ABOUT THIS EPISODE
Prompt Used for today's show: https://docs.google.com/document/d/1tDG3DKfYpLKwJOU8OKYA0-MWk22yMsIk4q2u2Rt6_FA/edit?usp=sharing
Link to the app we vibe coded: https://poll-spark-stream.lovable.app
Ready to dive into the future of digital tool creation? This week, we're not just talking about vibe coding – we're doing it LIVE!
Join me as we explore how this transformative approach is reshaping how we build tools, solve problems, and enhance both customer and employee experiences. I'll break down what vibe coding truly means, using practical metaphors and explaining why it's turning traditional coding on its head. We’ll discuss the exciting implications, from the rise of specialized micro-SaaS to teams solving their own unique challenges.
Plus, I'll share my "biggest unlock" for successful vibe coding: how to craft the perfect initial prompt to get 80% of the way there, right from the start. We'll even demo building a live polling app, so you can see the process firsthand (you might want to check out the video version!). This episode is packed with insights and takes you step-by-step through my own process and recommended tools.
Don't miss this deep dive into a skill that's quickly becoming essential for anyone in the digital space.
If you're a new Digital CX leader looking to fast-track your onboarding, an individual contributor wanting to learn more about Digital or a senior leader looking for ways of enabling your team - look no further than the Digital CX Masterclass: visit https://digitalcustomersuccess.com/masterclass.
+++++++++++++++++
Like/Subscribe/Review:
If you are getting value from the show, please follow/subscribe so that you don't miss an episode and consider leaving us a review.
FREE Digital CX Maturity Assessment:
Want to see how your digital cs program stacks up against The Four Pillars of Digital CX? Take a free, 15-minute assessment followed by tactical advice for advancing your program.
Register for The Digital CX Masterclass:
An 8-week, cohort based course that will get you fully operational in a few weeks instead of a few quarter! Fast-track your digital CS maturity and start shipping great work within the first week!
Subscribe to the Newsletter:
A weekly-ish companion newsletter in which I share the latest in digital cs, my own work and occasionally annoying opinions about the state of CX.
Thank you for all of your support!
The Digital Customer Success Podcast is hosted by Alex Turkovic
SHOW NOTES 🔗
TRANSCRIPT 🔗
00:00:22.489 --> 00:00:29.850
Today, we're going to get in vibe coding, and not only are we going to talk about it in theory and the implications of it, but we're actually going to do it live on the episode.
00:00:29.929 --> 00:00:32.409
So you might want to watch this one on YouTube.
00:00:32.890 --> 00:00:37.849
Once again, welcome to the Digital Customer Experience podcast with me, Alex Turkovich.
00:00:38.170 --> 00:00:45.530
So glad you could join us here today and every week as we explore how digital can help enhance the customer and employee experience.
00:00:45.769 --> 00:00:52.969
My goal is to share what my guests and I have learned over the years so that you can get the insights that you need to evolve your own digital programs.
00:00:53.209 --> 00:01:02.890
If you'd like more info, need to get in touch, or sign up for the weekly companion newsletter that has additional articles and resources in it, go to digitalcustomer success.com.
00:01:02.969 --> 00:01:04.730
For now, let's get started.
00:01:05.609 --> 00:01:12.329
Hello and welcome back to the Digital Customer Experience Podcast, the show where we talk about all things digital in CX.
00:01:12.409 --> 00:01:17.450
I'm Alex Turkovich and I'm so glad you're here with me this week as we're talking about vibe coding.
00:01:17.530 --> 00:01:32.009
Now, um, if you attended the Customer Success Uh Summit in Austin, you'll know that I did a live vibe coding session on stage where we built a customer value uh story generator.
00:01:32.250 --> 00:01:34.250
Super cool uh use case.
00:01:34.409 --> 00:01:43.450
Um, and so I wanted to actually bring some of that content into the podcast uh so that you can also partake if you weren't able to attend that event.
00:01:43.609 --> 00:01:54.170
So um before we actually do a live demo, and yes, you know, I'm gonna vibe code something on the podcast today so that you can watch it.
00:01:54.250 --> 00:02:10.330
Again, you may want to resume this episode um on YouTube going, you know, going forward from this point because I am gonna be sharing a bit of content, a couple slides that I shared as well, and then you know, again, you I'm gonna basically take you over my shoulder so that you can watch some of this stuff.
00:02:10.490 --> 00:02:16.890
I think there's some discrepancy out there or maybe some misunderstanding about what vibe coding really is all about.
00:02:17.129 --> 00:02:23.210
And one of the metaphors that I like to use is essentially a construction industry metaphor.
00:02:23.370 --> 00:02:29.530
The point being that coders of tomorrow are not gonna be construction workers, they're gonna be the architects, right?
00:02:29.689 --> 00:02:45.610
So when you think of traditional coding, um, you think of, you know, hands on keyboard, folks writing code line by line, and those kinds of things, that is essentially in construction akin to somebody hauling bricks or mixing mortar or doing those kinds of things.
00:02:45.850 --> 00:02:51.689
Whereas in vibe coding, you know, you're essentially becoming the architect.
00:02:51.770 --> 00:02:58.250
Um, and this is happening right now in software development, but it's also happening right now outside of software development.
00:02:58.409 --> 00:03:03.850
Uh so you're not necessarily hauling bricks around and actually doing the construction work.
00:03:03.930 --> 00:03:09.370
You're making the decisions about what you want the building to look like after it's done.
00:03:09.530 --> 00:03:13.689
And, you know, to some extent in the process and making adjustments and those kinds of things.
00:03:13.850 --> 00:03:25.050
So, you know, AI, the construction crew, so to speak, handles the construction and the implementation, and you handle essentially the vision and the vibe of what it is you want to build.
00:03:25.290 --> 00:03:27.130
Now, there are some implications here.
00:03:27.210 --> 00:03:35.450
I've consumed a lot of content about this in recent months, and the implications are essentially boiled down to three things.
00:03:35.610 --> 00:03:42.409
First off, we're going to start seeing a lot more niche uh micro-SaaS software out there.
00:03:42.570 --> 00:03:49.610
Things that are developed to do a very, very specific thing in a very, very specific way.
00:03:50.250 --> 00:04:01.930
Um, because you can now essentially code or you know create these kinds of um software applications, web pages, all those kinds of things that do a very specific thing.
00:04:02.090 --> 00:04:15.610
The second implication here is that teams are now gonna have the ability to essentially solve their own problems instead of immediately looking for a vendor, a software vendor doing an RFP to solve their problems.
00:04:15.770 --> 00:04:27.290
Um you're gonna have teams that develop tools and applications that help them with a business process and help them with a business process in the way that they want to operate that process.
00:04:27.850 --> 00:04:41.370
And that leads to the third implication that, you know, in the not too distant future, the days of bending your own processes to the way a specific software operates are somewhat limited, to be honest.
