--- title: "AI-Native Development Without the Hype: Kevin Riedl on Building Better Software With AI | 转录" canonical: https://wavect.io/zh/appearances/develpreneur-ai-native-development/ language: zh description: "Develpreneur: AI-Native Development Without the Hype: Kevin Riedl on Building Better Software With AI. 阅读转录." image: "https://wavect.io/img/yt/h1KXFFYNiFY.jpg?v=458045ddf2ba" --- Kevin in the Wild / 嘉宾访谈 # AI-Native Development Without the Hype: Kevin Riedl on Building Better Software With AI 主持方 [Rob Broadhead & Michael Meloche](https://develpreneur.com/) 录制语言 英语 30:44 录制发布日期 2026年10月20日 [阅读转录](#transcript) ![原始录制: AI-Native Development Without the Hype: Kevin Riedl on Building Better Software With AI](/img/yt/h1KXFFYNiFY.jpg?v=458045ddf2ba) 原始节目 [Develpreneur](https://www.youtube.com/channel/UCZOuFN_LhczvGyT2KSItH_g) [原始录制](https://www.youtube.com/watch?v=h1KXFFYNiFY) 转录 自动字幕经排版便于阅读。人名、词语和时间戳可能有误，尚未标注说话人身份。正文保留录制时的原始语言，以原始录音为准。 ## 章节 01 [观看此片段 · 0:00](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=0s) [0:27](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=27s) Okay. All right. Well, well, I am waiting on Michael. Um give you the sort of a a rundown of how we do this. [0:38](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=38s) Mhm. [0:38](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=38s) Uh we keep this very uh this is this is video plus audio. Uh we keep it uh very organic. Uh really I mean we'll have a few questions, but really it's uh it's just we're going to see where the conversation leads us. Uh the the audience is uh junior to senior developer technologists, uh particularly the entrepreneurial bent, so they usually have a a side hustle or business they're working on, something along those lines. [1:05](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=65s) So, there's definitely that um that business side of their their knowledge and their experience as well. Uh our focus this season is careers beyond the code. So, you know, instead of just being a coder, so what are the other skills and some of the other things you can do to leverage your your way into a a better and an improved career. Uh let's see. I'll I'll start off uh we do that we have sort of like pre-show information or pre-show stuff [1:33](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=93s) that is video uh that will be, you know, basically right now as well, so we'll pick that up. You'll know it'll be very obvious when I jump into the I guess the pure audio portion portion. We'll wrap that up, and then afterwards we'll have about a 5-to-10-minute um period of time that will basically ask you to provide an additional nugget of wisdom or maybe a challenge to put out to the audience, something along those lines. Uh just it [1:55](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=115s) may be a follow-up, something that we didn't actually cover during the the conversation. Uh it'll run about an hour. Uh I will start with a uh when I start I'll introduce myself, uh Michael introduce himself assuming he's joining us here in a minute, and I'll put it to you to introduce yourself. Um and let me [2:13](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=133s) Sounds great. [2:14](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=134s) one more time to ping Michael. Let's see if he's doing good or if he's got connections or what's going on there. Let's see. [2:34](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=154s) And is there anything uh like what kind of things would you prefer to focus on? Like what's the benefit that you want to have from people listening to this episode? [2:47](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=167s) Um [2:48](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=168s) Like the ideal outcome. Let's put it that way. [2:52](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=172s) Well, I think um really the best thing is for them to have something that is a uh ideally something actionable that they can they can do, take into their day or into their week to improve their career. Um you know, whether it's a soft skill, whether it's a technical skill, whether it's something that they can go research. Um we try to leave that, you know, sort of open and and fit it to how our conversation goes. [3:16](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=196s) Sure thing. Sounds good. [3:18](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=198s) Okay, so apologies for this. Give me about Give me about one more minute and see if he's going to join us. And if not, then we will figure it out. [3:34](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=214s) Mhm. [3:36](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=216s) It does happen to be a little early for him. Uh he's sitting at about 6:30 a.m. where he's at. Are you in uh you're in Australia? Austria? [3:45](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=225s) I'm in Austria, yeah. And you? [3:47](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=227s) Okay. Uh I'm currently I'm sitting in Scotland, so probably about an hour behind. It's uh what 1:30 1 just after 1:30 your time? [3:56](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=236s) Nice. [3:56](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=236s) Yeah. [3:57](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=237s) Correct. [3:58](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=238s) So. Haven't made it up there over to Austria yet, but we're doing about doing the digital nomad thing all over Europe and definitely Austria is one of where we want to get to. Well, we've we've been in the I've been in the I've been in the the airport in Vienna and then my wife's been there and actually ended up spending a night right next to the airport in Vienna, so I guess we've been there, but not been able to really like [4:22](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=262s) enjoy it. [4:23](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=263s) I see. I see. And I just out of curiosity like since you say digital nomad, like what has been the coolest place you have been so far? [4:33](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=273s) Oh, um It's really to me actually the the coolest place was probably um um probably Sarajevo. Uh just because it was uh we spent some time in the Balkans and I coming from the States had a very different view of a very slanted view of what the Balkans were and and the