Shownotes
Help us become the #1 Data Podcast by leaving a rating & review! We are 67 reviews away!
Is AI replacing data analysts? Here's my honest answer after testing an actual project.
💌 Join 33k+ aspiring data analysts & get my tips in your inbox weekly 👉 https://datacareerjumpstart.com/newsletter
🆘 Feeling stuck in your data journey? Come to my next free "How to Land Your First Data Job" training 👉 https://datacareerjumpstart.com/training
👩💻 Want to land a data job in less than 90 days? 👉 https://datacareerjumpstart.com/daa
👔 Ace The Interview with Confidence 👉 https://datacareerjumpstart.com/interviewsimulator
⌚ TIMESTAMPS
00:24 – What I gave Claude
06:00 – What it came up with
07:24 – First analysis results
19:33 – Building the dashboard
35:50 – Should you be worried?
🔗 CONNECT WITH AVERY
🎵 TikTok
💻 Website
Mentioned in this episode:
Live "How to Become a Data Analyst" Webinar
Come learn the EXACT roadmap to landing your first data job: https://web.datacareerjumpstart.com/webinar
October Cohort of The Accelerator Starts on October 12th
Land your first data job ASAP with The Accelerator. And for this cohort only, get a discount PLUS our premium job board software PLUS our live AI workshops on how to analyze data Learn more here: https://datacareerjumpstart.com/daa
Transcripts
A lot of aspiring data analysts ask
me, is AI going to take our jobs?
2
00:00:04,650 --> 00:00:05,520
Are we cooked?
3
00:00:05,550 --> 00:00:09,150
And my honest answer is,
let's watch and find out.
4
00:00:09,150 --> 00:00:11,310
So I did that exactly in this episode.
5
00:00:11,340 --> 00:00:15,690
I gave Claude code a real data
analyst project, the kind of analysis
6
00:00:15,690 --> 00:00:19,110
that I used to spend hours on, and
I just kind of let a do its thing.
7
00:00:19,140 --> 00:00:19,980
Here's what happens.
8
00:00:20,130 --> 00:00:21,420
So here's the project.
9
00:00:21,510 --> 00:00:24,240
I want to get some insights
on my YouTube channel.
10
00:00:24,240 --> 00:00:27,750
What videos are doing well and why
they're doing well, so I can try
11
00:00:27,750 --> 00:00:31,140
to make better performing videos in
the future and more helpful videos
12
00:00:31,140 --> 00:00:33,750
for you guys who are watching, or
the you guys who are listening.
13
00:00:33,810 --> 00:00:37,230
So what I did is I opened up
YouTube creator studio and
14
00:00:37,680 --> 00:00:39,930
filtered by the last 365 days.
15
00:00:40,480 --> 00:00:43,629
And got different things like the
content data, the traffic source
16
00:00:43,629 --> 00:00:48,460
data, the geography data, and I
just exported all those as CSVs
17
00:00:48,699 --> 00:00:50,949
straight to this folder here.
18
00:00:51,280 --> 00:00:54,940
And so you can see I have a content
geography, new and returning viewers,
19
00:00:55,150 --> 00:00:59,950
playlist posts, subscription status,
traffic source, and viewer age, zip
20
00:00:59,950 --> 00:01:02,200
folders right here on my desktop.
21
00:01:02,525 --> 00:01:05,914
And basically I wanna see what's
going well with my channel and what's
22
00:01:05,914 --> 00:01:07,445
not doing so well with my channel.
23
00:01:07,505 --> 00:01:11,195
If I were doing this analysis myself or
giving it to another fellow data analyst,
24
00:01:11,225 --> 00:01:13,985
I would just kind of hope that they'd
go through all the data, explore it,
25
00:01:14,015 --> 00:01:15,664
and generate some meaningful insights.
26
00:01:15,695 --> 00:01:18,455
If they had prior domain knowledge
about YouTube videos, they might
27
00:01:18,455 --> 00:01:21,095
know to look through, click-through
rates on the thumbnails and average
28
00:01:21,095 --> 00:01:22,715
view durations of certain videos.
29
00:01:22,715 --> 00:01:26,015
But if I gave it to just a normal data
analyst, they probably wouldn't have that
30
00:01:26,015 --> 00:01:29,134
domain knowledge of YouTube, and so they
wouldn't know where to look necessarily.
31
00:01:29,160 --> 00:01:33,119
In this case, I'm not going to use my
domain knowledge to give Claude any hints.
32
00:01:33,119 --> 00:01:34,979
I just wanna see what it
comes up with on its own.
33
00:01:35,039 --> 00:01:36,690
So let's go ahead and open up Claude.
34
00:01:36,720 --> 00:01:39,479
So if you haven't checked out
Claude yet, I highly recommend it.