00:04:41.609 --> 00:04:54.969
Now, of course, we're not getting rid of Salesforce.com or HubSpot or Gainsight or Vitally or any of the CSPs or any of those big platforms anytime soon.
00:04:55.129 --> 00:05:05.370
There is a lot of inherent complexity and functionality and infrastructure built around these uh fundamental platforms that you're not just gonna go vibecode, right?
00:05:05.529 --> 00:05:08.810
Let's kind of shove that to the side.
00:05:09.849 --> 00:05:13.529
That's not to say in 10 years you won't be able to, or maybe less than that.
00:05:13.769 --> 00:05:29.849
What I'm talking about, though, are all of those other things where you are manually doing things in spreadsheets and you know, docs and other places that could be an application or an automation.
00:05:30.009 --> 00:05:43.049
It could be something that feeds data and information into one of those platforms like a Salesforce or a HubSpot or works collaboratively with them via the API or whatnot, right?
00:05:43.289 --> 00:05:53.769
So we're somewhat limited right now in terms of our imagination of what could be built with this kind of technology.
00:05:53.930 --> 00:06:08.009
And obviously, also there are some security implications here because you know with generic kind of vibe coding, you're just kind of putting stuff out there, not necessarily in a secure way, right?
00:06:08.169 --> 00:06:15.689
So what I'm not talking about right now is things that handle sensitive customer data, although you can definitely do that.
00:06:15.930 --> 00:06:25.049
And if you, you know, if you hire somebody to vibe code that does have some engineering background, at that point you can you can probably build something securely.
00:06:25.209 --> 00:06:35.849
But for your everyday, what what I'm here to really talk about is just everyday usage and potential implications for vibe coding in your day-to-day.
00:06:36.009 --> 00:06:46.569
When we talk about vibe coding, there's really a uh kind of an iterative loop process that we follow when we write something or when we vibe something.
00:06:46.729 --> 00:06:49.449
And this iterative loop essentially takes four steps.
00:06:49.609 --> 00:06:50.490
First is the prompt.
00:06:50.569 --> 00:06:52.009
You describe what it is you want.
00:06:52.089 --> 00:06:53.849
That's pretty self-explanatory.
00:06:54.089 --> 00:06:57.849
And of course, good prompting equals good results.
00:06:58.089 --> 00:07:02.810
Uh, the reveal, which means AI builds it somewhat instantly.
00:07:02.889 --> 00:07:06.810
It takes, can take seconds, can take minutes, depending on what you're building.
00:07:07.049 --> 00:07:08.490
Then comes the vibe check.
00:07:08.649 --> 00:07:33.049
You look at it and you say, okay, change the functionality of this button, or you know, this field doesn't look quite right, or you know, the the colors are a little bit off, or whatever the, you know, whatever your feedback might be, you work iteratively with your preferred vibe coding tool to make those changes, and it'll make those changes, which is essentially the refinement step.
00:07:33.129 --> 00:07:39.609
You're you're vibing back and forth with the AI so that it matches hopefully the picture in your head.
00:07:39.769 --> 00:07:45.449
And again, the better you are at prompting up front, um the easier it is.
00:07:45.529 --> 00:07:56.569
And and I've got a huge unlock for you here in a second that um that will make that first initial prompt pretty much like it'll get you 80% of the way there.
00:07:56.810 --> 00:08:11.930
Now, quick note if you're building something very complex, I'm talking about um building you know, a web app with multiple tabs and sections and databases and all that kind of stuff.
00:08:12.089 --> 00:08:15.209
Um, and by the way, you can vibe code spreadsheets as well.
00:08:15.370 --> 00:08:25.529
Claude is especially good at that, where you can build a very complex um spreadsheet or model, or you know, I've used it for a staffing model, for instance.
00:08:25.769 --> 00:08:33.210
Um the more complex it is, the more you're gonna want to take things in bite-sized chunks, just like a software developer does today.
00:08:33.370 --> 00:08:37.690
In other words, you're not gonna want to vibe code the entire thing all at once.
00:08:37.769 --> 00:08:46.570
Um, but you are, you know, it's good to get a general layout, but then you're gonna want to focus on quote unquote feature by feature.
00:08:46.730 --> 00:08:54.970
Uh, focus on building certain functionality out and then moving on to the next rather than just you know vibing on the entire thing itself.
00:08:55.210 --> 00:09:14.569
We'll jump into this here in a second, but one of the things that I wanted to give you some practical advice on and just kind of a lay of the land on is what vibe coding tools are out there and and and do so in order of sophistication, so to speak.
00:09:14.730 --> 00:09:25.850
Now, I can't take total credit for this, although I have amended it a little bit, but um, Sabrina Romanoff, if you don't follow her on socials, she's all over TikTok and Instagram and YouTube.
00:09:26.250 --> 00:09:32.649
Sabrina Sabrina Romanoff is a fantastic AI educator.
00:09:32.889 --> 00:09:36.090
I've spent a lot of time consuming her content.
00:09:36.250 --> 00:09:41.210
And so she has these four stages essentially of vibe coding tools.
00:09:41.449 --> 00:09:47.370
The first one being you're essentially you're a non-technical beginner, you're just getting in, you're kicking the tires.
00:09:47.529 --> 00:09:52.730
Maybe you want to build a simple landing page, a lead funnel, simple tools.
00:09:52.970 --> 00:10:01.289
You're gonna want to look for a tool like base 44, for instance, which is you know very, very simple, but also somewhat limited.
00:10:01.370 --> 00:10:12.009
Uh Google AI Studio as well, if you're in the Google Suite, check out Google AI Studio because it does it allow it does allow you to do some vibe coding, but it does a lot of automation type stuff too.
00:10:12.169 --> 00:10:23.289
Um, if you happen to be on a WordPress instance and you want some WordPress done, um those three tools kind of fall into this stage one category.
00:10:23.449 --> 00:10:32.970
So if you don't even know what vibe coding is and you want to just kind of figure it out and build some simple stuff, um, check out base 44, Google AI Studio, 10 Web.
00:10:33.129 --> 00:10:53.049
When we move to stage two, we add a little bit more complexity and a little bit more capability into the system where you know you can have most of these tools allow you to manage, you know, either your own database or use their native uh databases, for example.
00:10:53.289 --> 00:11:03.610
Um, these tools can be a little bit harder to fix bugs or make edits without just burning through credits.
00:11:03.769 --> 00:11:15.529
And so again, that points to what I alluded to earlier, where you're gonna want to spend a little bit more time up front making sure that you are prompting really well from the get-go.
00:11:16.169 --> 00:11:23.769
Um, but some of these tools are emergent, lovable is probably the biggest one out there that a lot of people know about.
00:11:24.090 --> 00:11:28.889
Bolt.new and replit are among those in this category.
00:11:29.049 --> 00:11:32.649
Not the only ones, but those are kind of like the front runners, so to speak.
00:11:32.809 --> 00:11:36.329
So that's kind of that stage two intermediate vibe coder.