history, especially the you ## 章节 02 [观看此片段 · 5:00](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=300s) [5:00](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=300s) know, recent last 20 to 50 years of history there. Um and some of the people and and things like that and to and the culture, so it was it was fascinating to me. It was one of those it's just a great place. It's got literally thousands of years of history, but also very modern. The city itself reflects that. It's got you know, very modern areas and sections and buildings and it's got very ancient you know, buildings and and sections. [5:25](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=325s) So, it was it was really interesting to me. It was really fascinating. It was um We were there at the right time of year, so like climate-wise is really good. It wasn't too hot. It wasn't too cold. Um but that was yeah. It's one of those it was yeah. I definitely geeked out a little bit there. There's a lot of a lot of of history. There's a lot of learning that went on. There we go. [5:48](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=348s) Yeah, cool stuff. Love to hear that. [5:50](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=350s) So excellent. So I bought enough time for Michael to join us. [5:55](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=355s) Hi Michael. Great to meet you. [5:59](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=359s) Hey guys, sorry about that. [6:01](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=361s) All right, so we'll do a quick audio check for Michael and then we will dive into it. [6:08](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=368s) All right. Rob, you sound good and Kevin, please say something. [6:16](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=376s) Test, test, test. Great to meet you as well, Michael. Hi. [6:20](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=380s) Okay, so here we go. Three, two. Well, hello and welcome back. We are continuing season 29 where our season is also now our site focus of building a career beyond the code. Our what we are actually is DevelopMentor, building better developers. I am Rob Rutter, one of the founders of DevelopMentor, also the founder of RB Consulting where we help you avoid expensive technology mistakes before they happen. We help you get [6:48](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=408s) clarity so that when you dive into that big project, you actually have a good focus on where you start, where you want to go, and how are you going to get there? Like follow a road map, things like that. From a DevelopMentor point of view, we have still we're we're pushing the developer leverage interview and tool. This is a great way for you to figure out how to take the the reality of what you've done and put that into [7:12](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=432s) your resume, LinkedIn, blog articles, job proposals, all that kind of good stuff so that you can get credit for the work you did as opposed to just being sort of you know, assumed to be a more AI slop or something like that in this now very competitive market where AI loves to fill stuff up, but now we can make sure that you're filling it up with actual things you did that you can actually point to and say, yes, this is [7:35](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=455s) the problem I solved and the value I brought to it. Good thing and bad thing. A good thing is a uh yeah, I'm going to say it's a good thing is I'm actually about to shift again where I am at. And while it has been a very good time, we've had some fun times here. I'm also ready to move on to something different. Uh the place we've been, the actual living arrangements have been not the greatest. And so I'm ready to move on to to try something [8:01](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=481s) else. Um bad thing is that uh it's again, it's one of these places where every time we move, there's some things that are let's say left on the table essentially. We have some things that are not exactly uh you know, we would have loved to have gotten to them essentially. But instead of leaving something on the table, I am going to go ahead and push this on to Michael. [8:24](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=504s) Hey everyone, my name is Michael Moush. I'm one of the co-founders of DevelopNeer, building better developers. I'm also the founder of Envision QA, where we help businesses assess what's working, uncover what's holding them back, and test the technology to find problems before their customers do. Uh good thing, bad thing. Um bad thing, uh when you try to let your dogs out before a call and you expect to be on a call on time, doesn't always [8:51](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=531s) happen when your dog chases a deer. You have to go hunt the dog down to get back in. Good thing is I did make it to the call. [8:59](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=539s) Ah yes, fun times. And as you guys may have noticed, we have a guest again today. And Kevin, if you can go ahead and introduce yourself. [9:08](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=548s) Of course. Hi everyone, I'm Kevin. I'm the owner and founder of Wave Act. And we are K native as a AI native software agency. Uh mostly operating internationally with a 99% export quota. Yeah. [9:25](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=565s) So [9:26](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=566s) That's what I was [9:26](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=566s) That's great. I love that as a a start because I think this is a Uh I don't want to say it's just a buzz, but it's definitely something that people are pushing towards, which is being an AI native company. And people have talked about that from a, you know, a large-scale about large companies trying to figure out how to get to that versus a lot of startups right now have decided that we're just going to dive right in and be AI-native. What does [9:51](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=591s) that mean to you? [9:54](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=594s) I mean, the first step is to to not fall into the same trap, as you mentioned, um to not uh ## 章节 03 [观看此片段 · 10:00](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=600s) [10:01](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=601s) try