to break it down, and you've done a whole bunch of local testing and validating the plan well before it got built.
26:19 Scott splitting it into three smaller prs or four smaller prs actually makes the job of the reviewers harder because they they have to review essentially the piece and like it's only meaningful once all the pieces are put together like it's it's it's not only meaningful but it's it's much more meaningful when all the pieces are put together so that you can
26:43 Scott see the functionality manifest end to end,
26:48 Scott right?
26:48 Scott Mm-hmm.
26:49 Scott And so this is something that I do think
26:52 Scott I do think is challenging one of our standard practices that we would always say to people is like,
26:58 Scott Mm
26:58 Scott hey,
26:58 Scott -hmm.
26:59 Scott break it down,
27:00 Scott get your back end working correctly,
27:02 Scott have like super solid unit tests against your back end. If your front end is coming before your back end, then great.
27:07 Scott Implement like mocks or something like that, that your back end, you know, if when the back end arrives,
27:12 Scott it fully manifests the contract that you've agreed to,
27:15 Scott then your front end will work perfectly. And that's how we would like.
27:17 Scott would like break things down into smaller pieces and still get them over the finish line well that model which which was a which was a perfectly reasonable model that we've used for you know decades
27:29 Scott That actually creates more work for us if it's possible to stand up the back end and the front end at the same time across the same platform and demonstrate it.
27:41 Scott Right.
27:42 Scott And this was actually something that remember when we when Justin Kaufman came on and he was telling us all about the project he'd worked on, he basically made the case for like,
27:50 Scott yeah,
27:51 Scott I'm like all about mono repos now. Like, I'm just going to like.
27:54 Scott It's just so much easier to build features when the entirety of the stack is available for me to work in.
28:03 Scott Mm-hmm.
28:04 Scott Yes,
28:04 Scott agree.
28:05 Scott In fact, we're having this conversation about whether we should sort of move to a model right now.
28:10 Scott Coming back to the naysayer thing,
28:11 Scott the only thing I wanted to add was, you know, I was just talking to someone.
28:15 Scott earlier stay at my organization who is who is on the leading edge and he has been also frustrated by people and he gave this analogy he said I feel like I'm talking to people who are saying I'm not sure if this airplane thing is a good idea and he's like he's like what I just flew here on an airplane and it was effing awesome right and to me it's about experience I've just the people I see the people who I I mean maybe this is a
28:40 Scott a truism,
28:41 Scott but the people who are really making it work had to spend time to get there.
28:47 Scott Yeah,
28:47 Scott And
28:47 Scott I
28:47 Scott now, is it that there were other people who spent time to get there and they couldn't make it work and so these are just some lucky ones?
28:54 Scott I don't know. But these people
28:55 Scott don't buy who that.
28:56 Scott I see, the people who I see making it work also before AI were among the most talented engineers I knew.
29:03 Scott Yeah.
29:03 Scott So I see that those going hand in hand. And the last thing I'll say to the 39 people listening to our audience,
29:10 Scott I haven't asked every one of these engineers,
29:12 Scott but several of them are telling me.
29:13 Scott or tell me i'm having more fun engineering than i've had in a long time right i mean to be a professional commercial software engineer it's a little bit of a grind right you work in a big company there's product managers there's meetings you
29:25 Scott Yeah.
29:26 Scott know you're doing stuff you got to spend time writing the test it's all it's all a lot of work right and i'm thinking one guy in particular who you know said to me like it's just i'm just get it's just fun to get so much stuff done i just
29:38 Scott just feel like i have been released from
29:41 Scott Yeah.
29:42 Scott so much and the visual i have in my head is um you know play-doh you ever play with play-doh yeah
29:48 Scott You mean the Play-Doh like what we played with as kids?
29:52 Scott and
29:52 Scott Yeah.
29:52 Scott Okay.
29:52 Scott you know how easy it is to make a snake with play-doh you just roll your hands together like this
29:59 Scott I feel like it's like making the snake.
30:01 Scott It's like, that was easy.
30:03 Scott Yeah.
30:03 Scott This is fun.
30:04 Scott I just made something.
30:06 Scott Yeah.
30:06 Scott I don't know. But so that's what I've seen. And, you know, what are the reasons people that then there's all sorts of reasons people have for why it won't work.
30:16 Scott That's fair.
30:16 Scott That is fair.
30:17 Scott Okay.
30:18 Scott And I definitely agree with what you're saying.
30:20 Scott And I think that that's what I'm seeing in the people that I work with, the ones that are basically open minded, curious and were already good engineers to start with were already creative.