00:11:37.049 --> 00:11:45.769
Stage three is where you're moving if you do have some technical background, but maybe you're not a software engineer, but you have some code level familiarity.
00:11:46.009 --> 00:11:56.250
These essentially AI-powered IDEs allow you to much more easily refine and debug and expand on code that was generated in earlier um stages.
00:11:56.569 --> 00:12:14.809
And you know, it's it's pretty common for you to maybe do a prototype in a stage two tool like Lovable, and then move over into, you know, let's say Cursor or Google's Antigravity to do some more enhanced uh coding and revisions with these kinds of tools.
00:12:14.889 --> 00:12:22.649
So again, cursor AI, Windsurf AI, and Google's Anti-Gravity, which is super cool, um are essentially in that stage three.
00:12:22.730 --> 00:12:36.409
Now, stage four is this is is going to be your your highest quality uh and and highest bang for your buck um output in terms of being able to build code in a truly kind of agentic way.
00:12:36.649 --> 00:12:45.449
Um and and you know, stage four is essentially what software engineers are using today to build like production level high-quality code.
00:12:45.610 --> 00:12:54.809
Uh, it does require some technical oversight and know-how to be able to manage and maintain the code as well as to implement security features.
00:12:54.889 --> 00:13:04.730
But this is, you know, this is the stage you move to when you have hundreds and thousands of users and uh, you know, a complex code base to maintain.
00:13:04.809 --> 00:13:07.370
Uh, you're gonna basically use cloud code for this.
00:13:07.529 --> 00:13:39.210
Now, there is a relatively newer intermediary here in the anthropic slash cloud claud ecosystem called um cloud co-work, which essentially what it does is it combines claud code with just claude chat um and is is uh acting as an interface, so to speak, between claud code and claude, so that you can get those kind of claud code outputs um using natural language, so to speak.
00:13:39.370 --> 00:13:48.970
But um again, if you're if you're really advanced or whatnot, a lot of folks are going to be using claud code um probably within something like Visual Studio.
00:13:49.210 --> 00:13:53.689
So those are the four stages of uh vibe coding tools.
00:13:53.850 --> 00:13:58.329
Again, shout out to Sabrina Romanoff for the baseline of this.
00:13:58.569 --> 00:14:06.490
What we will be doing here in a second is I'll break into a screen share and we can start vibe coding.
00:14:06.730 --> 00:14:18.090
The process that I like to follow, and this is probably the biggest unlock for getting the best results possible from your first iteration, is that, well, first off, you're gonna want to gather your context.
00:14:18.329 --> 00:14:33.129
So, you know, whatever tool you're building or spreadsheet you're building, or whatever it is you do, you want to gather as much context and details about what it is you want to build as possible.
00:14:33.289 --> 00:14:37.210
Because the clearer you are up front with it, the better your result is going to be.
00:14:37.370 --> 00:14:38.490
So, what are you gonna build?
00:14:38.569 --> 00:14:40.329
What's the problem you're trying to solve for?
00:14:40.409 --> 00:14:41.529
What do you want it to look like?
00:14:41.689 --> 00:14:43.689
What features do you want to incorporate?
00:14:43.850 --> 00:14:45.850
What aesthetic are you going for?
00:14:46.090 --> 00:14:49.289
What do you want it not to do specifically?
00:14:49.449 --> 00:14:53.289
Those are the kinds of things that you'll want to gather when you're doing this.
00:14:53.449 --> 00:15:04.970
Now, um, here's where my biggest recommendation comes in is do the initial prompt or produce the initial prompt outside of your vibe coding tool.
00:15:05.129 --> 00:15:20.250
So you're gonna use whatever you use on a regular basis or prefer ChatGPT, Gemini, or Claude to generate that initial vibe coding prompt for you that you're gonna then put into uh that vibe coding tool.
00:15:20.490 --> 00:15:28.409
Now I am gonna give you that that prompt that I'm gonna show you shortly so you can you know use it as a baseline foundation.
00:15:28.569 --> 00:15:41.689
Um but essentially what you're asking ChatGPT or Gemini or Claude for is you know, give me a ready-to-go prompt that is, you know, that I can plug into lovable.
00:15:41.769 --> 00:15:46.649
Let's say we're gonna use lovable today, um, so that I can get the best result possible.
00:15:46.809 --> 00:16:04.730
So what we're gonna actually do here shortly is we're going to go into one of these tools, we're gonna ask it to give us the vibe coding prompt, and then we're gonna go into the vibe coding tool, we're going to pop that in and get uh, you know, and and watch it essentially build something for us.
00:16:04.889 --> 00:16:29.210
Now, in terms of what you want to build, this is where the infinite possibilities essentially open up where you can and okay, I gotta be honest, it it took a pretty big mindset shift for me to start thinking about how I could incorporate this into my daily life.
00:16:29.449 --> 00:16:40.889
So, I mean, look, one of the first things that I vibe coded for myself was a tool to help me publish these episodes that you're listening to.
00:16:41.210 --> 00:16:49.289
Um, because what you don't see coming out of recording these episodes is all of the post-production work that goes into it.
00:16:49.449 --> 00:16:56.649
Um, yes, you gotta edit the show and do all that kind of stuff, but then you know, you've got to have your show notes ready for YouTube.
00:16:56.730 --> 00:17:03.769
You have to have your um, you know, chapter, chapters and timestamps ready, uh, as well as your description.
00:17:03.929 --> 00:17:13.690
You gotta have your show notes ready for you know the podcast platforms, uh, you got to have some LinkedIn posts ready to go, you gotta have some a newsletter companion ready to go.
00:17:13.850 --> 00:17:26.250
Like it's there's a bunch of outputs uh that we can generate pretty easily now uh with the input of let's say a transcript, for instance.
00:17:26.410 --> 00:17:55.769
So what typically what I'll do is I'll get this episode edited, I will export the transcript with timestamps, I'll plug into this tool that I vibe coded, and the tool in I don't know, 10 seconds or so gives me all of those outputs so that I can then proofread them, make some edits, pop them into whatever tool, YouTube or um, you know, podcast platforms or whatever, so that I can, you know, really quickly get that content updated and I'm not spending a ton of time writing.
00:17:55.930 --> 00:18:03.609
Now I know there are some people out there that will be like, hey, he's just, you know, you're using AI-generated content.
00:18:03.849 --> 00:18:09.129
And um, yeah, I I take issue with that a little bit because the content is all mine.
00:18:09.369 --> 00:18:11.289
The transcript is not AI.
00:18:11.369 --> 00:18:16.410
This is me talking, this is me sharing ideas, this is me talking about these things specifically.
00:18:16.569 --> 00:18:29.849
I'm I am using artificial intelligence to, you know, create the outlines of things and to identify key moments um along a podcast's kind of episode and story arc, so to speak.
00:18:30.009 --> 00:18:40.730
Um, and you know, I'm I I am a big kind of advocate for having artificial intelligence do 80% of the work for you.