to slap AI into something that doesn't make sense at all. AI is just another tool. It's an incredibly awesome tool, uh probably the best tool that we had for a very long time. Uh but keeping it as a tool on top of your hat, I think is the key here. Cuz a lot of people, when they think about AI-native, it's mostly about, "Okay, let's change everything and and uh let's uh throw all our software principles uh out of the window and all [10:33](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=633s) of that." And obviously, uh we have to adapt processes, we have to to learn something new, we have to change to the uh new industry best practices that we're currently developing. But uh we shouldn't just throw everything out that we have learned over the last decades. And and I think that's the art when you say uh what's real AI-native, it's combining those two worlds uh and taking the best out of both worlds. [11:07](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=667s) And that's uh cuz you it's interesting cuz you mentioned which is very true, I feel, is that AI is just it's just a tool. So, what you mentioned, but you get the end, you mentioned it sort of combining those two worlds of AI versus, I guess, pre-AI or not AI. What is it that makes that What is it that you see makes that tool of AI something that now actually is its own uh essentially its own world, as you as you referred to it. [11:35](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=695s) I mean, the crazy part is and I think everyone has noticed that especially this year, AI is is getting to a point where you in theory or even practically can let it do almost everything, right? You can let it deploy applications for you, you can give it browser access, you can allow it to to deploy whole Kubernetes clusters, whatever you want to, right? Be it DevOps, be it writing applications, be it engaging with customers, collecting [12:03](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=723s) requirements, doing QA testing, also manual testing. Uh all of that. But just because you can doesn't mean you should, right? And I think especially more experienced engineers or professionals in any any area will confirm that even though AI is really uh crazy good in a lot of things, uh you still especially if you do have deep know-how in a certain area, you still discover that it oftentimes goes in circles, that it does [12:39](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=759s) does things that it's not supposed to do or not in the most efficient or best way or it misses some context that you have and so on. And uh yeah, one of the parts obviously is to to put QA uh or that human expertise at the root of everything. And if you do that, you have good chances that you don't throw out AI slop as you mentioned at the beginning of this episode. That's I would say is the key here. [13:09](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=789s) Yeah, it's interesting. Um I we've discussed this uh in length over the last year so as we've talked about AI. But as AI native becomes more the status quo, how are you approaching this with companies that are bringing AI in but not training their employees and expecting AI to just work within their systems? [13:38](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=818s) Is your question about change management? Do I get that right? [13:41](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=821s) Uh more along the lines of adoption. Like they Oh, we want AI, so we bring it in and we just expect everyone to start using it and it work. [13:53](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=833s) I mean, we do a lot of AI workshops. We uh we also did a lot of AI checks, uh which is was or is was uh a great lead magnet for us, especially for enterprise clients, and so on. And what we have discovered uh it's rarely uh the like the challenge rather is to get AI adopted. The challenge rather is to put the guardrails, the processes, the the do's and don'ts in place to make sure, hey, organizations actually use AI in in somewhat in a [14:27](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=867s) compliant manner, if that's possible. And uh to to make sure that AI usage doesn't go rogue because everyone does have their own smartphone. Just had a AI workshop last week. Big enterprise. Everyone would know it if if I would mention name. And they said, okay, um we do have uh a very competent IT department. We did have uh put a lot of thought in a lot of these things. We are using co-pilot and so on and so forth. But despite all of that, people still ## 章节 04 [观看此片段 · 15:00](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=900s) [15:00](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=900s) have the smartphone uh next to their uh PC and if they want something resolved, they just take a picture of it, send it to ChatGPT, and gone, right? So, that's uh I I think it's less about adopting AI. It's more about making sure, okay, people are aware of it. Similar thing to what we uh did over the last decade with IT security, I would say. Making sure people know what fishing is, that you can't trust uh just every email that receives [15:33](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=933s) is received in your inbox and all that kind of stuff. And I'm pretty sure the same will happen with AI. I think that's the main challenge. At at least in my opinion. What do you guys think? I'm not the only IT professional out here. [15:49](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=949s) I've seen it kind of work both ways. I've seen it where some companies actually have a good guardrail in place. They have good rules and regulations. Here, bring it in, but we're going to have a sandbox. We're going to start in the sandbox, then we're going to slowly introduce it. And in other cases, I've seen it where here, we went out and we bought um Copilot or GitHub Copilot, and here's a bunch of tokens, everyone start using it and [16:18](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=978s) um get the project done with an unrealistic deadline. Um and by unrealistic, I mean something that should have taken 2 years, well, we got it done in 6 months and only because we had AI. Um there was just no way this was going to happen otherwise. And I'm curious I've seen a lot of companies take shortcuts with this, but as you were talking there, the dos and don'ts and getting the compliance and the guardrails in