WEBVTT 1 00:00:05.320 --> 00:00:09.439 Hello everybody, and welcome to another exciting episode of JavaScript Jabber. 2 00:00:09.480 --> 00:00:11.519 I am Steve Edwards, a host with the face for 3 00:00:11.640 --> 00:00:14.439 radio and the voice for being your mind. Amine, excuse me, 4 00:00:14.480 --> 00:00:17.559 but I'm the host at least I am. Today with 5 00:00:17.719 --> 00:00:20.039 me on the panel, I have coming with us live 6 00:00:20.079 --> 00:00:22.120 from Tel Aviv, Israel, mister Dan Shapire. 7 00:00:22.120 --> 00:00:24.480 How are you doing, Dan, I'm doing well. 8 00:00:24.559 --> 00:00:27.719 I'm perfectly fine with you being my mind. I could 9 00:00:27.800 --> 00:00:28.760 use the mind. 10 00:00:29.280 --> 00:00:31.440 Yes, mine is a terrible thing to waste, as they 11 00:00:31.559 --> 00:00:35.679 used to say. So, how's weather in Tel Aviv? We 12 00:00:35.719 --> 00:00:38.079 always have to talk about this. It's still warm and hot. 13 00:00:38.320 --> 00:00:43.880 Yeah, well, I don't know about lovely, but it is hot. 14 00:00:44.000 --> 00:00:44.880 It's a it's a. 15 00:00:45.159 --> 00:00:50.039 It's humid because we're on the Mediterranean's humunity too. Okay, yeah, 16 00:00:50.079 --> 00:00:52.200 but on the other hand, we've got the beach, so, 17 00:00:52.359 --> 00:00:55.079 you know, some of the nicer things that we have 18 00:00:55.159 --> 00:00:57.640 among the also lots of not so nice things we 19 00:00:57.759 --> 00:01:00.280 recently have. But that's a topic for a different discuss. 20 00:01:00.479 --> 00:01:04.840 Yes, exactly. And coming as our special guest today is 21 00:01:04.920 --> 00:01:09.480 mister gunner Berger. How you doing Gunner? All right, I'm 22 00:01:09.519 --> 00:01:13.280 doing great. While these voice messages come on my phone, 23 00:01:13.760 --> 00:01:17.840 so we are here to talk today about vibe coding, 24 00:01:18.599 --> 00:01:22.840 that hot topic across the web and across the world 25 00:01:22.879 --> 00:01:26.480 these days, it's at least in the tech space. Before 26 00:01:26.599 --> 00:01:29.120 we get into the topic, Gunner, can you give us 27 00:01:29.120 --> 00:01:30.359 a little backgrounded on yourself? 28 00:01:30.480 --> 00:01:34.920 Sure, full background or vibe coding background or I'm. 29 00:01:34.719 --> 00:01:37.920 Whatever you deem relevant to the topic at hand. 30 00:01:38.519 --> 00:01:42.280 All right, sure, I'm I'm a true nerd, been a 31 00:01:42.280 --> 00:01:45.239 nerd for twenty plus years, been in tech industry for 32 00:01:45.280 --> 00:01:50.959 twenty plus years. First half my career is centered it traditional. 33 00:01:51.000 --> 00:01:53.719 It switched over about fifteen years ago. I was a 34 00:01:53.719 --> 00:01:57.599 Gartner analyst for a while. I covered in computing. It's 35 00:01:57.599 --> 00:01:58.719 worked Dan and I met. 36 00:02:00.159 --> 00:02:03.040 I went over to Citrics, was there for about six years. 37 00:02:03.079 --> 00:02:05.599 Have been currently now at Amazon. Been here about six 38 00:02:05.719 --> 00:02:09.719 years and I've been leading product in some form another. 39 00:02:10.159 --> 00:02:13.319 It constantly changes, but I've been doing some form of 40 00:02:14.000 --> 00:02:18.800 products for a while now. At CIDRICSS, I would say 41 00:02:18.919 --> 00:02:22.080 more new product initiatives and PI. I always kind of 42 00:02:22.159 --> 00:02:25.199 choked at our CEO, Mark Templeton would always have like 43 00:02:25.240 --> 00:02:28.439 and one more thing on stage at Synergy that's typically 44 00:02:28.439 --> 00:02:31.520 where the CTO department would have something to do with 45 00:02:31.560 --> 00:02:33.919 that and one more thing. So I did a lot 46 00:02:33.960 --> 00:02:36.919 of MPI mergency acquisitions, that kind of stuff at Citric 47 00:02:38.599 --> 00:02:43.240 and yeah, and I jumped over to product, which is 48 00:02:43.240 --> 00:02:47.520 where I've been ever since. Yeah, and so I'm I'm 49 00:02:47.560 --> 00:02:51.360 really interested in this topic because I think the definition 50 00:02:51.439 --> 00:02:54.439 of product manager or at Amazon we hire product PMT 51 00:02:54.599 --> 00:03:00.120 product manager technicals, and I lead a team of these professionals, 52 00:03:00.639 --> 00:03:05.280 and I think that that definition is changing rapidly because 53 00:03:05.400 --> 00:03:09.599 of what AI is empowering product managers to do. So Yeah, 54 00:03:09.599 --> 00:03:11.879 I thought it's really fun to have a conversation with 55 00:03:12.319 --> 00:03:15.280 technical people about this coming as kind of a I'm 56 00:03:15.280 --> 00:03:18.199 a nerd technical, but I'm definitely not like a developer technical. 