4 Questions Before You Vibe Code a Tool Replacement
Should you replace your software subscriptions with tools you vibe code? I’ve replaced several of mine, but I’ll never replace others. Here’s how I decide, using four questions: skill, expertise, tools, and the one that matters most, dependency.
Want help figuring out what to replace and building it to last? Join the waitlist for my upcoming cohort on how to vibe code your own tools: streamlined.fm/waitlist
- (00:00) – Intro
- (01:07) – DIY vs. Paying for Software
- (06:47) – 4 Criteria for Making the Decision
- (12:57) – Analyzing Examples Against the Criteria
- (16:48) – Next Steps
————
Streamlined Solopreneur helps overwhelmed solo business owners go from overwhelmed to having their time back.
Each week, Joe Casabona shares one practical idea — a system, tool, or strategy to help you get your time back without selling your soul to AI…and run your business without sacrificing the rest of your life, or your health.
Looking for a place to start? Take the Solo Systems Starter Quiz. 60 seconds, 8 questions, and I will tell you what system you should build first, and exactly how to build it. https://streamlined.fm/quiz
Connect with Joe on LinkedIn: https://www.linkedin.com/in/jcasabona/
Transcript
00:00:00,000 –> 00:00:05,940
Last year we needed to have a new fence built. Ours was falling apart and we had
2
00:00:05,940 –> 00:00:11,340
a new puppy who would easily get out. So we had a few options.
3
00:00:11,850 –> 00:00:17,400
Do nothing. That's always an option. Even if it's not a good one, hire somebody to
4
00:00:17,400 –> 00:00:21,480
do it for us at great costs, like $10,000
5
00:00:21,990 –> 00:00:27,900
or do it ourselves for $2,000 plus one weekend.
6
00:00:28,650 –> 00:00:34,860
Option three also required skill expertise and the right tools, which I don't have,
7
00:00:35,880 –> 00:00:39,150
but luckily my father-in-law and brother-in-law do.
8
00:00:39,960 –> 00:00:42,750
So we opted to build it ourselves.
9
00:00:43,650 –> 00:00:49,560
Now we faced a similar choice a couple of years prior when we had to replace our
10
00:00:49,830 –> 00:00:50,310
hvac.
11
00:00:51,030 –> 00:00:53,370
Except here we couldn't do nothing
12
00:00:54,180 –> 00:00:57,690
and we didn't have the skills, expertise,
13
00:00:58,200 –> 00:01:02,580
tools or access to the raw material.
14
00:01:03,600 –> 00:01:06,600
We had to hire somebody to replace it for us.
15
00:01:07,860 –> 00:01:12,540
Now I just got back from EEC Cam's creator camp where one of the biggest topics of
16
00:01:12,540 –> 00:01:15,630
discussion was the very idea
17
00:01:16,320 –> 00:01:17,250
around
18
00:01:17,760 –> 00:01:21,840
DIY versus paying for a tool but for software.
19
00:01:22,620 –> 00:01:28,740
And that's what I want to talk about today. Hey everybody and welcome to another
20
00:01:28,740 –> 00:01:33,150
episode of the Streamlined Solopreneur. My name's Joe Casabona and today I want to
21
00:01:33,150 –> 00:01:33,840
talk about
22
00:01:34,680 –> 00:01:37,770
when to vibe code, your own tool
23
00:01:38,460 –> 00:01:41,190
and when to actually pay for the software.
24
00:01:42,120 –> 00:01:49,800
So what is the major question that came up at ecam M's Creator camp and really what's
25
00:01:49,800 –> 00:01:51,810
been coming up a lot lately,
26
00:01:52,830 –> 00:01:53,580
it's this
27
00:01:54,120 –> 00:01:57,870
now that AI can write reliable software for us,
28
00:01:58,620 –> 00:02:04,950
should we replace our software subscriptions With tools we've vibe coded,
29
00:02:05,183 –> 00:02:09,890
it's easy to think. The answer is almost always yes.