00:18:40.970 --> 00:18:50.569
I am not an advocate of just having AI do stuff for you and then you blindly posting stuff because I've seen that done and it does not look good, and you can tell.
00:18:50.809 --> 00:19:02.569
Um, so you know, whenever whenever you use artificial intelligence just in general to create content, you always gotta give it that human eye and you always gotta make sure that, you know, this is actually what you want to say.
00:19:02.650 --> 00:19:04.970
So I'll get off my soap soapbox around that.
00:19:05.129 --> 00:19:22.170
But point being, that was one of the first things that I vibe coded was a web app that helps me take a show from transcript to a bunch of different assets that I can then take, edit, and implement in a fraction of the time that it took me before artificial intelligence.
00:19:22.250 --> 00:19:31.210
When I first launched the show, I would spend a half day basically um, you know, pull listening to the episode, pulling out things that I wanted to make sure were in there and those kinds of things.
00:19:31.289 --> 00:19:34.170
So that's um that has been a huge lifesaver.
00:19:34.650 --> 00:19:49.129
Um you know, it when when we were uh debating on what to vibe code during the conference last week, there were a lot of ideas uh that were brought up in that in the process of doing so.
00:19:49.450 --> 00:19:54.490
And those ideas um were kind of all across the board.
00:19:54.569 --> 00:19:55.609
A lot of it was like personal.
00:19:56.089 --> 00:20:02.650
Somebody said, hey, let's vibe code like a kid's chore chart uh or a chore tracker or something like that.
00:20:02.809 --> 00:20:23.930
So you can, you know, you can identify those little moments within your daily life where you're like, hey, it would be cool to have kind of an app for that and to you know really figure out how you can, you know, build something to make those kinds of daily activities or weekly activities easier to do.
00:20:24.089 --> 00:20:29.609
So for the purposes of this demonstration, um, what I've chosen to do is something a little bit different.
00:20:29.690 --> 00:20:33.609
Um, it is essentially a live poll or vote app.
00:20:33.930 --> 00:20:43.609
So it allows you to essentially collect answers in real time that are displayed with you know things like animated charts or whatever.
00:20:43.849 --> 00:20:57.210
Um, uh the reason why I I thought about this is because, you know, we in the in the conference we did use a uh you know a polling app, ones that you see kind of integrated into uh PowerPoint, for instance.
00:20:57.369 --> 00:21:04.250
But I thought, hmm, we could probably vibe code something similar on our own and and see if that works.
00:21:04.329 --> 00:21:10.329
And so what we're gonna do live on the podcast is just you know see if we can live code something like this.
00:21:10.490 --> 00:21:14.889
And it may fall completely on our faces or it may not.
00:21:14.970 --> 00:21:16.490
And it may be a really cool thing.
00:21:16.650 --> 00:21:30.569
Either way, after this episode, I will give you access via the show notes to a link where you can view the app, but then you can also download the the prompting that I used to get to that app.
00:21:30.730 --> 00:21:35.369
So we're gonna switch over to screen share and uh we're gonna get to some vibe coding.
00:21:35.609 --> 00:21:47.129
Okay, so what you're seeing here is a Google Doc that I um came up with and already have a misspelling on, which um it gives us our first prompt.
00:21:47.210 --> 00:21:51.609
I went ahead and pre-wrote it because you don't want to watch me like write a prompt for this, right?
00:21:51.769 --> 00:23:27.799
But um, I'll walk you through some of the key points of the prompt.
00:23:27.959 --> 00:23:34.279
First off, um like any good prompt, you're gonna want to essentially give AI a role to play.
00:23:34.359 --> 00:23:39.240
In this case, I said act as an expert in live polling survey technology.
00:23:39.719 --> 00:23:41.399
Kind of broad, but okay, cool.
00:23:41.719 --> 00:23:51.159
Uh with a high proficiency in vibe coding with level, then I gave it uh basically some context and what I want to build.
00:23:51.480 --> 00:23:54.439
Um I Said what I want it to do.
00:23:54.519 --> 00:24:02.119
So I would like you to produce a detailed prompt that I can enter into Lovable to get the best result possible for the first iteration.
00:24:02.919 --> 00:24:13.719
I gave it a primary goal for the app, which is essentially to run live polls with web browsers, either with an audience or on live streams, for instance.
00:24:14.199 --> 00:24:18.119
I gave it some specifics on specific features, right?
00:24:18.199 --> 00:24:20.519
So I said, hey, let's do two views.
00:24:20.599 --> 00:24:23.480
So let's do a host view and an audience view.
00:24:23.799 --> 00:24:27.480
Gave it a few specifics there, but nothing too crazy.
00:24:27.959 --> 00:24:35.559
I said the host should have the ability to display a QR code to allow the audience to scan via mobile phone.
00:24:36.039 --> 00:24:41.159
The audience view should be responsive so that it can be displayed on a variety of devices.
00:24:41.319 --> 00:24:47.240
I said the dashboard and the audience view should update in real time based on votes being cast.
00:24:47.399 --> 00:24:51.639
I said use animated progress bars and vote count tickers.
00:24:51.879 --> 00:24:56.679
Then I said, hey, you know, features don't need to be limited to the above, but definitely contain the above.
00:24:56.839 --> 00:25:05.559
And I said, use your practical knowledge of other live polling apps, core features, to determine additional functionality that might be needed.
00:25:05.799 --> 00:25:07.559
I said, this is going to be interesting.
00:25:07.799 --> 00:25:12.279
I said, um, basically look at my website and copy some of the aesthetic there.
00:25:12.359 --> 00:25:24.519
So I'm having it, I'm having, in this case, Gemini go and crawl digitalcustomer success.com to try and pull out some um, you know, some some color language there, maybe.
00:25:24.679 --> 00:25:30.919
Um, now here is basically the thing that I include in most any prompt these days.
00:25:31.079 --> 00:25:33.559
I actually just you know copied and pasted it over.
00:25:33.639 --> 00:25:36.839
But I include this because it's a great method to get even more detail out.
00:25:37.079 --> 00:25:45.000
So I said, ask me clarifying questions one by one until you're 100% sure that you can deliver this request to a high degree of accuracy.
00:25:45.159 --> 00:25:54.839
Um, here's something I've been um adding here recently a lot, which is provide me with a confidence score with each question that you ask.
00:25:55.079 --> 00:26:00.279
Once your certainty score reaches 100%, produce the lovable prompt for me.
00:26:00.519 --> 00:26:09.480
Do not produce a new lovable prompt after each clarifying question, but wait to produce it once you have that complete certainty.
00:26:09.799 --> 00:26:23.399
That last bit is something I've been doing recently because a lot of times what it'll want to do is produce a whole new prompt with every question that you answer, and it just wastes a whole bunch of time and tokens, and it's just not useful.
00:26:23.639 --> 00:26:27.559
So um, yeah, but I always have it ask me clarifying questions.
00:26:27.639 --> 00:26:34.359
I like seeing the confidence score because it tells me roughly how far we are until 100% certainty.