place, what are some [16:46](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1006s) of the dos and don'ts uh that you would recommend for our listeners to be cautious of with AI it when they start bringing it into their processes, into their business? [17:00](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1020s) I mean, the honest answer, obviously, is uh what's your company? Like, what industry are you in? How big are you? Uh for how much time have you existed and so on and so forth, right? There are a lot of uh things to consider here, which honestly make most like make the a biggest difference in what you should do and what you shouldn't do. If you're a small startup um or a small agency, it's it's all different. Or if you're a large corporate or a [17:31](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1051s) traditional company existing over 200 years, it completely varies, right? And what I usually do in these uh AI workshops, uh you you can't go really deep, obviously. But, similar with security, the simplest things usually protect you from 80% of the mistakes. So, if you focus on the 80%, hey, please don't paste your secret uh company information uh without redaction pipeline or whatever uh into a non-enterprise license uh AI tool [18:08](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1088s) or something like that, that's a great start, I would say. And employees actually adhering to that is the big next step. And making sure uh new employees understand that quickly as well, not just uh in in the first AI uh workshop they have in 1 or 2 years, stuff like that. And I think that's If you do that, you're probably ahead in the next years, I would dare to say. What do you guys think? [18:38](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1118s) Yeah, I think this hits you know, you you mentioned uh security awareness in general, and I think that is definitely one of those things that it's um what is it? An ounce of prevention is worth a pound of cure or something along those lines. And I I love your 80/20 kind of approach is that really, if you just do the the the best practice things, then it gets you pretty far along the way. The The most uh the easier things [19:03](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1143s) like, you know, accidentally pasting or or pasting a secret or code or API key or something like that into a public LLM, and then suddenly it's out there in the wild. You know, those are kind of things if you just don't do that then that knocks out a lot of the people are going to attack you. The easy attacks then sort of go away. Um I do think that this is I don't want to get too far into it, but I do think that one of the things that's an [19:27](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1167s) interesting change is the security by obscurity that we've used for many decades now where we just you don't publish it, you don't make it public, but you also don't necessarily make it inaccessible. I think is becoming less is becoming more of an issue and less of a you know, valid way to look at stuff because AI does allow people to do, you know, port scans and and simple password scans and stuff like that. So, the the things that are we used to just [19:55](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1195s) say, well, since it's not really visible, it's probably okay. Uh AI is allowing, you know, hackers and and ## 章节 05 [观看此片段 · 20:00](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1200s) [20:01](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1201s) those of of ill intent a faster way to actually see what is available out there. So, if you don't hide it and specifically protect it, it it may be an issue. Now, I do want to before we go too far into other things, I want to swing back to you know, initially we were talking about being an AI native company and then some of the things that you do to um to ensure that you can use AI in a proper way. And one of the things that [20:25](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1225s) I'm seeing uh that I'd like to get your take on is as we're using AI more, we being you know, individual company or even us, you know, globally, the context is growing bigger. We're starting to have AI use things that do things that are bigger that are that require more context. There's a difference between rewrite this function versus analyze this entire repository of code. How are you seeing and how are you, you know, maybe how you guys are doing it [20:52](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1252s) and how you are helping other companies handle that context issue is how do I bring the right amount of context so it doesn't hallucinate essentially versus how do I, you know, gather that and not have it just, you know, swamp the uh right, to go too far one way or too far the other. [21:11](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1271s) I mean, that's a great question and I think every engineer out there has the same question right now and there are many parts of this. One part, and that's a great part for every one of us, is uh it's in the big interest of big tech to make sure the harnesses and so on are crazy good. So, uh cloud code, codex, and whatever you use, they are already do a lot of optimization for you. Obviously, they're not fully aligned with you. [21:44](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1304s) So, there are a lot of frameworks, tools out there. I'm pretty sure many of you have experimented with with some of these things from RTK AI, which compresses uh CLI output because it's usually quite verbose when you enter some kind of command into your terminal. Or graphify, graft, which basically try to create some kind of knowledge or semantic graph around your code base. Uh these are great, save a lot of tokens. We use those. [22:18](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1338s) Um or I mean, there there are a lot of uh experiments out there for AI native programming languages, which is not very practical yet, of course, but I believe that might be theoretically something we might head towards in the next 10 years. I don't know, 5 years. Um aside from that, yeah. There there are many harnesses, tools out there and I just ask you to experiment because anything I mention here is probably obsolete next week. Um we have a very [22:54](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1374s) extensive blog where we basically discover 20 awesome, crazy, cool