30
00:02:10,490 –> 00:02:14,960
The temptation of replacing our tools
31
00:02:15,830 –> 00:02:19,460
or our monthly subscriptions is really good.
32
00:02:20,030 –> 00:02:22,730
I would love to not have to pay
33
00:02:23,330 –> 00:02:26,630
thousands of dollars a year for software.
34
00:02:27,650 –> 00:02:32,360
And to be honest, I have been vibe coding
35
00:02:32,930 –> 00:02:35,930
a lot more of my own tools lately.
36
00:02:36,530 –> 00:02:38,330
Here are a couple of examples.
37
00:02:39,050 –> 00:02:43,550
I coded a replacement stream deck plugin for Apple Music
38
00:02:44,060 –> 00:02:46,820
because El Gado removed theirs.
39
00:02:47,630 –> 00:02:54,330
I even made some improvements to it like adding playlist button support and dial
40
00:02:54,330 –> 00:02:55,860
support for the stream deck. Plus
41
00:02:56,820 –> 00:03:00,420
I also deleted El Dodos camera hub app
42
00:03:00,960 –> 00:03:07,800
and created my own teleprompter app. I am using that right now. It's so much better.
43
00:03:08,490 –> 00:03:13,410
Elga O'S Camera hub app was supposed to have this thing called voice sync where the
44
00:03:13,410 –> 00:03:19,380
teleprompter would move based on what you were saying and it did not work even remotely
45
00:03:19,380 –> 00:03:20,190
reliably.
46
00:03:20,760 –> 00:03:26,250
And the tool I am using does work reliably. In fact, I am
47
00:03:26,970 –> 00:03:29,820
ad-libbing off the script right now and
48
00:03:30,540 –> 00:03:33,240
the app is telling me, are you ad-libbing?
49
00:03:34,230 –> 00:03:34,830
So
50
00:03:35,700 –> 00:03:37,800
I coded this with Claude
51
00:03:38,460 –> 00:03:40,560
in a half hour.
52
00:03:42,270 –> 00:03:45,240
The biggest projects I've replaced are web-based.
53
00:03:45,930 –> 00:03:50,010
I replaced Seja with my own testimonials collector
54
00:03:50,700 –> 00:03:54,540
and I built my own beta reader software.
55
00:03:55,440 –> 00:04:01,080
I did this because honestly with Seja I wasn't collecting enough testimonials to
56
00:04:01,080 –> 00:04:02,520
really justify
57
00:04:03,030 –> 00:04:04,620
the $30 a month
58
00:04:05,160 –> 00:04:08,850
and nobody was using the Submit a video testimonial.
59
00:04:09,480 –> 00:04:13,980
I know that some companies like Ecamm use it for customer research and for a lot
60
00:04:13,980 –> 00:04:18,750
of other things or a lot of people get a lot of video testimonials. And if I were
61
00:04:18,750 –> 00:04:19,530
in that boat,
62
00:04:20,100 –> 00:04:21,900
maybe I would keep paying for Senda.
63
00:04:23,160 –> 00:04:24,510
But $30
64
00:04:24,510 –> 00:04:29,730
a month is a little much for the one to two text-based testimonials I get
65
00:04:30,780 –> 00:04:34,950
and the beta reader software, like I don't even know if people are gonna beta read
66
00:04:34,950 –> 00:04:35,700
my book.
67
00:04:35,700 –> 00:04:38,730
And so it didn't make a lot of sense for me to
68
00:04:38,730 –> 00:04:40,410
start paying for this software.
69
00:04:40,950 –> 00:04:45,270
And it could be the case that once I get users into this Beta Rita software, once
70
00:04:45,270 –> 00:04:46,440
I start writing my book,
71
00:04:47,910 –> 00:04:49,950
I might want to pay for the software.