57 00:03:18.639 --> 00:03:20.599 So I would like to add to that, Soner. If 58 00:03:20.639 --> 00:03:24.240 you recall, we kind of started talking about you coming 59 00:03:24.280 --> 00:03:27.360 on the show after I posted on X kind of 60 00:03:27.360 --> 00:03:31.759 a shout out inviting people who are involved with vibe 61 00:03:31.759 --> 00:03:34.719 coding in some form or shape to come on our 62 00:03:34.719 --> 00:03:37.439 show to talk about it. And about a month ago 63 00:03:38.159 --> 00:03:42.280 we had Anthony Compolo talking about vibe coding from the 64 00:03:42.319 --> 00:03:46.400 developer perspective. So I thought it would be great to 65 00:03:46.520 --> 00:03:50.800 have somebody coming at it from a different perspective. One 66 00:03:51.000 --> 00:03:55.159 of product management because I think again, looking at product 67 00:03:55.199 --> 00:03:58.479 managers in the company that I work at, Size Sense 68 00:03:59.000 --> 00:04:01.439 and other companies I talk to other people who are 69 00:04:01.479 --> 00:04:04.599 in product management, I do see it making a whole 70 00:04:04.639 --> 00:04:07.840 lot of impact. And I do think that one of 71 00:04:07.879 --> 00:04:13.759 the most impacted fields are developers and product people, but 72 00:04:13.800 --> 00:04:16.639 they're impacted in somewhat different ways, although there are a 73 00:04:16.639 --> 00:04:19.839 lot of similarities. So I thought your your take on this, 74 00:04:20.079 --> 00:04:22.920 your view, your point of view, would be very pertinent 75 00:04:23.079 --> 00:04:24.000 to our listeners. 76 00:04:24.480 --> 00:04:27.240 I think it's interesting that even I'm assuming your listeners 77 00:04:27.240 --> 00:04:31.639 are typical like in the development world, which is exactly 78 00:04:31.759 --> 00:04:34.120 kind of what I'm seeing happen within the product management worlds, 79 00:04:34.160 --> 00:04:38.199 Like those worlds are crossing more because it's almost like 80 00:04:38.279 --> 00:04:40.639 we spoke two different languages in the past, right, I 81 00:04:40.680 --> 00:04:43.160 speak the language the customer, and where I work we 82 00:04:43.279 --> 00:04:46.120 are very big writing culture, so I'm used to like 83 00:04:46.480 --> 00:04:50.319 great stories you go deep to the customer that world. 84 00:04:51.800 --> 00:04:55.759 But because of what this new technology has created, it's 85 00:04:55.759 --> 00:04:59.319 almost like having a translator with us at all times, 86 00:04:59.439 --> 00:05:04.040 where now I'm speaking developer language, even though I'm not right, 87 00:05:04.240 --> 00:05:08.480 I'm I'm vibing, and I think that has has massive 88 00:05:08.600 --> 00:05:12.160 change to how we approach building products. 89 00:05:12.519 --> 00:05:15.360 Uh, throughout the industry, and I think everyone. 90 00:05:15.759 --> 00:05:17.720 A conversation I've had with a lot of my you 91 00:05:17.800 --> 00:05:20.160 know buddies at work is if you had to start 92 00:05:20.160 --> 00:05:22.959 a new company today, would it look the same as 93 00:05:22.959 --> 00:05:25.240 if you did it five years ago? And I argued 94 00:05:25.279 --> 00:05:27.720 that it would not, like you know we have. I'm 95 00:05:27.720 --> 00:05:30.040 sure we'll talk about what is the role of junior devs? 96 00:05:30.040 --> 00:05:31.800 How do you get senior devs in a world where 97 00:05:31.839 --> 00:05:35.360 junior devs don't have a job anymore? Like, Uh, there's 98 00:05:35.360 --> 00:05:38.040 so many different directions we can come to this, but 99 00:05:38.160 --> 00:05:40.040 let me let me get one more dig in before 100 00:05:40.759 --> 00:05:42.399 you jumps some work. I do want to have like 101 00:05:42.480 --> 00:05:45.079 a legal note here. 102 00:05:45.920 --> 00:05:49.160 I'm Gunner. I'm just here talking about my experience. 