35
00:01:39,479 --> 00:01:42,630
It's produced by a company called
Anthropic that's very similar
36
00:01:42,630 --> 00:01:46,890
competitor to OpenAI, and Claude is
basically a competitor to chat GPT.
37
00:01:47,039 --> 00:01:50,429
Now, Claude has gained a lot of popularity
in the last, I don't know, six months,
38
00:01:50,429 --> 00:01:52,620
because one, it can write really well.
39
00:01:53,345 --> 00:01:54,935
Two, it can code really well.
40
00:01:55,115 --> 00:01:58,745
Andro has basically decided that it
doesn't want to be good at everything.
41
00:01:58,745 --> 00:02:01,055
It just wants to be good at
writing and good at coding.
42
00:02:01,175 --> 00:02:03,515
And here's the truth is when
you're good at writing and good
43
00:02:03,515 --> 00:02:05,705
at coding, you're very powerful.
44
00:02:05,765 --> 00:02:08,585
So they have this chat interface
that's very similar to Chat GPT,
45
00:02:08,913 --> 00:02:11,285
but they also have this thing
called Claude Code right here.
46
00:02:11,315 --> 00:02:13,985
Now, Claude Code is
basically the coding version.
47
00:02:14,170 --> 00:02:16,690
Of Claude, it's more designated
for getting tasks done,
48
00:02:16,690 --> 00:02:18,100
specifically coding tasks.
49
00:02:18,190 --> 00:02:22,210
And you can use the CLI, which is
basically the command line interface.
50
00:02:22,240 --> 00:02:25,270
Basically, that would look like you
opening up your command prompt and
51
00:02:25,270 --> 00:02:27,160
then typing in Claude right here.
52
00:02:30,760 --> 00:02:32,710
And then boom, Claude Code pops up here.
53
00:02:32,710 --> 00:02:35,890
So you can have like a command line
terminal version of Claude Code.
54
00:02:36,525 --> 00:02:40,215
Or you can just use the desktop app,
which has Claude Code right here.
55
00:02:40,245 --> 00:02:44,084
Now, personally, I like using the desktop
app because terminals and command lines
56
00:02:44,084 --> 00:02:47,024
still make me a little bit scared, and
it's just harder to know what's going on.
57
00:02:47,024 --> 00:02:49,575
So I'll be using the desktop
version of Claude Code.
58
00:02:49,605 --> 00:02:51,674
Now, I will say that I pay a
hundred dollars a month for
59
00:02:51,704 --> 00:02:53,685
Claude's Max subscription plan.
60
00:02:53,715 --> 00:02:56,655
Basically, that means I have the
very powerful version of Claude and
61
00:02:56,655 --> 00:02:58,095
I can use their most powerful model.
62
00:02:58,480 --> 00:02:59,980
Opus 4.6,
63
00:03:00,010 --> 00:03:02,980
which is basically just their
smartest, most sophisticated,
64
00:03:02,980 --> 00:03:04,209
best model that they have.
65
00:03:04,239 --> 00:03:08,290
They've also recently updated
it to have a 1 million context
66
00:03:08,290 --> 00:03:09,910
window, which is very powerful.
67
00:03:09,910 --> 00:03:13,480
Basically, it allows you to have
a lot of context, which can be
68
00:03:13,480 --> 00:03:14,500
good if you have a lot of data.
69
00:03:14,530 --> 00:03:17,799
Now, if you were to change models
from Opus to something like sonnet,
70
00:03:17,799 --> 00:03:19,540
this is their less powerful model.
71
00:03:19,540 --> 00:03:22,810
Now, sauna is still really good, but if
you were to change it to Haiku, which
72
00:03:22,810 --> 00:03:24,220
is really just their weakest model.
73
00:03:24,755 --> 00:03:26,045
It probably wouldn't do as well.
74
00:03:26,045 --> 00:03:30,005
So depending on what model you're using,
the performance will definitely change.
75
00:03:30,005 --> 00:03:31,355
The results will definitely change.
76
00:03:31,355 --> 00:03:33,725
So I'm just gonna use the most
powerful model just to see
77
00:03:33,725 --> 00:03:34,655
what we're working with here.
78
00:03:34,685 --> 00:03:37,925
Now, recently when I'm using AI
tools, uh, I have really gotten
79
00:03:37,925 --> 00:03:41,555
into dictation, and the reason
being is I kind of suck at writing.
80
00:03:41,555 --> 00:03:45,095
I kind of suck at typing, and if
I can just brain dump my thoughts
81
00:03:45,095 --> 00:03:49,175
verbally, I find that to be a lot
more effective than me filtering my
82
00:03:49,175 --> 00:03:51,785
thoughts via my typing with my fingers.