72
00:04:50,610 –> 00:04:52,110
But I didn't at this moment.
73
00:04:52,920 –> 00:04:58,290
But like I said, the temptation to replace every subscription with software we need
74
00:04:58,290 –> 00:04:59,100
to support
75
00:04:59,100 –> 00:05:01,020
shouldn't blind us to the fact
76
00:05:01,530 –> 00:05:04,320
that there are some things we shouldn't replace.
77
00:05:04,320 –> 00:05:09,120
It's really nice to think there's a world where, oh, I will just pay a hundred bucks
78
00:05:09,120 –> 00:05:11,880
a month for Claude and five bucks a month for lovable
79
00:05:12,720 –> 00:05:15,990
and I will replace thousands of dollars of software.
80
00:05:16,710 –> 00:05:19,230
But that's not
81
00:05:19,800 –> 00:05:20,460
tenable.
82
00:05:21,150 –> 00:05:24,990
I'm not gonna say it's not possible and I'll talk about why in a minute. But it's
83
00:05:24,990 –> 00:05:26,520
not tenable. For example,
84
00:05:27,240 –> 00:05:30,600
I will likely never replace
85
00:05:31,560 –> 00:05:34,020
Kit which sends my emails.
86
00:05:34,920 –> 00:05:37,710
I don't want to deal with deliverability.
87
00:05:38,340 –> 00:05:44,860
I don't want to deal with checking automations or managing payments for subscriptions
88
00:05:45,250 –> 00:05:47,020
or spam
89
00:05:47,187 –> 00:05:48,040
Ecamm,
90
00:05:48,730 –> 00:05:51,490
which is my recording and live streaming software.
91
00:05:52,240 –> 00:05:58,750
I don't want to have to deal with concurrent streams and massive overlays and managing
92
00:05:58,750 –> 00:06:03,340
resources and reliably recording files.
93
00:06:04,510 –> 00:06:12,850
Do I trust myself to vibe code something with AI that will reliably record and save
94
00:06:13,420 –> 00:06:16,240
isolated versions of all of my files? I don't.
95
00:06:16,960 –> 00:06:18,340
And the guys at Ecamm
96
00:06:19,090 –> 00:06:22,210
know this stuff really well. They've been doing it for a long time.
97
00:06:23,380 –> 00:06:27,310
And finally, my podcast hosts rss.com and transistor,
98
00:06:27,940 –> 00:06:33,070
I will not replace them because again, I'm serving up audio files or video files.
99
00:06:33,070 –> 00:06:33,400
Now
100
00:06:34,240 –> 00:06:40,150
I am doing the analytics and trying to account for spam. These are just things that
101
00:06:41,080 –> 00:06:41,320
the
102
00:06:41,320 –> 00:06:42,730
three companies that are
103
00:06:42,730 –> 00:06:47,170
the four companies that I just named have a lot of expertise in this.
104
00:06:47,830 –> 00:06:50,890
And so now we get to the crux of the matter.
105
00:06:51,580 –> 00:06:56,800
How do you decide if you should replace software you pay for
106
00:06:57,700 –> 00:07:00,310
with something you have vibe coded?
107
00:07:00,610 –> 00:07:04,024
And it comes down to those things I mentioned earlier, skill,
108
00:07:04,834 –> 00:07:07,264
expertise and the right tools
109
00:07:08,224 –> 00:07:10,534
as well as your dependency
110
00:07:11,044 –> 00:07:12,274
on the software.
111
00:07:12,274 –> 00:07:13,637
So with defense,
112
00:07:14,477 –> 00:07:18,797
and not at all with the hvac but with the fence, we had the skill
113
00:07:19,517 –> 00:07:23,777
being able to build anything, use tools properly like, like
114
00:07:24,617 –> 00:07:25,517
carpentry tools.
115
00:07:26,237 –> 00:07:31,037
We had the expertise knowing how to build a reliable fence. This was something my
116
00:07:31,037 –> 00:07:33,647
brother-in-law apparently has a lot of experience in.