103 00:05:49.319 --> 00:05:51.720 I in no way in speaking on behalf of my 104 00:05:51.879 --> 00:05:56.439 company at all, So please don't edit that boasts. Just 105 00:05:56.959 --> 00:05:59.519 make sure I'm required to have like a legal disclaimer 106 00:05:59.600 --> 00:06:01.720 that I'm speaking on behalf of myself and experience. 107 00:06:01.759 --> 00:06:03.680 I haven't product well, I don't know. 108 00:06:03.680 --> 00:06:05.480 We just got a response to our sweet on job 109 00:06:05.560 --> 00:06:08.360 script jabber from the head of AWS that said tell 110 00:06:08.399 --> 00:06:09.800 Gunner to be careful. 111 00:06:09.839 --> 00:06:12.680 No, I'm kidding turn go ahead, turning my back. 112 00:06:12.959 --> 00:06:16.040 Yeah, I do have to say that it's it's essentially 113 00:06:16.079 --> 00:06:18.680 the same for us. We're all here talking on behalf 114 00:06:18.720 --> 00:06:24.319 of ourselves, not representing our employers. It's uh, you know, 115 00:06:24.360 --> 00:06:26.000 take our opinions for what they're worth. 116 00:06:27.720 --> 00:06:27.839 Uh. 117 00:06:28.399 --> 00:06:33.079 Interestingly, I recently spoke with one of our senior developer 118 00:06:33.199 --> 00:06:37.240 slash architects at size Sense, and he's one of the 119 00:06:37.279 --> 00:06:41.360 people that has really bought into AI. He's the one 120 00:06:41.439 --> 00:06:45.879 using up all the tokens in his development environment. And 121 00:06:45.920 --> 00:06:48.720 the way he talked about it is how he feels 122 00:06:49.319 --> 00:06:52.639 in a lot of ways like he is becoming kind 123 00:06:52.639 --> 00:06:57.680 of product working with a team of junior devs that 124 00:06:57.800 --> 00:07:01.360 he's instructing on what they should be doing doing and 125 00:07:01.399 --> 00:07:02.839 then critiquing their work. 126 00:07:03.680 --> 00:07:06.399 So it's it. It is very. 127 00:07:06.199 --> 00:07:09.759 Interesting that we are coming at it from different perspectives, 128 00:07:10.160 --> 00:07:14.920 but it seems that they are kind of converging on 129 00:07:14.920 --> 00:07:18.240 on on this kind of a central place. But again, 130 00:07:18.279 --> 00:07:20.439 I'll hand it over to you to get your opinion 131 00:07:20.480 --> 00:07:20.800 on this. 132 00:07:21.040 --> 00:07:25.040 Yeah, I mean, it's what is the output that a 133 00:07:25.079 --> 00:07:28.839 product manager should have these days? Like I still think 134 00:07:28.839 --> 00:07:31.079 the input is very much the same, Like you need 135 00:07:31.120 --> 00:07:33.600 to go deep with your customers, like be customer obsessed. 136 00:07:34.000 --> 00:07:36.120 Understand what the problem is that you're trying to solve. 137 00:07:36.160 --> 00:07:38.560 Like that's something that is still very firmly a product 138 00:07:38.680 --> 00:07:40.000 manager role. 139 00:07:40.720 --> 00:07:41.959 But then it's what's the output. 140 00:07:42.040 --> 00:07:45.199 Well, previously the output is you know, writing a PRD, 141 00:07:45.639 --> 00:07:49.439 you know, a business requirement doc, product requirement docs, product 142 00:07:49.439 --> 00:07:52.000 feature request, whatever, it's it's in the world that I 143 00:07:52.000 --> 00:07:54.480 live in, as always some form of a document that 144 00:07:54.519 --> 00:07:58.800 then we have some paperwork, right, and we have a meeting, 145 00:07:58.879 --> 00:08:00.480 and I have a meeting with you my head of 146 00:08:00.480 --> 00:08:03.800 engineering or you know, some SDEs whoever it is with 147 00:08:03.839 --> 00:08:06.600 someone on the development side, and we have conversations, they 148 00:08:06.600 --> 00:08:08.839 have questions. So then I go back and I modify 149 00:08:08.920 --> 00:08:12.120 my documented. Maybe I'm doing focus group testing. Maybe I 150 00:08:12.160 --> 00:08:15.040 have a UX team coming in and uh sharing you know, 151 00:08:15.079 --> 00:08:17.600 their perfection how this thing should look right, and just 152 00:08:18.000 --> 00:08:18.920 this is just how it works. 