83
00:03:51,845 --> 00:03:54,695
So I'll just go ahead and click
the record button right here.
84
00:03:54,755 --> 00:04:01,295
In this folder, you'll find a set
of zip folders that contains the
85
00:04:01,295 --> 00:04:05,495
analytics for my YouTube channel
directly exported from YouTube Studio.
86
00:04:06,575 --> 00:04:10,325
I'd like you to analyze these data
sets and provide me meaningful,
87
00:04:10,445 --> 00:04:14,555
actionable insights on what I
could be doing better on my YouTube
88
00:04:14,555 --> 00:04:15,815
channel and what I'm doing well.
89
00:04:18,164 --> 00:04:19,034
And that's the prompt.
90
00:04:19,034 --> 00:04:21,735
I'm literally going to give Claude,
and I'm just gonna press this go
91
00:04:21,735 --> 00:04:23,745
button and see what it comes up with.
92
00:04:24,135 --> 00:04:27,435
It's gonna ask if it trusts this
workspace, and it indeed does.
93
00:04:27,555 --> 00:04:29,594
And you'll notice that I
have that folder right here.
94
00:04:29,625 --> 00:04:32,295
It's literally attached
to this folder right here.
95
00:04:32,495 --> 00:04:35,015
And that's the thing is cloud
code isn't working in the cloud.
96
00:04:35,015 --> 00:04:36,995
It's working here locally on your machine.
97
00:04:37,355 --> 00:04:40,715
So literally it has this YouTube
data analysis folder, the
98
00:04:40,715 --> 00:04:42,605
contents of which are inside.
99
00:04:42,875 --> 00:04:44,015
Now, I'm kind of curious.
100
00:04:44,045 --> 00:04:45,905
It's gonna ask me a lot
of permission things.
101
00:04:45,905 --> 00:04:48,845
I'm gonna literally just do, uh,
allow always for this project
102
00:04:48,845 --> 00:04:51,965
for right now, uh, I'm curious if
it's gonna be able to unzip these.
103
00:04:51,965 --> 00:04:52,835
It should be able to.
104
00:04:53,145 --> 00:04:56,685
Um, but we'll see what it actually
does to, to make this go through.
105
00:04:56,745 --> 00:04:59,715
So it's just like, Hey, do you wanna make
sure that I can run all these commands and
106
00:04:59,715 --> 00:05:03,405
I'm gonna let it run all these commands
because I, uh, trust it for right now.
107
00:05:03,405 --> 00:05:05,414
Now you obviously probably wanna
be a little bit more careful than
108
00:05:05,414 --> 00:05:09,284
me when allowing these AI agents
to do things on your desktop.
109
00:05:09,705 --> 00:05:10,965
You probably wanna make
sure you know that.
110
00:05:11,180 --> 00:05:12,380
What's actually going on.
111
00:05:12,440 --> 00:05:15,560
But to be honest, I'm a little
bit lazy and I just, I trust her.
112
00:05:15,590 --> 00:05:16,550
So far so good.
113
00:05:16,550 --> 00:05:17,870
Obviously there's been a lot of issues.
114
00:05:17,930 --> 00:05:21,860
I know that there's been one machine
learning content creator who like deleted
115
00:05:21,890 --> 00:05:26,120
an entire database completely with cloud
code, so you, you gotta be careful and
116
00:05:26,120 --> 00:05:27,350
make sure you know what it's doing.
117
00:05:27,410 --> 00:05:31,070
So right now it basically looks
like it created a user memory for
118
00:05:31,070 --> 00:05:32,465
me and it's compiling the analysis.
119
00:05:33,255 --> 00:05:35,745
It, read all the key files,
understand the picture.
120
00:05:36,015 --> 00:05:37,635
It's running these bash commands.
121
00:05:37,664 --> 00:05:40,275
It looks looking like it's
getting the CSV files.
122
00:05:40,275 --> 00:05:42,734
And this is, yeah, look, this
is what's in the CSV file.
123
00:05:43,065 --> 00:05:46,335
You can kinda see one of my titles,
how I'd become a data analyst in 2026.
124
00:05:46,364 --> 00:05:49,784
Then you're seeing some of the numbers,
views on a certain date or something like
125
00:05:49,784 --> 00:05:53,385
that, and you can see that it did that
with, um, post data, the content data,
126
00:05:53,385 --> 00:05:55,335
the playlist data, so on and so forth.
127
00:05:55,335 --> 00:05:56,145
So you can kind of see.
128
00:05:56,490 --> 00:05:59,250
What it's thinking about, let's
see what it's doing right now.