117
00:07:34,547 –> 00:07:40,427
And we had the tools, namely in Auger, which allowed us to sink the posts without
118
00:07:40,427 –> 00:07:44,237
having to manually dig three foot holes.
119
00:07:44,237 –> 00:07:47,470
But in this case, we could also do nothing.
120
00:07:48,490 –> 00:07:51,970
That is, we didn't have complete dependency on the fence.
121
00:07:52,780 –> 00:07:55,930
We could take the dog out and put him on a leash.
122
00:07:55,930 –> 00:08:01,890
When it comes to our hvac, like I said, we didn't have the skills, the expertise
123
00:08:02,580 –> 00:08:03,390
or the tools,
124
00:08:04,320 –> 00:08:07,200
but we also have dependency
125
00:08:07,710 –> 00:08:08,940
on our hvac,
126
00:08:09,750 –> 00:08:10,740
especially
127
00:08:11,310 –> 00:08:15,900
in the bitterly cold winters we have here in the Northeast.
128
00:08:16,167 –> 00:08:18,927
So doing nothing was not an option for us.
129
00:08:19,557 –> 00:08:25,797
We didn't have any of the skills, expertise, or tools to replace the HVAC ourself.
130
00:08:26,577 –> 00:08:27,117
And so we
131
00:08:27,140 –> 00:08:28,867
decided, well, we didn't.
132
00:08:28,867 –> 00:08:33,457
It was decided for us, right? We had to pay somebody to replace our hvac.
133
00:08:33,590 –> 00:08:36,370
But let's move away from the home examples.
134
00:08:37,030 –> 00:08:39,190
What does this look like in software?
135
00:08:40,000 –> 00:08:43,210
Let's break it down one by one. Number one skill.
136
00:08:44,230 –> 00:08:46,120
Do you have this skill
137
00:08:46,840 –> 00:08:49,870
to do this? You don't need to write code anymore.
138
00:08:50,530 –> 00:08:57,160
This is true, but you still need to understand software security and maintenance.
139
00:08:58,030 –> 00:09:02,290
You can't just launch a tool into the ether, possibly one that,
140
00:09:02,860 –> 00:09:05,710
has usernames and passwords or your own data
141
00:09:06,250 –> 00:09:08,230
and just trust it's going to work.
142
00:09:09,370 –> 00:09:13,600
You still need to at least ask the right questions or know the audits
143
00:09:14,200 –> 00:09:19,060
to do the security. And you need to know what to do if things break,
144
00:09:19,750 –> 00:09:23,680
right? If you make an iOS app or an iPad app
145
00:09:24,850 –> 00:09:29,320
and then the next version of iOS comes out and your app breaks,
146
00:09:29,950 –> 00:09:32,380
you need to be confident
147
00:09:33,130 –> 00:09:34,750
that you can fix it
148
00:09:35,740 –> 00:09:37,210
or the AI can fix it
149
00:09:38,050 –> 00:09:41,980
or that you can just stop using it. So that's the skill part.
150
00:09:43,090 –> 00:09:48,040
Number two is expertise. You need to know enough about the problem and how to solve
151
00:09:48,040 –> 00:09:50,440
it to build a solution for it.
152
00:09:51,550 –> 00:09:53,770
I think we've seen time and time again, right?
153
00:09:54,280 –> 00:09:55,720
Vague prompts
154
00:09:56,710 –> 00:09:57,700
lead to
155
00:09:58,300 –> 00:10:01,570
incomplete or inaccurate responses.
156
00:10:02,980 –> 00:10:06,940
The first thing I do when I create new software
157
00:10:07,720 –> 00:10:09,310
is create the spec.
158
00:10:09,410 –> 00:10:13,610
And I use that using one of the quote unquote smarter models.