153 00:08:18.959 --> 00:08:21.040 This is you know, in the industry, that's just this 154 00:08:21.160 --> 00:08:23.199 is normal product manager one of one stuff. 155 00:08:23.439 --> 00:08:28.279 And so we spend weeks, if not months, in meetings 156 00:08:28.319 --> 00:08:30.759 and doc reviews and back and forth, back and forth, 157 00:08:30.800 --> 00:08:33.440 back and forth in what I like to call agile 158 00:08:33.480 --> 00:08:38.000 full because it's neither actual nor waterfall. But you're doing 159 00:08:38.039 --> 00:08:41.519 this over and over and over and over. Whereas that 160 00:08:41.960 --> 00:08:47.320 iteration changes, everything changes. When I can just go into 161 00:08:48.279 --> 00:08:51.879 a tool like Cursor, like Caro, like you know vs 162 00:08:51.919 --> 00:08:55.240 Code with some MCP's running, Like there's so many tools 163 00:08:55.279 --> 00:08:58.559 out there right now, I can go on a tool 164 00:08:58.639 --> 00:08:59.519 and literally. 165 00:08:59.240 --> 00:09:00.960 Just like bullet point my thoughts. 166 00:09:01.639 --> 00:09:03.600 It's like this is this is this, and then have 167 00:09:03.759 --> 00:09:07.559 that tool take my thoughts, stretch them out and either 168 00:09:07.600 --> 00:09:10.279 write me a better BRD that makes me think of, 169 00:09:10.360 --> 00:09:12.799 oh I didn't think about the yeah QA testing, I 170 00:09:12.840 --> 00:09:14.639 should have done that. Yeah, And it thinks about that 171 00:09:14.679 --> 00:09:17.600 for me just fantastic, because then I add more questions. 172 00:09:17.960 --> 00:09:19.799 Now I'm having this back and forth from a product 173 00:09:19.799 --> 00:09:26.480 manager perspective with the AI on what are the requirements? Like, fully, 174 00:09:26.600 --> 00:09:28.320 what am I? What am I missing? Just ask the 175 00:09:28.320 --> 00:09:29.919 prompt what am I missing? And it it's like, well, 176 00:09:29.919 --> 00:09:31.679 did you think, well this is this? So you have 177 00:09:31.759 --> 00:09:34.279 these better docs that are written in much much faster times. 178 00:09:34.759 --> 00:09:38.039 But and I think, more importantly, I don't need to 179 00:09:38.279 --> 00:09:39.000 generate a DOC. 180 00:09:39.320 --> 00:09:39.919 I still do. 181 00:09:40.399 --> 00:09:44.000 That's still kind of the expectation, but more often than not, 182 00:09:44.279 --> 00:09:48.559 I'm actually more interested in building a prototype, and you know, 183 00:09:48.639 --> 00:09:50.919 working in sandbox environments and saying, you know what, I 184 00:09:50.960 --> 00:09:52.679 have this idea, let's. 185 00:09:52.440 --> 00:09:53.200 Just run with it. 186 00:09:53.519 --> 00:09:55.200 And I don't have I don't need a code review, 187 00:09:55.279 --> 00:09:57.240 I don't need security all this kind of stuff because 188 00:09:57.279 --> 00:10:00.399 I'm not a developer, right, But now I can develop 189 00:10:00.840 --> 00:10:04.639 and I can actually show a working system to my 190 00:10:04.720 --> 00:10:08.399 development team, where now the handoff is not necessarily just 191 00:10:08.519 --> 00:10:15.440 a document, it is a working experience prototype that I vibed, 192 00:10:16.080 --> 00:10:18.399 and I think that's where things change. And then we 193 00:10:18.399 --> 00:10:21.240 have this whole question of like what does that mean 194 00:10:21.279 --> 00:10:24.440 for developers? How many developers you need? If you're able 195 00:10:24.440 --> 00:10:26.960 to do quick prototyping like it used to be, I 196 00:10:26.960 --> 00:10:29.000 would maybe write a one pager up, send it to 197 00:10:29.080 --> 00:10:31.960 a junior dev. The dev like whips up a prototype 198 00:10:31.960 --> 00:10:35.080 in a sprint. We look at the prototype like that's 199 00:10:35.159 --> 00:10:38.600 we're talking weeks of time down to an afternoon. For me, 200 