00:26:34.679 --> 00:26:37.799
So that's basically the prompt that I'm gonna start with.
00:26:37.879 --> 00:26:45.799
And again, this is the prompt that I'm feeding either ChatGPT, Gemini, or Claude to get that initial lovable prompt.
00:26:46.039 --> 00:26:48.279
So I will copy and paste that.
00:26:48.599 --> 00:27:00.279
And for this example, we're gonna use Gemini for no real reason other than I had it pulled up, I guess.
00:27:00.359 --> 00:27:02.919
Um, you could totally use ChatGPT for this.
00:27:03.079 --> 00:27:06.439
I think you can totally use Claude for this as well.
00:27:06.599 --> 00:27:10.439
I think it just kind of depends on what you're most comfortable with.
00:27:10.599 --> 00:27:15.000
Um, you know, I am going to use Pro because why not?
00:27:15.159 --> 00:27:21.559
But whatever you have the most history in and whatever, you know, knows you knows the context of you most, uh, you can use.
00:27:21.719 --> 00:27:23.240
Claude is a whole different beast.
00:27:23.399 --> 00:27:32.439
And I might do a future episode on Claude Co-work because there's some cool kind of vibe coding kind of things that you can do in Claude Co-work and Claude Code as well.
00:27:32.519 --> 00:27:36.919
So that's kind of specifically why I didn't choose Claude for this particular exercise.
00:27:37.240 --> 00:27:42.119
Anyway, um, we fed it that prompt and we're gonna let it chug for a second.
00:27:42.279 --> 00:27:44.759
So I just clicked show thinking.
00:27:45.240 --> 00:27:47.559
Of course, it sounds like a fantastic project.
00:27:47.719 --> 00:27:49.639
Current confidence score is 70%.
00:27:50.279 --> 00:27:55.719
First clarifying question: how do you want to handle authentication and vote integrity?
00:27:55.879 --> 00:27:57.000
That's a cool question.
00:27:57.159 --> 00:27:57.480
Okay.
00:27:57.719 --> 00:28:03.799
Uh, should the host have a have a login system to have their polling sessions for future use?
00:28:04.359 --> 00:28:12.359
I think it would be cool to do a login, but for the for the sake of this demonstration, I think we'll just leave it open.
00:28:12.439 --> 00:28:19.719
And in fact, I'm gonna put it on the um I'll host it on my website so that y'all can go play with it.
00:28:19.799 --> 00:28:20.519
How about that?
00:28:20.679 --> 00:28:35.319
Um, so we're just going to uh for number one, oops, for number one, we're going to leave it open for anyone to access.
00:28:35.879 --> 00:28:49.159
Okay, number two is for the audience, should they remain completely anonymous using browser local storage cookies simply for the Vogue in twice?
00:28:49.480 --> 00:28:53.799
Or do you want them to input a name, nickname before voting?
00:28:54.759 --> 00:28:55.639
Let's do this.
00:28:55.799 --> 00:29:08.039
Uh let's say that name entry can be optional in the case that a name isn't entered.
00:29:12.839 --> 00:29:21.079
The audience member who voted will remain anonymous.
00:29:21.319 --> 00:29:24.199
And I see I misspelled member, but that's okay.
00:29:25.159 --> 00:29:26.679
Gemini's smart enough.
00:29:26.919 --> 00:29:28.519
Um let's see.
00:29:28.679 --> 00:29:30.039
Do we need to say anything else about that?
00:29:30.119 --> 00:29:30.599
I don't think so.
00:29:30.679 --> 00:29:31.959
So we're gonna submit that.
00:29:32.119 --> 00:29:35.319
We're gonna see what the confidence score is next.
00:29:36.519 --> 00:29:42.679
But you see how we kind of um get all of this out of the way before we go into the vibe coding tool.
00:29:42.759 --> 00:29:52.919
Um, because these are all things that I would need to A, first think about and ideate on, um, and then implement in later stages in the vibe coding tool.
00:29:53.000 --> 00:30:01.319
This way we're coming to the vibe coding tool with a very uh kind of well-thought out plan and a super detailed plan.
00:30:01.799 --> 00:30:05.559
Next clarifying question: what types of question polls should we support?
00:30:05.719 --> 00:30:06.679
I like it.
00:30:07.000 --> 00:30:16.439
Uh strictly multiple choice or single answer, multiple answer, word cloud free text rating slide scale.
00:30:16.839 --> 00:30:25.959
Um for this first iteration, why don't we just do for first iteration?
00:30:26.759 --> 00:30:35.079
Let's keep it to multiple or single.
00:30:38.279 --> 00:30:39.639
I can't type today.
00:30:39.799 --> 00:30:59.879
Multiple choice or single answer um questions where the host has the ability to select which type of question they want to ask.
00:31:02.199 --> 00:31:16.679
Use the check boxes for multiple choice and radial button or yeah for single select.
00:31:17.480 --> 00:31:18.119
Cool.
00:31:18.839 --> 00:31:20.599
Let's see where we end up next.
00:31:21.079 --> 00:31:24.439
Identifying color palette, current confidence score 92%.
00:31:24.839 --> 00:31:25.799
That's very specific.
00:31:25.959 --> 00:31:26.519
Perfect.
00:31:26.759 --> 00:31:29.480
Uh single answer radio buttons.
00:31:29.719 --> 00:31:31.159
Um, okay.
00:31:31.639 --> 00:31:35.399
There's one final set of clarifying questions to get me 100% aesthetics.
00:31:35.480 --> 00:31:48.359
Do you have specific primary, secondary hex codes for the digital customer brand that you want me to include in the prompt, or should I instruct Lovable to use modern clean B2B SaaS aesthetic?
00:31:49.319 --> 00:31:49.799
Good place.
00:31:50.279 --> 00:31:54.599
So I did not necessarily pick up on the colors from the website.
00:31:54.679 --> 00:31:59.959
I didn't really think it would, but um poll lifecycle on the host dashboard.
00:32:00.119 --> 00:32:07.799
Do we need the ability to create a queue of multiple questions in advance so that you can toggle them live one by one?
00:32:08.199 --> 00:32:09.399
Okay, this is cool.
00:32:09.559 --> 00:32:15.639
So yeah, that second question with the poll lifecycle, obviously that introduces complexity, right?
00:32:15.959 --> 00:32:24.919
And so at this point, you may decide to reduce complexity and just do a single question at a time.
00:32:25.159 --> 00:32:38.599
Or in this case, we're just gonna throw caution to the wind and essentially have it build the ability to create multiple questions that it then uh allows the host to move through.
00:32:38.839 --> 00:32:44.199
Okay, so I have grabbed my colors, primary and secondary from the website.
00:32:44.279 --> 00:32:51.079
It's that annoying orange that you see everywhere, and uh that green secondary color that I use.
00:32:52.119 --> 00:33:14.279
And for the poll lifecycle, we're just going to say let's create a queue where the host can pre-define multiple questions that they can cycle through live during the event.