129
00:05:59,340 --> 00:06:03,990
Um, it, it just created like a, a file,
a memory file for me about, you know,
130
00:06:03,990 --> 00:06:05,820
who I am and what this project is about.
131
00:06:05,850 --> 00:06:08,310
And it says Avery Smith is a, oh, okay.
132
00:06:08,310 --> 00:06:10,110
Let's see what it, it
came up with some stuff.
133
00:06:10,110 --> 00:06:10,830
I don't know what it's doing.
134
00:06:10,860 --> 00:06:11,220
Ah, okay.
135
00:06:11,220 --> 00:06:12,960
Here's my full analysis
of your YouTube channel.
136
00:06:12,960 --> 00:06:14,805
Over the past year, we've had 1.7
137
00:06:14,805 --> 00:06:18,720
million views, a hundred thousand
watch hours, 29,000 subscribers
138
00:06:18,720 --> 00:06:24,060
gained about $8,000 in ad revenue, 30
million impressions, a click through
139
00:06:24,060 --> 00:06:26,010
rate of 3% average view, duration of.
140
00:06:26,260 --> 00:06:29,740
Four minutes and 442
videos in the dataset.
141
00:06:29,770 --> 00:06:33,010
What we're doing, well, massive reach
with how to become a data analyst content.
142
00:06:33,010 --> 00:06:36,820
Your top two videos alone account for
22% of the total, um, which is how I'd
143
00:06:36,820 --> 00:06:40,060
become a data analyst in 2026 and how
I'd become a data data analyst in 2026.
144
00:06:40,090 --> 00:06:41,500
I basically just changed.
145
00:06:41,595 --> 00:06:43,665
The 2025 video to 2026.
146
00:06:43,755 --> 00:06:45,795
Uh, let's editor, let's,
let's rule that out.
147
00:06:45,885 --> 00:06:48,675
If you're wondering why those video
titles are the same, it's because one
148
00:06:48,675 --> 00:06:53,295
of 'em is actually for 2025, not for
2026, but I tweaked the title for search
149
00:06:53,295 --> 00:06:55,395
purposes, that it would be normal.
150
00:06:55,455 --> 00:06:57,645
That way people could actually
find the video still and be
151
00:06:57,645 --> 00:06:58,425
interested in watching it.
152
00:06:58,425 --> 00:07:02,355
'cause although some things have changed
from 20 25, 20 26, a lot remains the same.
153
00:07:02,415 --> 00:07:06,255
This also drove 12,000 subscribers,
which is 41% of my subscribers
154
00:07:06,255 --> 00:07:09,585
gained two strong subscriber
conversion on career advice video.
155
00:07:09,645 --> 00:07:14,265
Videos like I analyzed 2,893 Data
Analyst jobs don't miss these six
156
00:07:14,265 --> 00:07:17,414
entry data levels jobs, and nine huge
lies about becoming Data analysts
157
00:07:17,685 --> 00:07:19,875
have excellent sub to view ratios.
158
00:07:19,875 --> 00:07:22,155
Your audience converts to
subscribers when you deliver data
159
00:07:22,155 --> 00:07:24,164
backed actionable career insights.
160
00:07:24,255 --> 00:07:25,724
All right, let's get to know Number three.
161
00:07:25,724 --> 00:07:28,664
Excellent watch time on long
form interview content, your
162
00:07:28,664 --> 00:07:30,044
podcast slash interview video.
163
00:07:30,044 --> 00:07:31,185
So I, I like that it.
164
00:07:31,195 --> 00:07:34,945
Figured out that I have like podcasty
style videos and interview style
165
00:07:34,945 --> 00:07:36,895
videos versus just like YouTube videos.
166
00:07:36,895 --> 00:07:38,965
I think that's really interesting
that it already gleaned that
167
00:07:38,995 --> 00:07:39,775
'cause I didn't tell it that.
168
00:07:39,775 --> 00:07:40,015
Right.
169
00:07:40,075 --> 00:07:44,635
Um, let's see How to earn 250,000
with multiple remote data jobs.
170
00:07:44,875 --> 00:07:48,025
13,000 views, but 2000
hours of watch time.
171
00:07:48,085 --> 00:07:52,045
Data analyst mock interview, 25,000
views, 2000 uh, hours of watch
172
00:07:52,045 --> 00:07:53,920
time, and an 8% click-through rate.
173
00:07:54,225 --> 00:07:54,525
Wow.
174
00:07:54,525 --> 00:07:55,545
See, that's really interesting.
175
00:07:55,635 --> 00:07:57,915
Playlist driven watch time is
strong in your data career.
176
00:07:57,975 --> 00:08:02,055
Uh, podcast playlist alone drives
658 hours of playlist watch time.
177
00:08:02,355 --> 00:08:03,735
It's just listing a bunch of things.