159
00:10:15,050 –> 00:10:19,040
And then I will feed that to Claude Code after reviewing everything and going through
160
00:10:19,040 –> 00:10:20,240
and make sure it touches
161
00:10:20,750 –> 00:10:22,040
everything I needed to touch.
162
00:10:23,330 –> 00:10:26,240
But if you're just like, Hey, I need a way to send emails,
163
00:10:26,990 –> 00:10:29,180
right? I wanna replace Kit, I want a way to send emails.
164
00:10:29,810 –> 00:10:33,260
There's gonna be a lot of stuff that the large language model will not be able to
165
00:10:33,260 –> 00:10:35,570
help you with. In fact, when I replaced Seja,
166
00:10:36,140 –> 00:10:37,190
it's straight up said,
167
00:10:37,790 –> 00:10:41,330
Hey, do you want the video part? 'cause that's gonna be super hard.
168
00:10:41,497 –> 00:10:44,955
So you need the expertise. And I had the expertise to know
169
00:10:45,915 –> 00:10:47,475
I'm not gonna want the videos.
170
00:10:48,315 –> 00:10:50,145
All right, number three tools.
171
00:10:50,745 –> 00:10:54,525
The tools to actually deploy the software are much easier to use now,
172
00:10:55,155 –> 00:11:02,605
but do you know how to use those tools? Do you know how to use Netlify or Versal
173
00:11:02,605 –> 00:11:04,345
and Superb Base or
174
00:11:04,345 –> 00:11:10,105
CloudFlare, there's a lot of free options now. And knowing which one to use is important
175
00:11:10,975 –> 00:11:11,695
because
176
00:11:12,535 –> 00:11:17,365
for example, I just replaced my personal website, casabona.org. It was a WordPress
177
00:11:17,365 –> 00:11:18,895
site, now it's a flat file site.
178
00:11:19,495 –> 00:11:20,995
I'm hosting it on Netlify,
179
00:11:21,715 –> 00:11:25,885
which means that every time I write a blog post I have to deploy and it uses 15 credits.
180
00:11:27,475 –> 00:11:31,825
If I was writing multiple blog posts a day,
181
00:11:32,275 –> 00:11:34,555
I would've made an incredible mistake
182
00:11:35,485 –> 00:11:35,665
and
183
00:11:35,665 –> 00:11:36,775
I probably
184
00:11:36,775 –> 00:11:38,665
should have kept paying
185
00:11:39,265 –> 00:11:43,975
for my WordPress host or move to a different thing like Ghost if I was sick of WordPress.
186
00:11:45,445 –> 00:11:47,065
So that's something you need to understand.
187
00:11:47,635 –> 00:11:50,575
And then number four, perhaps the most important question, right?
188
00:11:51,085 –> 00:11:54,775
Because the first three, like maybe they're not insurmountable. Maybe AI can help
189
00:11:54,775 –> 00:11:59,245
you quote unquote, or maybe you have friends who have expertise in this area, but
190
00:11:59,245 –> 00:12:00,325
dependency.
191
00:12:01,585 –> 00:12:06,295
If the software stopped working and you didn't know how to fix it,
192
00:12:07,135 –> 00:12:11,155
how would that impact your business?
193
00:12:12,235 –> 00:12:12,835
I was quote,
194
00:12:12,835 –> 00:12:14,305
coding an iOS app
195
00:12:14,815 –> 00:12:18,805
back in March and I really wanted this feature and I thought it would be neat.
196
00:12:19,315 –> 00:12:19,945
And
197
00:12:20,545 –> 00:12:23,785
that version of Open AI's Codex
198
00:12:24,835 –> 00:12:25,795
couldn't get it right.
199
00:12:25,795 –> 00:12:28,165
it's fixed. It wasn't fixed, it's fixed. It wasn't fixed.