new tools every week and I'm pretty sure you too. And yeah, it's basically just tells me, "Okay, the market is in explo- exploration mode." And the best thing in a practical terms you can do as an engineer is a straight Look look at X, look at LinkedIn a little bit, look at Instagram. Uh people post about this. This is where we get our information from. [23:31](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1411s) And yeah, try it out sometimes or at least start to not lose it or And yeah, we we save around, let's say, to give you some kind of number at least from what the tools are saying, we're saving 95% of our token usage by combining all these things, right? But it's very easy to save 50 to 80% if you do the basics, right? So, that's I think a great start. What about you? [24:00](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1440s) Hey, you meant Yeah, I I I agree. Um I don't know I haven't I don't have hard measures of of metrics around what has been saved, but there is definitely uh a marked difference from just jumping into code and having AI do stuff versus taking essentially I It's funny to me it's the right steps. These are things we should do with software development in general, is making sure that we have like properly documented stuff, designs, and things [24:28](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1468s) like that. And when we have whether we do it or we have AI or some tool build those kinds of uh structured documents that say, "This is what you're working with, you know, this is this is your API and these are the endpoints and these are all the signatures." And those kinds of things that that we as dev- as developers like to have ourselves. So, we can just look at it and say, "Oh, this is a snapshot of what we're dealing [24:51](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1491s) with." When you give that to AI, it benefits from that uh dramatically as well. Uh both um token usage, but also how quickly it can respond and even I ## 章节 06 [观看此片段 · 25:00](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1500s) [25:02](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1502s) found it is very useful in the the depth of insight it can provide when I've got some of those things that it can actually it's not spending so much time this sort of goes through that context that context is not so big that it sort of falls out of context and now can't really give you good information instead it's got something that is very small or it's easy for it to we'll say hold in its head and then do some work [25:25](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1525s) and then actually give you more useful results coming out of that that chat or that that conversation. And that sort of leads me to a question that you mentioned AI native languages basically or pure you know AI languages which I do see as we're we're not quite there yet but there is also sort of our our stepping stone there is that there are people that have purely developed use AI purely to develop solutions. So you have an application that is [25:55](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1555s) entirely has been done through you know it's it's I guess vibe coding but it's actually it's a little more than that. This is somebody that's actually taken it a step beyond that but they're still using AI systems development throughout it. So AI has essentially written every line of code you know maybe there's a few comments or some configuration but essentially it it knows the code. Now have you done any of those and have you [26:19](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1579s) seen that that has been successful and something that is more likely to do it the right way and save your tokens or do you still have to tell AI sort of guide it how to do it properly? [26:34](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1594s) I mean there's there's no right or wrong I would say. Depends on what you're building how novel it is how complex it is how critical it is. But usually they will have prompt base and that's what the benchmarks kind of say as well the more advanced the model is the less guidance it needs or should have because it kind of makes it fixate on that uh instead of giving it that freedom to apply best practices that you maybe aren't even [27:03](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1623s) aware of, to be honest. So, um and we we we regarding white coding, I I think that that's maybe that the missing link here. Uh difference between white coding and AI assistant coding is at today's day and age, I would dare to say is simply is the person operating it someone who has an idea about billing software. I think that's the main difference because even though I don't believe anyone wants to say it. I don't want to say it either. [27:35](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1655s) But, I don't know any engineer or not many at least that have written much code or any code by hand in the last year or last 6 months. And I think that's the harsh truth. So, basically from the old terms, everyone is white coding. Uh the difference is are you do you have guardrails in place? Do you have uh quality gates? Do you have uh do you review your stuff or at least uh have some kind of mechanism to make sure it works or achieves acceptance [28:07](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1687s) criteria? And uh do you know what you're doing? Cuz uh just last week, uh we had a small client uh white coded. Not an engineer or junior engineer at the very least. And uh yeah, she developed some something like a e-commerce application. And yeah, it was like com- despite the great models that we have, it was unusable. Right? Um we uh like the engagement that we had with her was like, "Okay, let's create GitHub issues." So, that her agents can fix it. [28:45](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1725s) And I think we had like 70 issues and then we had another iteration of 30 issues and another and it got better a lot but it clearly shows okay. It still matters who is operating that even if tomorrow's are great even if you have proper instructions because that's exactly how we operate to a large part. We just do have different quality gates. We just make sure we we know what to check for. We I think that's the difference. [29:18](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1758s) And that was a great example cuz the models now are good