178
00:08:03,735 --> 00:08:04,245
I don't know.
179
00:08:04,305 --> 00:08:05,385
Some of it's actionable.
180
00:08:05,385 --> 00:08:06,975
Uh, we'll see if it suggests things.
181
00:08:07,035 --> 00:08:10,725
Um, audience demographics,
basically 25 to 44.
182
00:08:10,755 --> 00:08:13,485
Mostly us, India, uk, and Canada.
183
00:08:13,665 --> 00:08:14,625
Um.
184
00:08:15,130 --> 00:08:19,299
Browse features and suggested videos
are your top engagement sources.
185
00:08:19,359 --> 00:08:22,900
By watch time, this actually means YouTube
is actively recommending your content.
186
00:08:23,140 --> 00:08:24,190
The algorithm likes you.
187
00:08:24,219 --> 00:08:25,750
Oh, I'm glad to hear that.
188
00:08:25,750 --> 00:08:27,130
Sometimes it feels like it doesn't.
189
00:08:27,190 --> 00:08:28,240
Alright, what needs improvement?
190
00:08:28,240 --> 00:08:30,370
My CTR is below average.
191
00:08:30,430 --> 00:08:33,100
YouTube considers four to 5% healthy CTR.
192
00:08:33,370 --> 00:08:35,140
You're at 3% overall.
193
00:08:35,438 --> 00:08:37,150
Some of your biggest videos in the 2.4,
194
00:08:37,150 --> 00:08:38,230
2.8%,
195
00:08:38,260 --> 00:08:40,390
this means your thumbnails
and titles are underperforming
196
00:08:40,750 --> 00:08:42,130
relative to your impressions.
197
00:08:42,640 --> 00:08:42,975
Your highest.
198
00:08:43,875 --> 00:08:46,334
CTR videos give you
clues about what works.
199
00:08:46,814 --> 00:08:47,265
Okay.
200
00:08:47,505 --> 00:08:51,344
Then it says How to export
Tableau dashboard to image 15%.
201
00:08:51,704 --> 00:08:56,834
So this is interesting because me having
those domain knowledge and actually
202
00:08:56,834 --> 00:09:00,435
like being a YouTube content creator
and knowing YouTube, I know that this
203
00:09:00,435 --> 00:09:03,435
is bad advice because let's, let's go.
204
00:09:03,435 --> 00:09:06,224
In fact, let's go to how to
exports Tableau dashboard to image.
205
00:09:06,375 --> 00:09:09,704
And if you actually just go to
Google and you search that I'm gonna
206
00:09:09,704 --> 00:09:10,905
be the first video that pops up.
207
00:09:11,219 --> 00:09:14,805
Right, and so when you're
ranking number one on Google.
208
00:09:15,570 --> 00:09:19,200
You're going to have a high click
through rate because most of this
209
00:09:19,200 --> 00:09:24,510
video's traffic comes via search,
not via browse or suggested videos.
210
00:09:24,570 --> 00:09:28,170
So with search, you're like already
know what you really want, right?
211
00:09:28,170 --> 00:09:29,580
You're like, this is what I want.
212
00:09:29,610 --> 00:09:32,670
And when someone's like, Hey, here
you go, you're gonna click on it.
213
00:09:32,670 --> 00:09:33,600
So that's why you have a high.
214
00:09:33,865 --> 00:09:38,605
Click through rate versus if you're just
like on, you know, YouTube in general,
215
00:09:38,964 --> 00:09:41,579
just on the like, uh, homepage, right?
216
00:09:41,579 --> 00:09:41,860
Mm-hmm.
217
00:09:41,964 --> 00:09:43,795
Right here, it's like, I
don't know what I want.
218
00:09:43,795 --> 00:09:47,545
Do I wanna watch the, this is a
new chapter, or how I built a lead
219
00:09:47,545 --> 00:09:50,125
magnet or, um, what is Databricks?
220
00:09:50,155 --> 00:09:51,025
Those types of things.
221
00:09:51,025 --> 00:09:51,385
Right?
222
00:09:51,444 --> 00:09:53,245
Oh, editor, let's redo that
because I don't want 'em to see
223
00:09:53,245 --> 00:09:54,475
that I'm watching this video.
224
00:09:54,655 --> 00:09:55,824
When you open up YouTube, it's like.
225
00:09:56,135 --> 00:09:57,064
What do you wanna watch?
226
00:09:57,064 --> 00:09:59,735
Do I wanna watch you know,
data with Barr right now?
227
00:09:59,735 --> 00:10:00,965
Do I wanna watch Mark Lowe?
228
00:10:00,965 --> 00:10:01,985
Do I watch Tom Scott?