00:33:15.399 --> 00:33:19.159
Okay, this might get us to 100%.
00:33:19.639 --> 00:33:21.879
We shall see here shortly.
00:33:23.000 --> 00:33:25.319
Okay, current confidence score.
00:33:25.559 --> 00:33:26.119
100%.
00:33:26.599 --> 00:33:28.119
That is exactly what I needed.
00:33:28.279 --> 00:33:28.839
I know.
00:33:29.000 --> 00:33:30.119
Okay, cool.
00:33:30.359 --> 00:33:32.199
Uh since I have all the details.
00:33:32.359 --> 00:33:44.919
Okay, and so here what you'll see is a prompt that I can copy and paste into Lovable to start vibe coding this app.
00:33:45.480 --> 00:33:52.519
Um, now we're not gonna spend a ton of time on this for the sake of this demonstration.
00:33:52.679 --> 00:33:54.919
Okay, this is interesting down here, by the way.
00:33:55.079 --> 00:33:57.480
Um, it says Superbase setup.
00:33:57.559 --> 00:34:06.439
For those of you who may not be familiar with Superbase, it is essentially a um a database platform that Lovable partners with.
00:34:06.519 --> 00:34:08.360
And so they have a very tight integration.
00:34:08.519 --> 00:34:17.079
And for something like this, the app is going to want to create its own database so it can store the questions and the responses and all that kind of stuff, right?
00:34:17.240 --> 00:34:24.760
Um, and so a lot of times the reason why lovable is so approachable is because you don't have to create your own database and whatnot.
00:34:24.920 --> 00:34:29.079
It will essentially do it for you, uh, which is super cool.
00:34:29.320 --> 00:34:37.559
And then it is telling me that I can essentially iterate um with lovable from here on out, which is yeah, it's exactly what we're gonna be doing.
00:34:37.800 --> 00:34:40.280
But point is I'm gonna copy and paste this.
00:34:40.440 --> 00:34:45.240
Um, what I would normally do actually is put this into like a doc.
00:34:45.559 --> 00:34:46.760
In fact, I may do that.
00:34:46.920 --> 00:34:53.559
So this is the document that I will be sharing with you, or that is shared in the links down below in the show notes.
00:34:53.639 --> 00:34:54.599
So go grab it.
00:34:54.760 --> 00:34:57.639
I'm going to add another tab.
00:34:57.960 --> 00:35:06.840
And this is where I'm going to put in the initial, the uh say first lovable prompt.
00:35:07.400 --> 00:35:07.960
Cool.
00:35:08.199 --> 00:35:13.000
And so you see, it does put a very clear prompt before you.
00:35:13.159 --> 00:35:31.480
This is if we were to just go lovable and start prompting like we did in Gemini, uh, we would be further behind because this is what it's actually, it's actually starting to predetermine what some of the requirements are for the data table and the back end essentially.
00:35:31.639 --> 00:35:39.159
So it's saying that you know you're gonna need a uh a poll table and options and votes and whatnot.
00:35:39.320 --> 00:35:45.880
But for the most part, you can directly attribute a lot of this back to you know the prompting and the questions that we got.
00:35:46.039 --> 00:35:48.440
Um, so just quick scan.
00:35:49.880 --> 00:35:55.880
I don't see anything crazy that we need to change.
00:35:55.960 --> 00:36:06.279
What I would do normally is go through this with a fine-tooth comb and just kind of add remove things just based on you know what the image in my head is of this thing.
00:36:06.440 --> 00:36:09.000
I'm not seeing anything crazy that we need to omit.
00:36:09.079 --> 00:36:12.279
And there's even some interesting choices here.
00:36:12.440 --> 00:36:15.719
For instance, ensure real-time changes feel magical.
00:36:15.880 --> 00:36:17.000
That's kind of cool.
00:36:17.159 --> 00:36:21.639
We'll see what magical uh we'll see what lovable thinks magical is.
00:36:21.799 --> 00:36:24.360
Uh, but we're just gonna run with this, right?
00:36:24.519 --> 00:36:31.239
We're just going to take all of this and we're gonna go over to lovable.
00:36:31.559 --> 00:36:33.559
This is what lovable looks like.
00:36:33.799 --> 00:36:39.880
Um, and I'm gonna just paste that prompt in there while we're talking.
00:36:40.199 --> 00:36:52.759
One thing to note is with lovable, you know, much like a lot of other um, you know, tools, you can uh, you know, predetermine certain connectors you want to use.
00:36:53.000 --> 00:36:57.480
This is where I could, you know, tell it some of my design choices as well.
00:36:57.639 --> 00:37:01.480
You can attach files, spreadsheets, whatever it may be.
00:37:01.719 --> 00:37:03.639
In this case, we're not doing any of that.
00:37:03.799 --> 00:37:09.000
Um, there is another interesting feature that lovable does have, which is this plan mode.
00:37:09.239 --> 00:37:19.400
What's cool about that is you can essentially plan the app a little bit with lovable before you actually vibe code the app.
00:37:19.719 --> 00:37:34.199
Again, this is this would be another thing that I would actually recommend you do, where you're going into plan mode, you're iterating on the plan a little bit before it actually builds it for you, so that then you know you're not iterating after it's already built it.
00:37:34.360 --> 00:37:41.480
In other words, you're iterating on it so that you're not spending a bunch of tokens iterating in real time on an already built app.
00:37:41.639 --> 00:37:44.679
In this case, we're just going for broke here, right?
00:37:44.759 --> 00:37:49.319
So I'm gonna hit submit on that, and we're gonna see what it comes back with.
00:37:49.480 --> 00:38:11.159
Now, one of the first things it's probably gonna ask me here is for permission for it to build the back end, um, which should be popping up right here, but um, you will start to be able to, as it initializes, you'll be able to start getting more details on what it is actually doing.
00:38:11.319 --> 00:38:14.839
And so, yep, just like we thought, enable cloud.
00:38:14.920 --> 00:38:24.759
This is essentially us giving permission to enable SuboBase to be set up on our behalf in the background.
00:38:25.000 --> 00:38:32.440
I don't have it set to just always allow just because I like that kind of control, but I've just allowed it to.
00:38:32.599 --> 00:38:42.279
And so now what it is doing is it is establishing the database and it is going to start writing this app before our very eyes.
00:38:42.839 --> 00:38:54.039
And once it gets a little bit further along, we're actually going to be able to get some details in terms of what is actually happening live.
00:38:55.319 --> 00:38:59.719
And so, yeah, you start to see those kinds of things populating.
00:39:00.119 --> 00:39:09.480
And so, you know, if you like watching this kind of thing, you can definitely get the details, or you know, you can close the details if you want to.
00:39:09.639 --> 00:39:14.279
Uh, this is asking me for some changes it needs to make to the database.
00:39:14.679 --> 00:39:18.119
This might get annoying if it asks me to do that a lot.