enough. Simple as that. [29:26](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1766s) And that is where we're going to pause. You probably already figured out that Kevin is one of these people that knows AI because he does it and he's working with organizations that do it. So this is while this has also been a been a great episode the next one continues this. This is going to be more conversation with Kevin. We're going to dig in a little bit more about some of the we're going to get a little more geeky. We're going [29:49](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1789s) to get a little deeper into local LLMs and mixing and routing and some of those kinds of things that are I guess they're advanced topics right now but I have a feeling these are going to become much much more the common kind ## 章节 07 [观看此片段 · 30:00](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1800s) [30:02](https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1802s) of discussions we're going to have in the the months ahead as more people use more AI and the cost start adjusting. However, for now we're going to wrap this one up because we're not AI. We got to go. We got to go rest. We got to eat. We got to do all those human things. We can't just be an agent running through this. So go out there and have yourself a great day, a great week. We will talk to you next time. ## Structured Data ```json { "@context": "https://schema.org", "@graph": [ { "@id": "https://wavect.io/#organization", "@type": [ "Organization", "ProfessionalService", "LocalBusiness" ], "employee": [ { "@id": "https://wavect.io/team/kevin-riedl/#person", "@type": "Person", "jobTitle": "Managing Director", "name": "Kevin Riedl", "url": "https://wavect.io/team/kevin-riedl/", "worksFor": { "@id": "https://wavect.io/#organization", "@type": [ "Organization", "ProfessionalService", "LocalBusiness" ] } }, { "@id": "https://wavect.io/team/christof-jori/#person", "@type": "Person", "jobTitle": "Managing Director", "name": "Christof Jori", "url": "https://wavect.io/team/christof-jori/", "worksFor": { "@id": "https://wavect.io/#organization", "@type": [ "Organization", "ProfessionalService", "LocalBusiness" ] } } ], "founder": [ { "@id": "https://wavect.io/team/kevin-riedl/#person", "@type": "Person", "jobTitle": "Managing Director", "name": "Kevin Riedl", "url": "https://wavect.io/team/kevin-riedl/", "worksFor": { "@id": "https://wavect.io/#organization", "@type": [ "Organization", "ProfessionalService", "LocalBusiness" ] } }, { "@id": "https://wavect.io/team/christof-jori/#person", "@type": "Person", "jobTitle": "Managing Director", "name": "Christof Jori", "url": "https://wavect.io/team/christof-jori/", "worksFor": { "@id": "https://wavect.io/#organization", "@type": [ "Organization", "ProfessionalService", "LocalBusiness" ] } } ], "legalRepresentative": [ { "@id": "https://wavect.io/team/kevin-riedl/#person", "@type": "Person", "jobTitle": "Managing Director", "name": "Kevin Riedl", "url": "https://wavect.io/team/kevin-riedl/", "worksFor": { "@id": "https://wavect.io/#organization", "@type": [ "Organization", "ProfessionalService", "LocalBusiness" ] } }, { "@id": "https://wavect.io/team/christof-jori/#person", "@type": "Person", "jobTitle": "Managing Director", "name": "Christof Jori", "url": "https://wavect.io/team/christof-jori/", "worksFor": { "@id": "https://wavect.io/#organization", "@type": [ "Organization", "ProfessionalService", "LocalBusiness" ] } } ], "name": "Wavect GmbH", "subjectOf": { "@id": "https://wavect.io/verified-claims.json#dataset", "@type": "Dataset", "creator": { "@id": "https://wavect.io/#organization", "@type": [ "Organization", "ProfessionalService", "LocalBusiness" ] }, "description": "A machine-readable registry of quantitative and qualitative claims published by Wavect, with review dates, localized page appearances and public third-party citations where available.", "inLanguage": "en", "isAccessibleForFree": true, "license": "https://creativecommons.org/licenses/by/4.0/", "name": "Wavect verified publication claims", "url": "https://wavect.io/verified-claims.json" }, "url": "https://wavect.io/" }, { "@id": "https://wavect.io/team/kevin-riedl/#person", "@type": "Person", "jobTitle": "Managing Director", "name": "Kevin Riedl", "sameAs": [ "https://www.wikidata.org/wiki/Q139796365", "https://www.linkedin.com/in/wsdt", "https://github.com/wsdt" ], "url": "https://wavect.io/team/kevin-riedl/", "worksFor": { "@id": "https://wavect.io/#organization", "@type": [ "Organization", "ProfessionalService", "LocalBusiness" ] } }, { "@id": "https://wavect.io/team/christof-jori/#person", "@type": "Person", "jobTitle": "Managing Director", "name": "Christof Jori", "sameAs": [ "https://www.wikidata.org/wiki/Q139796367", "https://www.linkedin.com/in/jocr77/", "https://github.com/jo-chris" ], "url": "https://wavect.io/team/christof-jori/", "worksFor": { "@id": "https://wavect.io/#organization", "@type": [ "Organization", "ProfessionalService", "LocalBusiness" ] } }, { "@id": "https://wavect.io/#website", "@type": "WebSite", "inLanguage": [ "en", "de", "es", "zh" ], "name": "Wavect", "potentialAction": { "@type": "SearchAction", "query-input": "required name=search_term_string", "target": { "@type": "EntryPoint", "urlTemplate": "https://wavect.io/search/?q={search_term_string}" } }, "publisher": { "@id": "https://wavect.io/#organization", "@type": [ "Organization", "ProfessionalService", "LocalBusiness" ] }, "url": "https://wavect.io/" }, { "@id": "https://wavect.io/zh/appearances/develpreneur-ai-native-development/#webpage", "@type": "WebPage", "dateModified": "2026-11-05", "inLanguage": "zh", "isPartOf": { "@id": "https://wavect.io/#website", "@type": "WebSite" }, "lastReviewed": "2026-11-05", "url": "https://wavect.io/zh/appearances/develpreneur-ai-native-development/" } ] } ``` ```json { "@context": "https://schema.org", "@graph": [ { "@id": "https://wavect.io/zh/appearances/develpreneur-ai-native-development/#webpage", "@type": "WebPage", "dateModified": "2026-11-05", "datePublished": "2026-11-05", "inLanguage": "zh", "isPartOf": { "@id": "https://wavect.io/#website", "@type": "WebSite" }, "mainEntity": { "@id": "https://wavect.io/zh/appearances/develpreneur-ai-native-development/#video" }, "name": "AI-Native Development Without the Hype: Kevin Riedl on Building Better Software With AI", "url": "https://wavect.io/zh/appearances/develpreneur-ai-native-development/" }, { "@id": "https://wavect.io/zh/appearances/develpreneur-ai-native-development/#video", "@type": "VideoObject", "contributor": { "@id": "https://wavect.io/team/kevin-riedl/#person", "@type": "Person", "name": "Kevin