229
00:10:01,985 --> 00:10:02,975
What am I in the mood for?
230
00:10:03,005 --> 00:10:04,655
Maybe I'm gonna play
this Burger Life game.
231
00:10:04,655 --> 00:10:08,915
There's just a lot more distractions and
earning the click here is a lot harder
232
00:10:08,915 --> 00:10:10,905
to do than if you're like, you know.
233
00:10:11,500 --> 00:10:13,689
How to export to Tableau
dashboard to image.
234
00:10:13,750 --> 00:10:14,290
Oh, okay.
235
00:10:14,290 --> 00:10:15,189
I'm number one.
236
00:10:15,189 --> 00:10:17,380
Click on Google for, or
YouTube for this click.
237
00:10:17,410 --> 00:10:20,380
Like, that's the reason why that
click through rate is high is
238
00:10:20,380 --> 00:10:23,260
because it's mostly search base
versus browse or the homepage.
239
00:10:23,709 --> 00:10:25,180
Um, same with these videos.
240
00:10:25,180 --> 00:10:29,020
These are all going to be,
um, higher search videos.
241
00:10:29,020 --> 00:10:30,790
This one's not, which is interesting.
242
00:10:31,240 --> 00:10:33,880
Um, I'll admit, becoming a data
analysis is sustainable right now.
243
00:10:34,360 --> 00:10:36,219
Um, so that ones may be
interesting to look into.
244
00:10:37,260 --> 00:10:40,290
Titles with specificity,
controversy, or clear utility.
245
00:10:40,290 --> 00:10:41,100
Get clicked more.
246
00:10:41,520 --> 00:10:42,840
You're brought how to
become a data analyst.
247
00:10:42,840 --> 00:10:46,800
Titles get massive impressions, but lower
CTR consider AB testing thumbnails on your
248
00:10:46,800 --> 00:10:49,230
top impression videos, even with a 0.5%
249
00:10:49,500 --> 00:10:50,250
improvement.
250
00:10:50,250 --> 00:10:51,570
That's 30,000 more views.
251
00:10:52,515 --> 00:10:53,835
View your retention is short.
252
00:10:53,955 --> 00:10:55,305
Yes, I agree.
253
00:10:55,755 --> 00:10:56,625
Let's see.
254
00:10:56,655 --> 00:10:57,525
Um, action.
255
00:10:57,525 --> 00:11:00,645
Front load your value, your
short form content isn't
256
00:11:00,645 --> 00:11:01,905
driving meaningful engagement.
257
00:11:01,905 --> 00:11:04,725
That's why we stopped posting
short form, uh, engagement.
258
00:11:04,725 --> 00:11:09,165
Really, to be honest, 89% of
views come from non-subscribers.
259
00:11:09,515 --> 00:11:11,825
Let's see your attorney viewers have a 3.7
260
00:11:11,825 --> 00:11:13,895
click through rate versus a 2.81
261
00:11:13,895 --> 00:11:15,425
for new viewers.
262
00:11:15,665 --> 00:11:18,965
And watch a minute, 20 longer,
add stronger CTAs for subscribing
263
00:11:18,965 --> 00:11:20,195
mid video, not just the end.
264
00:11:20,555 --> 00:11:23,525
Consider a subscriber CTA
in the first two minutes.
265
00:11:23,555 --> 00:11:24,005
Okay?
266
00:11:24,665 --> 00:11:27,245
If you guys are watching right
now, hit subscribe so that way
267
00:11:27,245 --> 00:11:28,955
you can make Claude and me happy.
268
00:11:28,985 --> 00:11:29,315
Right?
269
00:11:29,345 --> 00:11:30,935
And that's, I'm doing my CTA right here.
270
00:11:30,935 --> 00:11:32,015
Hit subscribe right now.
271
00:11:32,585 --> 00:11:33,215
Um, okay.
272
00:11:33,215 --> 00:11:36,335
YouTube search is high volume,
but low engagement brings
273
00:11:36,335 --> 00:11:39,095
in a lot of YouTube search.
274
00:11:39,735 --> 00:11:43,485
Your number one source by view count,
but it doesn't have long view duration.
275
00:11:43,574 --> 00:11:45,704
I don't even know if that's true.
276
00:11:45,795 --> 00:11:48,974
I'm gonna go back to the actual
raw data here, and I'm just
277
00:11:48,974 --> 00:11:50,655
gonna go to traffic source.
278
00:11:50,714 --> 00:11:51,405
Oh, wow.
279
00:11:51,405 --> 00:11:56,564
See, I don't think I knew that
that search, which is this.
280
00:11:57,464 --> 00:11:58,844
Now see, oh, I don't know.