200
00:12:28,915 –> 00:12:32,275
And then it told me how to fix it. And I had no idea. I have never programmed
201
00:12:33,115 –> 00:12:35,335
with Swift. I had never written an iOS app before
202
00:12:36,055 –> 00:12:39,325
and luckily I had the skill and expertise
203
00:12:39,835 –> 00:12:41,515
to make feature branches
204
00:12:42,805 –> 00:12:43,705
so that
205
00:12:44,515 –> 00:12:47,695
if something went awry, it didn't kill the whole app,
206
00:12:48,955 –> 00:12:50,965
but it also wasn't a required feature.
207
00:12:51,985 –> 00:12:56,005
So that's the dependency thing. So let's look at my examples again.
208
00:12:57,355 –> 00:13:00,715
First, let's do the stream deck plugin and the teleprompter app.
209
00:13:01,885 –> 00:13:03,865
I have the skill
210
00:13:04,705 –> 00:13:06,415
expertise and tools
211
00:13:07,675 –> 00:13:10,945
and I have zero dependency on these.
212
00:13:12,595 –> 00:13:17,635
If they disappeared tomorrow, I'd be mildly inconvenienced.
213
00:13:18,865 –> 00:13:22,435
So I was very comfortable vibe coding them,
214
00:13:22,602 –> 00:13:23,412
if my
215
00:13:23,746 –> 00:13:27,496
stream deck plugin stopped working, I could go pay $8 for one.
216
00:13:28,246 –> 00:13:30,406
It maybe wouldn't do everything I wanted to do.
217
00:13:31,696 –> 00:13:35,806
But also I have the media keys on my keyboard, like that's not the only way I can
218
00:13:35,806 –> 00:13:38,986
control Apple music. Same thing with the teleprompter. There's a lot of teleprompter
219
00:13:38,986 –> 00:13:43,336
apps. I vibe coded this one 'cause there are some very specific features I wanted
220
00:13:44,116 –> 00:13:47,296
and I have them now and it's working great, like unbelievably great,
221
00:13:47,529 –> 00:13:48,856
but I have zero dependency.
222
00:13:49,696 –> 00:13:53,536
Okay, number two, send your replacement. And the beta reader software,
223
00:13:54,136 –> 00:13:56,326
beta reader software man,
224
00:13:57,856 –> 00:14:01,576
that really does a number on my accent. I try to keep my New York accent on a low
225
00:14:01,576 –> 00:14:03,946
burn, but beta reader software really kills me.
226
00:14:04,486 –> 00:14:07,846
Okay? I have the skill, I have some expertise
227
00:14:08,716 –> 00:14:10,006
and I have most of the tools.
228
00:14:10,606 –> 00:14:15,916
So I felt very comfortable doing this. And again, virtually no dependency on these.
229
00:14:17,026 –> 00:14:19,066
Would I be inconvenienced if
230
00:14:19,066 –> 00:14:23,476
my Senda replacement went away? Yes, I'd have to update
231
00:14:23,986 –> 00:14:26,896
a bunch of embeds across my websites
232
00:14:27,586 –> 00:14:28,876
and that would be annoying,
233
00:14:29,926 –> 00:14:31,996
but I would spin up a Google form
234
00:14:32,836 –> 00:14:34,636
to keep collecting testimonials
235
00:14:35,536 –> 00:14:37,546
and the beta reader software. Forget about it. Like
236
00:14:38,416 –> 00:14:39,706
I'm not even using that right now.
237
00:14:40,786 –> 00:14:42,286
Okay, so those are the things
238
00:14:42,286 –> 00:14:44,386
I've coded. Now let's look at Kit
239
00:14:45,076 –> 00:14:46,906
EAM and podcast hosting.
240
00:14:48,046 –> 00:14:52,966
I do not have this skill for these types of software,
241
00:14:53,506 –> 00:14:55,816
nor do I have the expertise.
242
00:14:56,866 –> 00:14:57,496
Things like deliverability
243
00:14:59,116 –> 00:15:01,006
or concurrent streaming,
244
00:15:01,576 –> 00:15:04,426
file storage, spam management,
245
00:15:04,996 –> 00:15:07,336
server management.