00:10:39.600 --> 00:10:44.320 we're talking less communication errors because now I'm actually showing you, 201 00:10:44.440 --> 00:10:47.120 not just telling you. I've said this multiple times with 202 00:10:47.279 --> 00:10:49.480 never on a podcast. It's you know, there's this phrase 203 00:10:49.480 --> 00:10:52.279 that a picture it's worth a thousand words, but a 204 00:10:52.399 --> 00:10:56.480 prototype is worth a thousand meetings. Just showing me the 205 00:10:56.480 --> 00:10:58.799 thing that you're trying to build, and it shouldn't matter 206 00:10:58.840 --> 00:11:01.759 that the code is not that good, Like it doesn't matter. 207 00:11:02.159 --> 00:11:05.240 What matters from a product standpoint. It's because I'm not 208 00:11:05.320 --> 00:11:08.360 I'm not trying to say build it like this as 209 00:11:08.360 --> 00:11:10.320 far as like the code goes. I'm saying, build it 210 00:11:10.399 --> 00:11:12.559 like this because this is how I fundamentally want this 211 00:11:12.639 --> 00:11:13.360 thing to work. 212 00:11:14.000 --> 00:11:17.080 So are you saying then that it's a it's from 213 00:11:17.120 --> 00:11:19.480 a Okay, you're saying so the underlying code may not 214 00:11:19.559 --> 00:11:23.600 be what they want, but the UI, the appearance, the flow, 215 00:11:23.720 --> 00:11:25.440 this is what you're trying to give them. The idea 216 00:11:25.639 --> 00:11:31.120 is gives me. The ideas is the is the says, 217 00:11:31.679 --> 00:11:33.559 is it very close to what you want? As an 218 00:11:33.639 --> 00:11:36.440 end product ors? You'r I would assume this is just 219 00:11:36.440 --> 00:11:39.159 sort of okay, this is a general idea of what 220 00:11:39.200 --> 00:11:41.000 I'm looking for. It's not going to be you know, 221 00:11:41.039 --> 00:11:42.799 fit and finish isn't going to be there. It's just 222 00:11:42.840 --> 00:11:44.679 sort of a general, yeah, this is what I want 223 00:11:44.679 --> 00:11:46.399 it to do, so you can see it instead of 224 00:11:46.440 --> 00:11:47.639 me'b describe it on paper. 225 00:11:48.039 --> 00:11:49.879 That's just it. It depends. I would agree with what 226 00:11:49.919 --> 00:11:53.399 you said. The fit and finish doesn't necessarily have to 227 00:11:53.399 --> 00:11:55.799 be there. But at the same time, it depends how 228 00:11:55.879 --> 00:11:58.679 deep we go into using these AI agents. 229 00:11:58.759 --> 00:11:59.960 Okay, I gotta be someone careful. 230 00:12:00.120 --> 00:12:02.799 Let's just say there's an MCP that exists that has 231 00:12:02.879 --> 00:12:06.399 my UI framework built into it. Well, now my fit 232 00:12:06.440 --> 00:12:09.120 and finish is my fit and finish. 233 00:12:09.320 --> 00:12:13.320 Now is the code fit? I don't know. 234 00:12:13.360 --> 00:12:15.679 I'm not intelligent enough to tell you if the code 235 00:12:15.720 --> 00:12:17.799 is right, but I can tell you that the fit 236 00:12:17.879 --> 00:12:19.720 and finish like the when I pull it up on. 237 00:12:19.960 --> 00:12:20.679 You know, a browser. 238 00:12:21.279 --> 00:12:24.360 Yeah, that's actually what the end result should look like 239 00:12:24.679 --> 00:12:28.679 because I can use an AI that takes like a 240 00:12:28.679 --> 00:12:32.879 figma and turns it into working code that's public information, 241 00:12:33.080 --> 00:12:36.399 right doing taking advantage of these tools out there, Like now, 242 00:12:36.399 --> 00:12:38.360 all of a sudden, like my UI is my UI, 243 00:12:38.440 --> 00:12:40.279 even though it maybe only took me an afternoon to 244 00:12:40.320 --> 00:12:44.519 do it, I actually have a rich UI using the components, 245 00:12:44.639 --> 00:12:47.240 using everything that I wanted to use. But again, I 246 00:12:47.240 --> 00:12:49.120 do want to draw a really firm line that I'm 247 00:12:49.159 --> 00:12:53.000 not saying that the actual code makes any sense. 248 00:12:54.600 --> 00:12:55.240 That right, for sure? 249 00:12:55.399 --> 00:12:57.960 Yeah, we get that, but the fit and finish might 250 00:12:58.360 --> 00:12:59.720 depending on the tools you're using. 