00:39:20.920 --> 00:39:24.839
Alright, so we're starting to see a little bit more detail populate here.
00:39:26.199 --> 00:39:31.239
And it basically just told me you're creating a very unsecure app, which is kind of true.
00:39:31.559 --> 00:39:40.759
So, yeah, it's starting to essentially create the back end, and you can see what it is writing and editing in real time.
00:39:41.719 --> 00:39:43.960
Okay, so um a couple things.
00:39:44.199 --> 00:39:51.880
This is about five minutes or so that this has taken me, and um, you'll see we are now seeing a live preview.
00:39:52.039 --> 00:39:59.799
It has described essentially what it has built, and uh the colors are kind of cool.
00:39:59.960 --> 00:40:03.880
I kind of like how it flipped at the primary and the secondary.
00:40:04.119 --> 00:40:06.519
Well, the secondary, I guess, used for a background, right?
00:40:06.679 --> 00:40:07.639
So cool.
00:40:07.799 --> 00:40:09.880
Um built the back end.
00:40:09.960 --> 00:40:14.360
It did have a quick issue, which it essentially fixed itself.
00:40:14.679 --> 00:40:21.159
But now we have a live kind of view of the app that I mean, okay, cool.
00:40:21.319 --> 00:40:22.839
It's a landing page.
00:40:22.920 --> 00:40:32.920
You can go to the host dashboard or you can go to the audience vote, which the colors on this little bit suspect, so we're gonna need to address that.
00:40:33.079 --> 00:40:38.759
Um, but if we go to the host dashboard, it's super simple, which is cool.
00:40:38.920 --> 00:40:40.759
What is your favorite color?
00:40:41.079 --> 00:40:45.239
We are going to select a single answer option.
00:40:45.400 --> 00:40:49.239
We're going to say red, yellow.
00:40:49.960 --> 00:40:53.319
We're going to add an option of blue.
00:40:54.279 --> 00:40:58.279
So now we're basically what we're doing here is we're just testing this thing.
00:40:58.519 --> 00:41:01.559
Um, and it created a question.
00:41:01.960 --> 00:41:13.559
Uh, and it is in draft, which I don't really know what that means, but I'm assuming that I can either trash it or I can go live with this question.
00:41:14.279 --> 00:41:15.880
Okay, the question is live.
00:41:16.039 --> 00:41:23.400
There is a QR code, and there is a link to go to that question.
00:41:23.639 --> 00:41:28.279
I will copy that link and I will paste it in this second tab.
00:41:28.839 --> 00:41:30.839
Okay, so there's my name.
00:41:31.000 --> 00:41:33.319
Uh, here's red, yellow, blue.
00:41:33.400 --> 00:41:39.159
We're gonna submit the vote, and now we're waiting for the next question.
00:41:39.719 --> 00:41:43.480
And I would assume that somewhere over here.
00:41:45.079 --> 00:41:46.440
So this hasn't come back yet.
00:41:46.519 --> 00:41:55.400
So look, I mean for a first iteration, this isn't bad.
00:41:55.559 --> 00:41:57.319
I don't know what I just did.
00:41:57.799 --> 00:42:00.440
I think I just got uh I don't know.
00:42:00.839 --> 00:42:05.000
It's closed for a first iteration, this isn't bad.
00:42:05.239 --> 00:42:19.559
Now, what I would do next is you know, as I'm kind of testing this, what I would be doing is essentially jotting some things down that aren't quite right.
00:42:19.960 --> 00:42:27.559
So, you know, the button on the front where it said audience, I think it was answer questions, something like that.
00:42:27.799 --> 00:42:29.880
Uh the colors were all weird here.
00:42:30.039 --> 00:42:37.239
Now, here I don't see any kind of ability to see answers.
00:42:37.799 --> 00:42:44.599
And maybe this is because we haven't published it yet, but um, and we can maybe publish it and see if that works.
00:42:44.759 --> 00:42:52.599
Now, publishing here, you can provide your own URL and things like that for for for you know these kind of instances.
00:42:52.759 --> 00:43:00.440
You know, I'll just use lovable's URL and we're gonna publish this public and see.
00:43:01.159 --> 00:43:04.839
Okay, we're just gonna publish this bad boy.
00:43:05.480 --> 00:43:07.239
And then maybe it'll work, right?
00:43:07.400 --> 00:43:15.239
So, you know, you can essentially do some testing, and then if you want to iterate on it, um, you're just gonna ask lovable.
00:43:15.400 --> 00:43:25.319
So um, you know, I would probably start with that button on the front page and say, hey, need to change the um the colors of that.
00:43:25.480 --> 00:43:38.679
Um, and then two, I would also say, you know, I don't see necessarily where I can view the different questions and the answers coming in and those kinds of things.
00:43:38.759 --> 00:43:42.360
Now we we've just published it, so we might test it out live here.
00:43:42.519 --> 00:43:44.759
I'm gonna go back to the host dashboard.
00:43:45.000 --> 00:43:46.199
What's your favorite color?
00:43:46.360 --> 00:43:47.319
Is closed.
00:43:47.639 --> 00:43:49.400
See, and I can't go back and edit it.
00:43:49.480 --> 00:43:51.000
So that might be an iteration.
00:43:51.159 --> 00:43:57.239
We say, hey, if a poll is closed, I'd like to be able to reopen it, for instance.
00:43:57.480 --> 00:44:09.319
Okay, so and you'll also notice that because we didn't don't have the live preview and the sidebar here, that the app is responsive and so it is kind of you know moving things around.
00:44:09.559 --> 00:44:14.360
We're gonna do um, I don't know, have you ever gone fishing?
00:44:15.880 --> 00:44:22.360
Single select, we're gonna do yes, no, create poll.
00:44:23.559 --> 00:44:26.519
Let's maybe create two of them.
00:44:27.000 --> 00:44:30.839
And maybe let's do a multiple choice and see what that looks like as well.
00:44:31.159 --> 00:44:36.839
Which of these is your favorite number?
00:44:37.400 --> 00:44:39.239
Three or four.
00:44:40.599 --> 00:44:41.400
Create poll.
00:44:41.480 --> 00:44:43.960
Okay, so now we have a couple more.
00:44:44.039 --> 00:44:48.279
Um, looks like we are going to launch one of these, perhaps.
00:44:48.920 --> 00:44:55.239
Okay, so it did update this page, which is super cool.
00:44:56.360 --> 00:44:59.480
Uh I'm gonna say yes and submit my vote.
00:44:59.719 --> 00:45:01.639
And then maybe, oh yeah, okay.
00:45:01.719 --> 00:45:07.319
So now because we published the app, it is basically seeing what's happening on the back end, right?
00:45:07.559 --> 00:45:14.679
And then if I go and I launch maybe the second one, it'll automatically close that first one.
00:45:14.759 --> 00:45:19.799
So the point I'm getting at here is that for a V1, this is a really great result.
00:45:20.039 --> 00:45:29.239
And you know, this is a somewhat complex app, but the point is you can build these things, and it's relatively simple.