246
00:15:08,446 –> 00:15:14,686
There's a lot of things that can go wrong with all of these, which is why I trust
247
00:15:15,166 –> 00:15:15,586
Kit
248
00:15:16,186 –> 00:15:18,796
ecamm rss.com and transistor.
249
00:15:20,086 –> 00:15:21,916
I have some of the tools.
250
00:15:22,516 –> 00:15:24,316
I know how software works
251
00:15:25,216 –> 00:15:31,456
and so I know enough to know that I don't have all of the skills and tools and expertise.
252
00:15:31,689 –> 00:15:34,762
But that leads me to number four. I have deep
253
00:15:35,422 –> 00:15:41,902
dependency on all of these things. I am using Ecamm right now to record. I sent an
254
00:15:41,902 –> 00:15:48,862
email with Kit this morning. Both of my podcasts go out later this week and I know
255
00:15:48,862 –> 00:15:50,812
they will reliably do so.
256
00:15:51,682 –> 00:15:54,172
If they went away tomorrow,
257
00:15:54,922 –> 00:15:55,972
I'd be screwed.
258
00:15:56,932 –> 00:15:59,902
Yes, I could find a kit replacement.
259
00:16:00,412 –> 00:16:06,202
Yes, I could find a podcast host replacement. I honestly don't believe I would find
260
00:16:06,202 –> 00:16:11,019
a good enough Ecamm replacement. Like yes, OBS exists, but
261
00:16:11,019 –> 00:16:13,809
I would be really left in the lurch,
262
00:16:14,319 –> 00:16:16,959
which is why I happily pay for all of those things.
263
00:16:17,499 –> 00:16:19,779
I guess disclosure, here I am,
264
00:16:19,779 –> 00:16:24,819
a content creator and evangelist for rss.com. And so I do get that account for free,
265
00:16:24,849 –> 00:16:26,949
but I host actual podcasts over there.
266
00:16:27,082 –> 00:16:28,087
Now. I
267
00:16:29,342 –> 00:16:30,092
suspect
268
00:16:30,692 –> 00:16:32,412
I'm at a slight advantage here
269
00:16:32,922 –> 00:16:35,742
because I have software development expertise,
270
00:16:36,312 –> 00:16:39,222
I have a master's degree in software engineering.
271
00:16:40,392 –> 00:16:43,962
Maybe some would say because of that I have the burden of knowledge
272
00:16:45,162 –> 00:16:47,862
and maybe just go out there and try stuff and see what happens.
273
00:16:48,972 –> 00:16:52,452
These decisions are going to be different for you.
274
00:16:53,472 –> 00:16:58,062
Maybe you don't have the dependency I have on kit until you could try creating your
275
00:16:58,062 –> 00:17:01,032
own ESP, though I really wouldn't recommend that.
276
00:17:02,742 –> 00:17:06,077
It's up to you to evaluate if you want to spend time
277
00:17:06,657 –> 00:17:12,732
coding something, testing it, deploying it, and most importantly
278
00:17:13,422 –> 00:17:14,562
supporting it.
279
00:17:14,662 –> 00:17:15,246
That's
280
00:17:15,246 –> 00:17:15,966
the big one.
281
00:17:16,686 –> 00:17:20,916
Because yeah, you might launch something and it works great today,
282
00:17:22,026 –> 00:17:23,736
but what happens
283
00:17:24,936 –> 00:17:28,086
a month from now, two months from now, six months from now
284
00:17:28,776 –> 00:17:32,316
where something goes wrong and you don't know how to fix it.