30:29 Scott Like it's just like, bam,
30:30 Scott this is this amazing tool and I already knew how to write code and this thing is just helping,
30:35 Scott you know, I can just get it to write code correctly the way that I would have written it and it's just making me so much faster. Right.
30:42 Scott And,
30:43 Scott you know, another one on this.
30:45 Scott i would say is like one of my senior engineers i work with regularly he was like it's doing a better job of code reviews than i ever did right
30:52 Scott Mm-hmm.
30:53 Scott it's like yeah like it it is a it is finding the obscure things that were really hard to find you know and so you know again like i agree i clearly am a believer and a convert that this tool is really quite amazing
31:10 Scott Now, in the last week, there have been some pretty colossal, some pretty colossal massive mistakes.
31:19 Scott The startup that accidentally deleted their production database because they let Cursor get,
31:26 Scott you know, had an MCP server to essentially the database and it like it literally just saw some it had some bad mismatch keys and so it decided it was going to fix those.
31:36 Scott It's those mismatched keys,
31:38 Scott and it basically deleted the database and the backup.
31:41 Scott Look,
31:42 Scott the AI agent isn't eager to please entry-level engineer.
31:47 Scott I'm sure at some point in my early in my career, I deleted something I shouldn't have.
31:51 Scott And over a generation,
31:54 Scott my generation,
31:55 Scott we built up all sorts of guardrails to prevent against those things.
31:59 Scott Right,
32:00 Scott and so I guess I'm throwing that out as an example of...
32:04 Scott That's great fodder for all the naysayers.
32:08 Scott Totally.
32:09 Scott And to which my response would be, who gave your local development environment write access to your production database?
32:17 Scott I mean, this is just basic development practice.
32:21 Scott You wouldn't have given write access to your eager to please intern.
32:24 Scott You wouldn't let your intern make a change to your database without having it looked at.
32:30 Scott Right.
32:31 Scott I mean, you know, one of the things I've learned, you've probably learned it too,
32:34 Scott is when anytime somebody is doing a major change to our environment,
32:38 Scott the first thing I ask is, what is your rollback plan?
32:42 Scott Because things go wrong. So if you don't have a rollback plan before you go into doing it, my point is like, no, you need to get that together first and then go do it.
32:52 Scott And that's Murphy's law in action, because when you get your rollback plan together,
32:55 Scott then you don't need it.
32:56 Scott Right. Exactly.
32:57 Scott Yeah.
32:58 Scott And
32:58 Scott Premium.
32:58 Scott if you have a, and whenever I see a plan of some sort where it says like, this is a point of no return once we go past here or whatever,
33:05 Scott I'm like,
33:05 Scott no, you guys need to go back and rework this,
33:07 Scott figure it out. There's some other way you can do this, I'm sure.
33:10 Scott Right.
33:11 Scott You can make it safe because we've learned from all those production databases that we fat fingered on our own.
33:18 Scott One of my non-technical buddies who's using AI pretty aggressively, and he's very technical actually,
33:25 Scott but he's just not a classically trained software engineer.
33:28 Scott He and his co-founder is a classically trained software engineer. They've set up their,
33:34 Scott and I don't know if they're using Gastown or not,
33:36 Scott but it sounds almost like they're using a Gastown type thing.
33:38 Scott And they have two different code review agents and one
33:41 Scott Mm
33:41 Scott of
33:41 Scott -hmm,
33:41 Scott the code review agents they've given the persona of the the eager rising star with a bias for action and just get it done.
33:50 Scott And then the other code review agent,
33:52 Scott they've given it as the persona of the grizzled veteran that has seen so many production failures like,
33:59 Scott you know, you wouldn't believe this war stories I have and they literally.
34:04 Scott really set up they gave their coding agent their code review agents these personas intentionally to get like you know essentially antagonistic reviews
34:14 Scott Okay, there's a few things I want to say.
34:15 Scott I want to come back to the previous thing about rollback plans and just I want to give a nod to Mike Hansen if you're out there listening once Mike Hansen and I effed something up really badly in production and we got it all fixed and ready we had a script already to fix it and he did something which I thought was so wise that I've taken with me he was like we're working as fast as we can to fix this problem we're ready to push the button again to like fix it
34:40 Scott And he said, you know, why don't we just wait for an hour?
34:44 Scott Why don't we go get some food?
34:46 Scott Just let's just see if anything comes to our mind that maybe we haven't thought of before we push this button again to fix the problem that we already made and then make another problem.
34:55 Scott Right.