00:45:29.400 --> 00:45:39.799
Now, what I would be doing next is going through taking note of you know what it is I need to fix and essentially having a conversation with Lovable to fix certain things.
00:45:39.960 --> 00:45:47.319
I would iterate upon it and I would keep iterating upon it until I get to the point where it is what I want it to be.
00:45:47.639 --> 00:45:50.839
You update the published version and you're good to go.
00:45:51.000 --> 00:45:52.199
So I'm gonna get out of screen share.
00:45:52.679 --> 00:45:55.960
Real quick, and then we'll wrap this episode up.
00:45:56.199 --> 00:46:07.960
When I first did this with the audience at the CS Summit in Austin, uh one of the things I did was I polled the audience in terms of their familiarity with vibe coding.
00:46:08.279 --> 00:46:17.880
And I was surprised to see that more than I'd say more than half the room didn't really know about vibe code coding.
00:46:18.039 --> 00:46:21.239
And I, you know, I guess that makes sense.
00:46:21.319 --> 00:46:23.319
It's it's a relatively new thing, right?
00:46:23.559 --> 00:46:33.559
And um, it's not necessarily mainstream, but it is incredibly powerful and it is the way that software is going.
00:46:33.719 --> 00:46:37.719
Whether you're a developer or you're not a developer, it's a thing.
00:46:38.039 --> 00:46:39.880
And it's a powerful thing.
00:46:40.119 --> 00:46:47.079
And so my goal for today is for those of you who are vibe coding, kudos to you.
00:46:47.159 --> 00:46:47.880
That's awesome.
00:46:47.960 --> 00:46:48.599
That's great.
00:46:48.759 --> 00:46:52.199
I would love to hear about the projects that you're working on.
00:46:52.519 --> 00:47:02.920
For those that aren't vibe coding, hopefully this kind of demystified it a little bit and maybe gave you the impetus to go try it out yourself.
00:47:03.159 --> 00:47:07.400
Now, here's a couple of caveats that I'm going to give you, and then we'll say goodbye.
00:47:07.559 --> 00:47:24.199
First off, you're not going to want to do this right now with sensitive information, customer information, company information, unless you are a thousand percent certain that the environment you're doing it in is a secure environment, right?
00:47:24.360 --> 00:47:51.960
Please don't go and create a bunch of like uh, you know, calculators or and things that ingest, you know, data in from your CRM and those kinds of things without really knowing what you're doing and without putting some guardrails around these systems because the chances of exposing that information elsewhere are pretty high if you don't know what you're doing.
00:47:52.199 --> 00:48:01.000
Second is we didn't really talk about integrations and things like that, but you can build these things in such a way to where they can integrate with all of your data, right?
00:48:01.159 --> 00:48:08.119
And so again, you're gonna want to do that in an enclosed environment and in a safe environment where that data is being transferred.
00:48:08.279 --> 00:48:17.079
Third, and kind of relating to all of that, a lot of you operate in a corporate environment that is incredibly locked down.
00:48:17.880 --> 00:48:20.279
I mean, that's the truth of it.
00:48:20.519 --> 00:48:25.559
Um, some of you are operating in like a startup and it's a little bit more free, and you can do these kinds of things.
00:48:25.799 --> 00:48:29.159
So, uh a couple of um words of advice here.
00:48:29.400 --> 00:48:31.559
First off, build tools.
00:48:31.799 --> 00:48:39.880
Um, one of my CSMs built a renewal calculator using an existing spreadsheet we were using, we just you know turn it into a web app.
00:48:39.960 --> 00:48:48.679
The inputs are manual, the inputs are not anything like identifiable from a personal information standpoint.
00:48:48.839 --> 00:48:59.000
It is literally a tool that outputs things way quicker than you know, actually manually typing things or grabbing screenshots and whatnot.
00:48:59.239 --> 00:49:14.199
So the the point is build tools, build tools that aren't reliant on your data and go into your day and your week analyzing those opportunities where you can potentially build some efficiency in your day by just vibe coding a tool.
00:49:14.920 --> 00:49:17.960
Second, do this for your own personal life.
00:49:18.039 --> 00:49:30.279
Like if there's something that you're passionate about, if you're passionate about gardening, for instance, and you're doing seedlings, you can build a vibe coding app that helps you keep track of where your seedlings are on the trays as they you know sprout.
00:49:30.440 --> 00:49:35.880
Like, I mean, go nuts because you can you can do this stuff now.
00:49:36.039 --> 00:49:42.599
You can make these apps that are um that are personal to you and that work like you want them to.
00:49:43.319 --> 00:49:48.920
Third thing I will tell you is have fun with this.
00:49:49.159 --> 00:49:50.759
It's it is super fun.
00:49:51.319 --> 00:49:53.319
Play with it, get to know with it.
00:49:53.400 --> 00:49:57.159
You don't have to solve a massive problem, you don't have to build a great tool.
00:49:57.239 --> 00:50:01.480
You just need to know that this exists and how to go about doing it.
00:50:01.799 --> 00:50:13.880
Because this is going to be one of those durable skills that you need to have in your tool belt in order to really stay ahead of the curve and stay relevant.
00:50:13.960 --> 00:50:16.199
And again, you don't need to be an expert here.
00:50:16.440 --> 00:50:24.920
You just need to know what the deal is so that you can have intelligent conversations about it and you can suggest, hey, maybe we should vibe code something like this.
00:50:25.079 --> 00:50:28.039
So look, I hope this has been helpful.
00:50:28.199 --> 00:50:43.639
Um and I hope it didn't scare anyone, and I hope it um brought you some excitement about what the possibilities are because it literally, you can literally make anything you want these days for the most part.
00:50:43.799 --> 00:50:44.839
So I'll leave you with that.
00:50:45.000 --> 00:50:46.199
Let me know if you have any questions.
00:50:46.360 --> 00:50:47.400
I'd love to hear from you.
00:50:47.559 --> 00:50:50.039
If you're doing this stuff, what are you doing?
00:50:50.360 --> 00:50:55.960
And um we'll do more of this on future episodes, maybe in different little ways.
00:50:56.199 --> 00:50:57.799
I hope you have a great rest of your week.
00:50:57.960 --> 00:50:59.000
We'll talk to you soon.
00:50:59.319 --> 00:51:02.759
Thank you for joining me for this episode of the Digital CX Podcast.
00:51:02.920 --> 00:51:07.960
If you like what we're doing, uh consider leaving us a review on your podcast platform of choice.
00:51:08.119 --> 00:51:10.440
If you're watching on YouTube, leave a comment down below.
00:51:10.519 --> 00:51:21.159
It really helps us to grow and provide value to a broader audience and get more information about the show and some of the other things that we're doing at digitalcustomersuccess.com.
00:51:21.319 --> 00:51:22.519
I'm Alex Drogovic.
00:51:22.679 --> 00:51:25.079
Thanks so much for listening, and we'll talk to you next week.