251 00:13:00.639 --> 00:13:02.879 A few questions about that. So, first of all, I 252 00:13:02.919 --> 00:13:05.600 totally agree with you and understand the concept that the 253 00:13:05.639 --> 00:13:09.159 code is not production ready. For example, it might not 254 00:13:09.279 --> 00:13:12.720 be secure, it might have you know, it might not 255 00:13:12.840 --> 00:13:16.120 require our log in or anything. It just it just 256 00:13:16.240 --> 00:13:19.279 looks like, you know, there might not be issues like 257 00:13:19.279 --> 00:13:22.840 permissions and all this stuff, although you might actually vibe 258 00:13:22.840 --> 00:13:25.200 code some of that in order to show how that works, 259 00:13:25.240 --> 00:13:28.559 if that's part of what you're designing. I totally get that, 260 00:13:28.840 --> 00:13:34.039 and I totally agree with that. I am curious about 261 00:13:34.039 --> 00:13:37.639 some other aspects though. So first of all, how likely 262 00:13:37.679 --> 00:13:40.320 are you actually going to be to try to actually 263 00:13:40.440 --> 00:13:48.039 connect it to back end data versus just mocking some data? 264 00:13:48.519 --> 00:13:51.799 So that would be one question. Another question, you mentioned 265 00:13:51.799 --> 00:13:56.200 that you can take Figma designs, but will you actually 266 00:13:56.240 --> 00:14:00.320 even be waiting for the UX people to you have 267 00:14:00.399 --> 00:14:04.519 the designs ready or will you also kind of quote 268 00:14:04.600 --> 00:14:07.919 unquote jump the gun on them and say this is 269 00:14:08.080 --> 00:14:10.840 kind of I'm not like, I'm not a developer. I'm 270 00:14:10.879 --> 00:14:15.000 also not a UX expert, but this is kind of 271 00:14:15.200 --> 00:14:18.000 like how I envision it working. I don't know if 272 00:14:18.000 --> 00:14:21.320 this is the proper color scheme, if this is like 273 00:14:22.919 --> 00:14:26.320 it has accessibility and stuff like that. I just want 274 00:14:26.360 --> 00:14:29.759 to show you how I feel it should kind of look. 275 00:14:29.919 --> 00:14:31.759 So those are the two questions that I have. 276 00:14:32.399 --> 00:14:35.399 I come from a position of privilege here. I just 277 00:14:35.399 --> 00:14:38.679 want to be really clear about this. I have a 278 00:14:38.840 --> 00:14:42.320 UI framework, and in fact, I can pick from a 279 00:14:42.399 --> 00:14:46.799 set of UI frameworks that have a wonderful UX team 280 00:14:46.879 --> 00:14:51.080 behind them that are built on it. So your question 281 00:14:51.240 --> 00:14:53.080 of like as a product manager, when I just like, hey, 282 00:14:53.080 --> 00:14:55.960 this is how it works, honestly, like I would point 283 00:14:55.960 --> 00:14:59.360 it to an MCP of like, hey, using this framework, 284 00:14:59.600 --> 00:15:02.440 right to talk to this MVP about that framework, I 285 00:15:02.480 --> 00:15:06.000 can within a few minutes, I can have something like 286 00:15:06.000 --> 00:15:06.960 I don't know if you've messed with. 287 00:15:06.919 --> 00:15:08.600 Like lovable AI or these other ways. 288 00:15:08.879 --> 00:15:11.960 There's a lot of these guys out there where they 289 00:15:11.960 --> 00:15:14.200 can actually give you the fit and finish that is 290 00:15:14.240 --> 00:15:17.639 aligned to your standards. So even accessibility, this is actually 291 00:15:17.679 --> 00:15:19.960 one of that I'm glad you brought that up, Like 292 00:15:20.000 --> 00:15:21.159 that's a common one. 293 00:15:21.200 --> 00:15:23.840 It's like, oh, well, you know, a product manager. 294 00:15:23.519 --> 00:15:26.159 Doesn't necessarily think about that because they're just thinking like 295 00:15:26.200 --> 00:15:29.279 the end customer problem is, Dan needs to talk to Steve, 296 00:15:29.720 --> 00:15:31.679 and this is how we got to make it work right, 297 00:15:32.639 --> 00:15:34.759 and they're not thinking about light mid dark mode and 298 00:15:34.919 --> 00:15:38.200 whatever else is going on within the Accessibility to I framework. 