34:55 Scott And I just thought that was so wise.
34:57 Scott Yeah.
34:58 Scott He was like, why don't we just wait?
35:00 Scott I know we're in a hurry,
35:01 Scott but why don't we just wait one hour and maybe we'll just think of something.
35:04 Scott Yeah, there's a quote that totally resonates with that that I've heard from my mountain world is don't just do something.
35:12 Scott stand there.
35:14 Scott Yes, that's right.
35:16 Scott That's right.
35:17 Scott Okay,
35:18 Scott so you're talking about the two agents.
35:20 Scott When I was with the Gastown crew last week,
35:23 Scott I can't remember the exact scenario they had.
35:27 Scott I think it was similar to this code review.
35:29 Scott They had three personas,
35:31 Scott like these code reviewers.
35:33 Scott They ran them all.
35:36 Scott three on the three major models so gemini uh whatever open ai's got whatever whatever model gemini there's some gemini models some open ai models some anthropic models and then they had they had nine reports
35:49 Scott Then they had three other agents that synthesized all these together. So then they had three reports and then I can't remember how they whittled it all down, but they had built this whole layered things of different perspectives, synthesizing different perspectives to come up with.
36:07 Scott Yeah,
36:07 Scott this is OK.
36:09 Scott Yeah.
36:09 Scott If all these different perspectives from these different models, because remember the models do stuff differently,
36:14 Scott they've got biases built into them, you know, and so it's the same idea and that's probably where all this stuff is going to go,
36:19 Scott which leads me to a question I've been sitting on for about 20 minutes now.
36:22 Scott So okay,
36:23 Scott code reviewer agent,
36:24 Scott grizzled veteran,
36:25 Scott eager,
36:26 Scott eager intern.
36:29 Scott When I was doing this training last week and we were getting it all set up and you're setting up all your agents,
36:36 Scott you know, I was just copying.
36:38 Scott agents that they had made for this workshop that i could just use to like use the thing and they talked about like look you're going to kind of create these for your own company for your rules for how you want to do your business in fact i was talking to another company today and they were i was talking to the cto was telling me how they created like you know front-end agents and develop different types of developer agents all this different stuff they'll specialize for how they like to do it at their company
37:03 Scott And the thought that I've been kind of running through my head is,
37:08 Scott do you think that's how it's going to work or do you think we're going to?
37:12 Scott like is there going to be maybe maybe be more of a marketplace for agents where like i'm just either i'm just buying the grizzled veteran code review agent and it's got it's in github and it's got 50 000 stars or whatever so everyone thinks it's really good and we just like we've all as an industry agreed like this is the good one and maybe it's an open source agent so people can submit
37:33 Scott because an agent's just an MD file.
37:34 Scott People can
37:35 Scott Yeah.
37:35 Scott submit improvements to it.
37:36 Scott I'm just kind of thinking about how that's going to go. Like if all of our companies are out there having to build our own software factories,
37:42 Scott our own agents,
37:43 Scott all this stuff, there's a lot of risk in that.
37:45 Scott I'd love to have the wisdom of the crowd in that.
37:48 Scott Yeah,
37:48 Scott it's a great question.
37:49 Scott I have a couple.
37:50 Scott feel i think is probably going to be a little bit of both that's my answer you know i'm going to stick with that one it's going to be a little bit of both you know we've already been living this with open source right like there are
38:02 Scott you know, open source frameworks like that are clearly benefiting from massive amount of support.
38:08 Scott And so to your point, it's like the wisdom of the crowds.
38:10 Scott And then there are still opinions and one
38:13 Scott Mm
38:14 Scott opinionated
38:14 Scott -hmm.
38:14 Scott version of a framework versus another opinionated version of a framework like and, you know, so I think there will be I think there will be room for diverse opinions in this.
38:30 Scott And that kind of goes back to the point that I was making in my post that went viral is that the cost of building actually has gone down so much that you're allowed to be opinionated because it used to be it used to be cost prohibitive to be opinionated and now it's not cost prohibitive.
38:48 Scott That's exactly right.
38:50 Scott That's why you end up with products like Jira.
38:52 Scott Yeah, exactly.
38:54 Scott The thing that I feel pretty certain about that for the and I'm going to say near term, I don't know how long this near term is, but for the near term,
39:03 Scott I feel like I've been saying this for a while. It's the K-shaped economy.
39:07 Scott The people that were already.