Riedl", "url": "https://wavect.io/team/kevin-riedl/", "worksFor": { "@id": "https://wavect.io/#organization", "@type": [ "Organization", "ProfessionalService", "LocalBusiness" ] } }, "description": "Develpreneur: AI-Native Development Without the Hype: Kevin Riedl on Building Better Software With AI", "duration": "PT30M44S", "embedUrl": "https://www.youtube-nocookie.com/embed/h1KXFFYNiFY", "hasPart": [ { "@type": "Clip", "endOffset": 300, "name": "章节 01", "startOffset": 0, "url": "https://www.youtube.com/watch?v=h1KXFFYNiFY&t=0" }, { "@type": "Clip", "endOffset": 600, "name": "章节 02", "startOffset": 300, "url": "https://www.youtube.com/watch?v=h1KXFFYNiFY&t=300" }, { "@type": "Clip", "endOffset": 900, "name": "章节 03", "startOffset": 600, "url": "https://www.youtube.com/watch?v=h1KXFFYNiFY&t=600" }, { "@type": "Clip", "endOffset": 1200, "name": "章节 04", "startOffset": 900, "url": "https://www.youtube.com/watch?v=h1KXFFYNiFY&t=900" }, { "@type": "Clip", "endOffset": 1500, "name": "章节 05", "startOffset": 1200, "url": "https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1200" }, { "@type": "Clip", "endOffset": 1800, "name": "章节 06", "startOffset": 1500, "url": "https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1500" }, { "@type": "Clip", "endOffset": 1844, "name": "章节 07", "startOffset": 1800, "url": "https://www.youtube.com/watch?v=h1KXFFYNiFY&t=1800" } ], "inLanguage": "en", "name": "AI-Native Development Without the Hype: Kevin Riedl on Building Better Software With AI", "publisher": { "@type": "Organization", "name": "Develpreneur", "url": "https://www.youtube.com/channel/UCZOuFN_LhczvGyT2KSItH_g" }, "thumbnailUrl": "https://i.ytimg.com/vi/h1KXFFYNiFY/maxresdefault.jpg", "transcript": "Okay. All right. Well, well, I am waiting on Michael. Um give you the sort of a a rundown of how we do this.\nMhm.\nUh we keep this very uh this is this is video plus audio. Uh we keep it uh very organic. Uh really I mean we'll have a few questions, but really it's uh it's just we're going to see where the conversation leads us. Uh the the audience is uh junior to senior developer technologists, uh particularly the entrepreneurial bent, so they usually have a a side hustle or business they're working on, something along those lines.\nSo, there's definitely that um that business side of their their knowledge and their experience as well. Uh our focus this season is careers beyond the code. So, you know, instead of just being a coder, so what are the other skills and some of the other things you can do to leverage your your way into a a better and an improved career. Uh let's see. I'll I'll start off uh we do that we have sort of like pre-show information or pre-show stuff\nthat is video uh that will be, you know, basically right now as well, so we'll pick that up. You'll know it'll be very obvious when I jump into the I guess the pure audio portion portion. We'll wrap that up, and then afterwards we'll have about a 5-to-10-minute um period of time that will basically ask you to provide an additional nugget of wisdom or maybe a challenge to put out to the audience, something along those lines. Uh just it\nmay be a follow-up, something that we didn't actually cover during the the conversation. Uh it'll run about an hour. Uh I will start with a uh when I start I'll introduce myself, uh Michael introduce himself assuming he's joining us here in a minute, and I'll put it to you to introduce yourself. Um and let me\nSounds great.\none more time to ping Michael. Let's see if he's doing good or if he's got connections or what's going on there. Let's see.\nAnd is there anything uh like what kind of things would you prefer to focus on? Like what's the benefit that you want to have from people listening to this episode?\nUm\nLike the ideal outcome. Let's put it that way.\nWell, I think um really the best thing is for them to have something that is a uh ideally something actionable that they can they can do, take into their day or into their week to improve their career. Um you know, whether it's a soft skill, whether it's a technical skill, whether it's something that they can go research. Um we try to leave that, you know, sort of open and and fit it to how our conversation goes.\nSure thing. Sounds good.\nOkay, so apologies for this. Give me about Give me about one more minute and see if he's going to join us. And if not, then we will figure it out.\nMhm.\nIt does happen to be a little early for him. Uh he's sitting at about 6:30 a.m. where he's at. Are you in uh you're in Australia? Austria?\nI'm in Austria, yeah. And you?\nOkay. Uh I'm currently I'm sitting in Scotland, so probably about an hour behind. It's uh what 1:30 1 just after 1:30 your time?\nNice.\nYeah.\nCorrect.\nSo. Haven't made it up there over to Austria yet, but we're doing about doing the digital nomad thing all over Europe and definitely Austria is one of where we want to get to. Well, we've we've been in the I've been in the I've been in the the airport in Vienna and then my wife's been there and actually ended up spending a night right next to the airport in Vienna, so I guess we've been there, but not been able to really like\nenjoy it.\nI see. I see. And I just out of curiosity like since you say digital nomad, like what has been the coolest place you have been so far?\nOh, um It's really to me actually the the coolest place was probably um um probably Sarajevo. Uh just because it was uh we spent some time in the Balkans and I coming from the States had a very different view of a very slanted view of what the Balkans were and and the history, especially the you\nknow, recent last 20 to 50 years of history there. Um and some of the people and and things like that and to and the culture, so it was it was fascinating to me. It was one of those it's just a great place. It's got literally thousands of years of history, but also very modern. The city itself reflects that. It's got you know, very modern areas and sections and buildings and it's got very ancient you know, buildings and and sections.\nSo, it was it was really interesting to me. It was really fascinating. It was um We were there at the right time of year, so like climate-wise is really good. It wasn't too hot. It wasn't too cold. Um but that was yeah. It's one of those it was yeah. I definitely geeked out a little bit there. There's a lot of a lot of of history. There's a lot of learning that went on. There we go.