299 00:15:38.600 --> 00:15:41.039 But that's where I point to, like that may be 300 00:15:41.080 --> 00:15:43.159 true and how a product manager thinks today. It's like, hey, 301 00:15:43.200 --> 00:15:46.080 I'm just going to solve this problem, but these tools 302 00:15:46.120 --> 00:15:47.720 make it so even though I'm not necessary to think 303 00:15:47.720 --> 00:15:50.960 about it, they're embedded into it. Even your comment Steve 304 00:15:51.000 --> 00:15:54.080 about security, if you're using the right tool, if you're 305 00:15:54.159 --> 00:15:56.320 using the right I don't want to call it prompt 306 00:15:56.320 --> 00:15:58.879 because they're like the prompts before the prompts, I forgot 307 00:15:58.879 --> 00:16:00.639 what they're called the rules. 308 00:16:00.639 --> 00:16:02.000 I think that's what they're rules. 309 00:16:02.200 --> 00:16:03.559 Like if you have the right rules in there is 310 00:16:03.600 --> 00:16:06.600 like and when you respond, like think about securities, think 311 00:16:06.600 --> 00:16:08.720 about this, think about that, like when you have those 312 00:16:08.799 --> 00:16:11.440 embedded in the background, even though I might not me 313 00:16:11.480 --> 00:16:13.120 thinking about it, which is what I love about it. 314 00:16:13.120 --> 00:16:15.399 By the way, it's like, I'm just thinking, I want 315 00:16:15.440 --> 00:16:17.840 to get Dan to talk to Steve using my new 316 00:16:17.919 --> 00:16:18.799 in semessenger app. 317 00:16:18.840 --> 00:16:19.480 I'm making it up. 318 00:16:20.440 --> 00:16:23.159 It's like cool, Okay, well I didn't think about this, 319 00:16:23.240 --> 00:16:26.600 that and the other, but it did. And that's where 320 00:16:26.639 --> 00:16:28.120 I was saying earlier is like where I used to 321 00:16:28.120 --> 00:16:30.399 write a BRD and I have to think about every 322 00:16:30.440 --> 00:16:33.320 single edge case scenario. Getting a meeting is like, Gunnard, 323 00:16:33.320 --> 00:16:35.240 did you think about this edge case? 324 00:16:35.279 --> 00:16:36.000 And then I get mad. 325 00:16:36.000 --> 00:16:38.159 It's like, my gosh, we're going to be naval gazing 326 00:16:38.159 --> 00:16:40.480 for the next four months about every edge case. Well, 327 00:16:40.519 --> 00:16:44.200 now I can throw it in here and it's it's 328 00:16:44.320 --> 00:16:47.480 got doing a very good job. Like these tools six 329 00:16:47.519 --> 00:16:50.279 months ago to today are just completely different as far 330 00:16:50.320 --> 00:16:52.519 as I'm concerned. Like I remember trying to do this 331 00:16:52.559 --> 00:16:54.679 about six months ago and I'm like copying and pasting 332 00:16:54.679 --> 00:16:59.080 stuff into like chat, GBT or Rock two five or 333 00:16:59.080 --> 00:16:59.960 whatever it was at the time. 334 00:17:00.480 --> 00:17:02.080 Now you know it's fully embedded. 335 00:17:02.240 --> 00:17:04.839 It's thinking the latest one that I'm very impressed with 336 00:17:04.880 --> 00:17:07.680 this amount of QA testing that it built. I've never 337 00:17:08.000 --> 00:17:11.160 once asked it to build a QA test for this 338 00:17:11.240 --> 00:17:14.960 feature that I'm biting. But these tools are as they're 339 00:17:14.960 --> 00:17:18.119 getting more mature, they're thinking about scale, They're doing all 340 00:17:18.119 --> 00:17:20.759 this stuff where it is thinking about accessibility, is thinking 341 00:17:20.759 --> 00:17:23.279 about security, is thinking about how do you test this 342 00:17:23.720 --> 00:17:26.839 stuff at scale so you automatically alert when things are 343 00:17:27.000 --> 00:17:29.880 working properly or latency is getting too high or you 344 00:17:29.920 --> 00:17:30.759 know you're. 345 00:17:31.039 --> 00:17:36.240 Yeah, but even when you do have a design system, 346 00:17:36.880 --> 00:17:39.400 UX stood as a job. I mean, you know how 347 00:17:39.440 --> 00:17:44.079 to organize stuff on the page, how to break things 348 00:17:44.119 --> 00:17:45.160 between pages. 