39:10 Scott good at building software and knowing how to build software in a high quality way those people are really and and then they they decide to adopt AI strategies they're the ones that are going to just get these massive outsized gains and then people in the lower half of the K are either going to be a combination of to your point people that aren't open-minded aren't curious maybe they were very talented
39:36 Scott But they've just for whatever reason, reluctant to actually adopt and be curious about the tools.
39:43 Scott That's part of it's going to be that.
39:45 Scott And then the other part, I think, will be filled with people that don't have the fundamental engineering expertise. And so they're very much dependent on getting lucky.
39:59 Scott And
39:59 Brad Mm
40:00 Scott not
40:00 Brad -hmm.
40:00 Scott being able to check the work of the agents. And at least now in the short term,
40:05 Scott I think that's a very real, like there's not yet a solution to that.
40:14 Scott And, you know, anthropic would say, oh, that's only six months out and we're going to we're going to you know, we're going to solve those problems.
40:21 Scott I don't know. Six months.
40:23 Scott I mean, it was certainly was a year ago that we were going to lose all software engineering jobs in six months. Well,
40:28 Scott you know, past due on that one.
40:30 Scott Yeah, well,
40:32 Scott that actually leads to another thought,
40:34 Scott which is I just sort of see all the software factory stuff moving into something like cloud code or whatever.
40:42 Scott But what is you know, there's codecs over it up in the eye and I don't know who has them But don't you just think all this is just going to move into the platforms?
40:50 Scott Sure.
40:51 Scott But again,
40:51 Scott my thesis,
40:53 Scott that's great.
40:53 Scott Yeah,
40:54 Scott sure.
40:54 Scott I think if you're trying to make a business out of building a framework,
40:58 Scott I think that's probably not going to be that useful to you.
41:01 Scott But I think that the frameworks are getting better and better.
41:08 Scott Mm
41:08 Scott And
41:08 Scott -hmm.
41:08 Scott using the frameworks well is just a huge opportunity.
41:14 Scott yeah but your point that you were just making about being able to verify that the agent or the model does the right thing is real it's real here it's real with everybody who's using models you know like i i tell everybody that i get a chance to tell them like hey i looked this up on ai but you can't believe anything you get from ai so like take it with a grain of salt you
41:36 Scott Yeah.
41:36 Scott know when you want when you want another because you know you do stuff like
41:39 Scott Okay, I'm just going to go right now,
41:41 Scott ask Gemini, where is it? Where's my Gemini window?
41:43 Scott I got Gemini open right now.
41:45 Scott What day is it?
41:47 Scott Is he going to get it right?
41:49 Scott I don't know. Let's find out.
41:51 Scott It actually got it right.
41:52 Scott It is indeed the day that it said,
41:54 Scott which I will not say because I don't know when we're going to release this podcast.
41:57 Scott In case people wanted to know,
41:59 Scott Gemini also told me it's also International Jazz Day,
42:02 Scott National Bubble Tea Day,
42:04 Scott National Adopt a Shelter Pet Day and National Honesty Day,
42:09 Scott which is really interesting because that means all the rest of the days we can be dishonest.
42:14 Scott Yeah,
42:14 Scott I just asked ChatGPT.
42:16 Scott what day is it it just came back with today is the date it
42:20 Scott Yeah,
42:21 Scott didn't give
42:21 Scott I
42:21 Scott me
42:21 Scott guess they got that figured out.
42:22 Scott it didn't give me it didn't give me a fancy details about what what happens on this day today
42:29 Scott Well,
42:30 Scott you know what today is for?
42:32 Scott is tell me what is today it's
42:34 Scott It's a great day.
42:35 Scott a great day to smash that subscribe button
42:39 Scott Great review.
42:39 Scott Rate and review.
42:41 Scott Awesome,
42:42 Scott Scott.
42:42 Scott It's great talking to you again.
42:43 Scott It really was. Good talking to you,
42:44 Scott Brent.
42:44 Scott All right. Have a good one. Bye.
42:47 Scott This episode of the How Many CTOs Does It Take podcast was produced and edited by Saffron Teftekau.
42:52 Scott Our theme song was AI Generated by Brad.
42:56 Scott Please follow us on all the social media platforms at HowManyCTOsPod.
43:01 Scott You can find us on YouTube,
43:03 Scott LinkedIn,
43:04 Scott Instagram,
43:04 Scott Facebook,
43:05 Scott Threads, X,
43:06 Scott TikTok,
43:06 Scott and Patreon.
43:07 Scott Or at our website at HowManyCTOsPod.com. And remember to rate, review,
43:13 Scott and subscribe.
43:13 Scott Subscribe on the podcast platform of your choice.
43:16 Scott Thanks for listening.