\nYeah, cool stuff. Love to hear that.\nSo excellent. So I bought enough time for Michael to join us.\nHi Michael. Great to meet you.\nHey guys, sorry about that.\nAll right, so we'll do a quick audio check for Michael and then we will dive into it.\nAll right. Rob, you sound good and Kevin, please say something.\nTest, test, test. Great to meet you as well, Michael. Hi.\nOkay, so here we go. Three, two. Well, hello and welcome back. We are continuing season 29 where our season is also now our site focus of building a career beyond the code. Our what we are actually is DevelopMentor, building better developers. I am Rob Rutter, one of the founders of DevelopMentor, also the founder of RB Consulting where we help you avoid expensive technology mistakes before they happen. We help you get\nclarity so that when you dive into that big project, you actually have a good focus on where you start, where you want to go, and how are you going to get there? Like follow a road map, things like that. From a DevelopMentor point of view, we have still we're we're pushing the developer leverage interview and tool. This is a great way for you to figure out how to take the the reality of what you've done and put that into\nyour resume, LinkedIn, blog articles, job proposals, all that kind of good stuff so that you can get credit for the work you did as opposed to just being sort of you know, assumed to be a more AI slop or something like that in this now very competitive market where AI loves to fill stuff up, but now we can make sure that you're filling it up with actual things you did that you can actually point to and say, yes, this is\nthe problem I solved and the value I brought to it. Good thing and bad thing. A good thing is a uh yeah, I'm going to say it's a good thing is I'm actually about to shift again where I am at. And while it has been a very good time, we've had some fun times here. I'm also ready to move on to something different. Uh the place we've been, the actual living arrangements have been not the greatest. And so I'm ready to move on to to try something\nelse. Um bad thing is that uh it's again, it's one of these places where every time we move, there's some things that are let's say left on the table essentially. We have some things that are not exactly uh you know, we would have loved to have gotten to them essentially. But instead of leaving something on the table, I am going to go ahead and push this on to Michael.\nHey everyone, my name is Michael Moush. I'm one of the co-founders of DevelopNeer, building better developers. I'm also the founder of Envision QA, where we help businesses assess what's working, uncover what's holding them back, and test the technology to find problems before their customers do. Uh good thing, bad thing. Um bad thing, uh when you try to let your dogs out before a call and you expect to be on a call on time, doesn't always\nhappen when your dog chases a deer. You have to go hunt the dog down to get back in. Good thing is I did make it to the call.\nAh yes, fun times. And as you guys may have noticed, we have a guest again today. And Kevin, if you can go ahead and introduce yourself.\nOf course. Hi everyone, I'm Kevin. I'm the owner and founder of Wave Act. And we are K native as a AI native software agency. Uh mostly operating internationally with a 99% export quota. Yeah.\nSo\nThat's what I was\nThat's great. I love that as a a start because I think this is a Uh I don't want to say it's just a buzz, but it's definitely something that people are pushing towards, which is being an AI native company. And people have talked about that from a, you know, a large-scale about large companies trying to figure out how to get to that versus a lot of startups right now have decided that we're just going to dive right in and be AI-native. What does\nthat mean to you?\nI mean, the first step is to to not fall into the same trap, as you mentioned, um to not uh\ntry to slap AI into something that doesn't make sense at all. AI is just another tool. It's an incredibly awesome tool, uh probably the best tool that we had for a very long time. Uh but keeping it as a tool on top of your hat, I think is the key here. Cuz a lot of people, when they think about AI-native, it's mostly about, \"Okay, let's change everything and and uh let's uh throw all our software principles uh out of the window and all\nof that.\" And obviously, uh we have to adapt processes, we have to to learn something new, we have to change to the uh new industry best practices that we're currently developing. But uh we shouldn't just throw everything out that we have learned over the last decades. And and I think that's the art when you say uh what's real AI-native, it's combining those two worlds uh and taking the best out of both worlds.\nAnd that's uh cuz you it's interesting cuz you mentioned which is very true, I feel, is that AI is just it's just a tool. So, what you mentioned, but you get the end, you mentioned it sort of combining those two worlds of AI versus, I guess, pre-AI or not AI. What is it that makes that What is it that you see makes that tool of AI something that now actually is its own uh essentially its own world, as you as you referred to it.\nI mean, the crazy part is and I think everyone has noticed that especially this", "uploadDate": "2026-10-20T03:00:36-07:00", "url": "https://www.youtube.com/watch?v=h1KXFFYNiFY" }, { "@type": "BreadcrumbList", "itemListElement": [ { "@type": "ListItem", "item": "https://wavect.io/zh/", "name": "首页", "position": 1 }, { "@type": "ListItem", "item": "https://wavect.io/zh/appearances/", "name": "Kevin in the Wild", "position": 2 }, { "@type": "ListItem", "item": "https://wavect.io/zh/appearances/develpreneur-ai-native-development/", "name": "Develpreneur", "position": 3 } ] }, { "@id": "https://wavect.io/zh/appearances/develpreneur-ai-native-development/#episode", "@type": "PodcastEpisode", "associatedMedia": { "@id": "https://wavect.io/zh/appearances/develpreneur-ai-native-development/#video" }, "datePublished": "2026-10-20", "inLanguage": "en", "name": "AI-Native Development Without the Hype: Kevin Riedl on Building Better Software With AI", "partOfSeries": { "@type": "PodcastSeries", "name": "Develpreneur", "url": "https://www.youtube.com/channel/UCZOuFN_LhczvGyT2KSItH_g" }, "publisher": { "@type": "Organization", "name": "Develpreneur", "url": "https://www.youtube.com/channel/UCZOuFN_LhczvGyT2KSItH_g" }, "url": "https://www.youtube.com/watch?v=h1KXFFYNiFY" } ] } ```