349 00:17:46.000 --> 00:17:47.680 That's where I say it came from a position of 350 00:17:47.839 --> 00:17:50.279 privilege in that, yes, you exit the job. So I 351 00:17:50.400 --> 00:17:53.839 have a rich library of components that I can talk 352 00:17:53.880 --> 00:17:56.079 to an AI and have it use those commonents. Now 353 00:17:56.119 --> 00:17:58.920 the question is what happens when you come up with 354 00:17:58.960 --> 00:18:02.519 an idea that doesn't it within that library component? My 355 00:18:02.559 --> 00:18:04.839 position privilege is, well, then I that would be kind 356 00:18:04.880 --> 00:18:07.759 of traditional product management of like, hey, go talk to 357 00:18:07.759 --> 00:18:09.000 the UX team, have a meeting. 358 00:18:09.440 --> 00:18:12.039 This is what I'm thinking. They build a component and 359 00:18:12.079 --> 00:18:14.240 so yeah, that would be maybe I'm moving back into 360 00:18:14.240 --> 00:18:15.240 the traditional world. 361 00:18:16.480 --> 00:18:18.960 But you only have so much of that because once 362 00:18:19.000 --> 00:18:23.119 you built this library up, I can in that library 363 00:18:23.160 --> 00:18:24.400 is understood by AI. 364 00:18:25.279 --> 00:18:26.440 It just doesn't. 365 00:18:26.640 --> 00:18:31.279 So in effect, you've not only cut kind of the 366 00:18:31.400 --> 00:18:36.640 developer out of building the MVP, you've also cut the 367 00:18:37.119 --> 00:18:42.480 designer out of building the MVP. You could, let's let's 368 00:18:42.480 --> 00:18:43.799 put it bluntly. 369 00:18:43.519 --> 00:18:48.000 I would say compress. We've compressed the amount of designers 370 00:18:48.039 --> 00:18:51.279 we've needed. We've compressed the amount of developers we've needed 371 00:18:52.000 --> 00:18:55.920 within this process of creation. It just allows me to 372 00:18:55.960 --> 00:18:59.039 iterate much quicker now. I think you actually kind of 373 00:18:59.079 --> 00:19:01.359 hit an interesting point. And I think AI in general, 374 00:19:01.440 --> 00:19:04.400 AI is only backwards facing, right, it can only tell 375 00:19:04.480 --> 00:19:07.359 you what it's been taught. I think it struggles more 376 00:19:07.400 --> 00:19:09.480 with like, hey, I want to do something that's new 377 00:19:09.519 --> 00:19:12.160 and different. I have a much harder time and I'm like, hey, 378 00:19:12.200 --> 00:19:15.359 I want a UI component that does this. Those prompts 379 00:19:15.440 --> 00:19:19.119 have done that, Like those are painful, whereas it's lot 380 00:19:19.160 --> 00:19:22.119 easier when if it's something that's more common, like hey, 381 00:19:22.160 --> 00:19:24.240 this thing don't exist, it can do that no time. 382 00:19:25.440 --> 00:19:28.839 But thinking I don't know. At the same time, you see. 383 00:19:28.640 --> 00:19:33.079 These freaking crock AI videos that do interesting stuff. But 384 00:19:33.559 --> 00:19:36.920 in my experience that the creation side of it that's 385 00:19:37.000 --> 00:19:39.680 like new and different, I find that to be a 386 00:19:39.720 --> 00:19:40.119 little bit. 387 00:19:41.400 --> 00:19:45.200 I had that amusing situation recently. I had I was 388 00:19:45.240 --> 00:19:50.359 trying to get and I was playing around with a 389 00:19:50.400 --> 00:19:54.440 new library that does a certain thing, an alternative to 390 00:19:54.480 --> 00:19:58.400 an existing library that we're using, and I asked it 391 00:19:58.480 --> 00:20:01.440 to build a mall application for me using that does 392 00:20:01.480 --> 00:20:04.720 a certain thing using this new library, And I was going. 393 00:20:05.400 --> 00:20:08.519 Cursor was chugging along, and a certain point it says, 394 00:20:09.079 --> 00:20:11.559 I failed, I'm going to revert to that old library, 395 00:20:12.799 --> 00:20:15.279 which I found to be really amusing. It's kind of 396 00:20:15.359 --> 00:20:18.240 almost a human type response in a sense. So I 397 00:20:18.680 --> 00:20:22.680 stopped it because that the whole point was building the 398 00:20:22.720 --> 00:20:26.039 thing using the new library, not just doing it again using. 399 00:20:25.880 --> 00:20:27.000 The old library first. 400 00:20:27.079 --> 00:20:29.200 Or deleted my entire front end because it got tired 401 00:20:29.240 --> 00:20:31.839