281
00:11:59,145 --> 00:12:02,895
Search is this, um, blue
bar right here, right?
282
00:12:02,925 --> 00:12:06,734
And it's saying it's my number one
traffic source over the last 365 days.
283
00:12:06,734 --> 00:12:11,354
And I don't know if it
is browse, is this green?
284
00:12:11,354 --> 00:12:15,734
And it looks like it's above blue
most of the time, except for, um,
285
00:12:16,995 --> 00:12:19,364
a little bit of a period last year.
286
00:12:20,114 --> 00:12:20,625
I don't know.
287
00:12:20,625 --> 00:12:21,435
That's really interesting.
288
00:12:21,435 --> 00:12:23,385
I don't know if blue is always higher.
289
00:12:24,255 --> 00:12:26,025
It's more steady, which is really nice.
290
00:12:26,055 --> 00:12:28,515
At suggested videos and browse
videos are very similar.
291
00:12:29,565 --> 00:12:33,045
So if you take green plus yellow,
that's always gonna be bigger than blue.
292
00:12:33,075 --> 00:12:36,225
But I guess it's not combining
those, it doesn't know, once again,
293
00:12:36,225 --> 00:12:37,605
it's missing that domain knowledge.
294
00:12:37,635 --> 00:12:41,925
Browse and suggested are very
similar style type videos because
295
00:12:41,925 --> 00:12:44,895
once again, you're, you're having
to earn the click in those.
296
00:12:45,195 --> 00:12:49,875
Um, maybe, maybe I'm over assuming how
similar they are, but from my domain
297
00:12:49,875 --> 00:12:51,315
experience, these two are very similar.
298
00:12:51,345 --> 00:12:52,365
Okay, interesting.
299
00:12:52,485 --> 00:12:54,345
Action search viewers are
looking for quick answers.
300
00:12:54,345 --> 00:12:57,105
Consider creating dedicated answer videos.
301
00:12:57,510 --> 00:12:59,790
Under five minutes optimize
for search while keeping your
302
00:12:59,790 --> 00:13:01,199
longer career advice for browse.
303
00:13:01,260 --> 00:13:01,860
Interesting.
304
00:13:01,860 --> 00:13:03,900
Your Tableau export video.
305
00:13:04,290 --> 00:13:06,810
Of a 15.64%
306
00:13:06,810 --> 00:13:09,030
CTR proves this model.
307
00:13:09,450 --> 00:13:12,750
Well, okay, it proves that we have
a high click-through rate, but do
308
00:13:12,750 --> 00:13:14,460
I get anything from that video?
309
00:13:14,550 --> 00:13:16,050
I'd argue not really.
310
00:13:16,080 --> 00:13:18,270
Let's open it up and look at the
data a little bit more closely.
311
00:13:18,330 --> 00:13:18,570
Okay.
312
00:13:18,570 --> 00:13:19,980
I have that video popped up.
313
00:13:19,980 --> 00:13:23,520
As you can see, it has
37, almost 38,000 views.
314
00:13:23,525 --> 00:13:26,525
473, uh, watch hours.
315
00:13:26,555 --> 00:13:30,574
It's only gotten me
$135 and 73 subscriber.
316
00:13:30,635 --> 00:13:33,694
So although this video is getting
a lot of views, like how am
317
00:13:33,694 --> 00:13:35,375
I really benefiting from it?
318
00:13:35,435 --> 00:13:39,005
I've made, let's see, I guess,
how many dollars a day do I make?
319
00:13:39,005 --> 00:13:40,204
135.
320
00:13:40,295 --> 00:13:43,295
I make like 10 cents a day
from this video, right?
321
00:13:43,655 --> 00:13:48,845
1 36 divided by 14, 16 days.
322
00:13:49,905 --> 00:13:55,185
Yeah, I make 9 cents a day with
this video, um, which isn't
323
00:13:55,185 --> 00:14:00,045
nothing, I'm grateful for it, but
like, that's not really the point.
324
00:14:00,045 --> 00:14:03,314
Like even though this has an
unreal, uh, click through rate,
325
00:14:03,314 --> 00:14:06,194
like this, this click through rate
is really, really high, right?
326
00:14:06,194 --> 00:14:09,194
Like at 13%, I guess, since published.
327
00:14:09,255 --> 00:14:11,865
When you compare it to a video
like this, how to become a data
328
00:14:11,865 --> 00:14:14,265
analyst in 2026, like, look at this.
329
00:14:14,415 --> 00:14:17,415
So many more subscribers, so
much more money, you know?
330
00:14:17,415 --> 00:14:19,155
And even though our click through rate.
331
00:14:19,545 --> 00:14:20,415
Is really low.
332
00:14:20,415 --> 00:14:22,335
It's probably like 2% for this video.