285
00:17:33,396 –> 00:17:36,636
Again, I know the temptation is great,
286
00:17:36,836 –> 00:17:39,481
having the discernment to know when you should
287
00:17:40,151 –> 00:17:41,516
code a replacement
288
00:17:42,476 –> 00:17:44,426
or keep paying for something
289
00:17:44,996 –> 00:17:47,156
that is well supported and reliable
290
00:17:48,176 –> 00:17:49,076
is important.
291
00:17:49,142 –> 00:17:52,569
if you need help with this or if you've been wondering
292
00:17:53,109 –> 00:17:57,519
how you should approach using AI to write or replace software for you,
293
00:17:58,209 –> 00:18:04,179
I am cooking up something special. It's a cohort and course where I will walk you
294
00:18:04,179 –> 00:18:09,069
through how to figure out what to replace and how to use AI to replace it
295
00:18:09,669 –> 00:18:10,239
and
296
00:18:10,899 –> 00:18:14,739
how to make sure it turns into a long-term solution for you.
297
00:18:15,579 –> 00:18:20,379
We'll have an example project to walk through before you start building your own.
298
00:18:20,649 –> 00:18:26,439
And that's really my goal For the end of this cohort. You will have a tool that you
299
00:18:26,439 –> 00:18:33,219
have fully replaced with your own version. Thanks to Vibe Coding with ai, this is
300
00:18:33,219 –> 00:18:38,049
something I have saved literally thousands of dollars on. I've replaced websites
301
00:18:38,049 –> 00:18:41,469
where I was paying a ton for hosting. I've replaced tools with high monthly subscriptions
302
00:18:41,636 –> 00:18:45,792
what I've done for myself is to replace the tools
303
00:18:46,602 –> 00:18:47,202
that
304
00:18:47,772 –> 00:18:53,412
I know I won't need in six months if they go away, or the tools that I don't have
305
00:18:53,412 –> 00:18:55,812
heavy dependency on. 'cause I don't want you to switch
306
00:18:56,442 –> 00:18:56,652
and
307
00:18:56,652 –> 00:19:01,482
then end up having to switch back. So I will be with you every step of the way to
308
00:19:01,482 –> 00:19:01,992
help you.
309
00:19:02,532 –> 00:19:07,542
If you're interested, you can head over to streamlined fm slash waitlist, scan the
310
00:19:07,542 –> 00:19:10,272
QR code to join the wait list
311
00:19:11,472 –> 00:19:16,392
and you'll be the first to be notified when presale opens. There will be a special
312
00:19:16,722 –> 00:19:20,262
presale price. Again, that is streamlined
313
00:19:20,772 –> 00:19:23,142
fm slash waitlist.
314
00:19:23,142 –> 00:19:28,602
So that's it for this episode of the streamlined solopreneur. In it, we went over
315
00:19:28,662 –> 00:19:31,812
the basically four criteria to figure out
316
00:19:32,412 –> 00:19:37,842
if you should look into vibe, coding, a replacement, or just pay for the tool. I
317
00:19:37,842 –> 00:19:44,952
am a big proponent of paying for software that's worth paying for. I pay for convenience
318
00:19:45,402 –> 00:19:46,272
all the time
319
00:19:47,232 –> 00:19:48,852
and I pay for expertise.
320
00:19:49,782 –> 00:19:50,532
But
321
00:19:51,342 –> 00:19:56,202
if there's a tool that you can reliably replace to save yourself some extra money
322
00:19:56,202 –> 00:19:59,022
or simplify your tech stack,
323
00:20:00,492 –> 00:20:02,442
I think that's really worth looking into.
324
00:20:02,509 –> 00:20:07,876
So let me know over@streamlinedfeedback.com. Have you vibe coded your own tool? Are
325
00:20:07,876 –> 00:20:10,906
you worried about it? You can send me a voice note. I'll play it on the show. But
326
00:20:10,906 –> 00:20:14,866
But that's it for this episode of the Streamlined solopreneur. Thanks so much for
327
00:20:14,866 –> 00:20:19,546
listening and until next time, I hope you find some space in your week.