333
00:14:22,425 --> 00:14:24,645
Yeah, look at the
click-through rate's only 2.8%.
334
00:14:24,885 --> 00:14:29,325
Even though the click-through rate kind
of stinks, like the overall number of
335
00:14:29,325 --> 00:14:31,725
subscribers and revenue is way better.
336
00:14:31,725 --> 00:14:35,115
So I don't know why it's kind
of fixed on, like the idea that.
337
00:14:35,235 --> 00:14:36,315
Clickthrough rate is everything.
338
00:14:36,315 --> 00:14:38,775
Now clickthrough rate's really important,
but just 'cause your clickthrough
339
00:14:38,775 --> 00:14:41,925
rate is high doesn't mean that it's
good for you as a YouTube creator.
340
00:14:41,985 --> 00:14:44,865
But I do kinda like the idea of
creating dedicated answer videos under
341
00:14:44,865 --> 00:14:46,275
five minutes for optimized search.
342
00:14:46,275 --> 00:14:47,505
That is an interesting concept.
343
00:14:47,535 --> 00:14:51,225
India viewers have low
engagement shorts aren't working.
344
00:14:51,225 --> 00:14:51,525
Yep.
345
00:14:51,945 --> 00:14:54,315
Uh, either invest seriously
in short to the clear strategy
346
00:14:54,315 --> 00:14:55,485
or stop spending time there.
347
00:14:55,490 --> 00:14:56,360
And that's unfortunately.
348
00:14:56,970 --> 00:14:59,640
Uh, what I've done is we
just haven't done any shorts.
349
00:14:59,640 --> 00:15:03,300
Now, we might start doing shorts in a
little bit, but um, we'll have to see.
350
00:15:03,870 --> 00:15:08,820
End screens only drove 2,800
views and video cards, 1592 views.
351
00:15:09,540 --> 00:15:11,370
That's a very small amount,
so yeah, you're right.
352
00:15:11,370 --> 00:15:15,360
We don't use end screens nearly as well as
we probably should, which is unfortunate.
353
00:15:15,390 --> 00:15:19,380
Okay, top strategic recommendations,
double down on data backed career
354
00:15:19,380 --> 00:15:20,940
insights, AB test thumbnails.
355
00:15:20,940 --> 00:15:21,840
We're already doing that.
356
00:15:21,840 --> 00:15:22,800
I like this idea.
357
00:15:23,370 --> 00:15:24,720
Create a quick answer series.
358
00:15:24,720 --> 00:15:25,320
I like that.
359
00:15:25,330 --> 00:15:26,860
Front load hooks in the first 30 seconds.
360
00:15:26,860 --> 00:15:30,250
I mean, I try, but it's harder
than it, I guess, than it looks
361
00:15:30,430 --> 00:15:31,720
and leverage your podcast.
362
00:15:31,720 --> 00:15:33,460
More interview content
drives disproportional.
363
00:15:33,460 --> 00:15:35,350
Watch time in the Data
Career podcast playlist.
364
00:15:35,590 --> 00:15:38,440
Use your strongest pay, consider
promoting it more actively
365
00:15:38,440 --> 00:15:40,060
in your recommended videos.
366
00:15:40,090 --> 00:15:40,390
Okay.
367
00:15:40,390 --> 00:15:41,110
Interesting.
368
00:15:41,620 --> 00:15:42,190
Um.
369
00:15:42,485 --> 00:15:44,795
So this is like all the analysis it did.
370
00:15:44,795 --> 00:15:45,635
I don't even know.
371
00:15:45,695 --> 00:15:45,935
Okay.
372
00:15:45,935 --> 00:15:51,515
It did extract all of those ZIP files and
to get all those separate CSVs, and for
373
00:15:51,515 --> 00:15:55,325
each one of these CSVs, it usually has the
table data, the totals and the chart data.
374
00:15:55,595 --> 00:15:56,015
Okay.
375
00:15:56,255 --> 00:15:59,885
It kind of like crunched a bunch of these
numbers, but I didn't give much direction.
376
00:15:59,885 --> 00:16:03,395
And one thing I actually really wanted
to actually see is like a dashboard.
377
00:16:03,755 --> 00:16:06,455
So I'm gonna actually ask
it to create a dashboard.
378
00:16:07,265 --> 00:16:11,345
Can you create a dashboard that
monitors these metrics and shows me.
379
00:16:11,745 --> 00:16:15,015
The key things that I should be looking
at as a YouTube content creator.
380
00:16:16,185 --> 00:16:17,835
Once again, I'm leaving it pretty.
381
00:16:18,510 --> 00:16:20,880
Open-ended in general because
I wanna see what it does.
382
00:16:20,880 --> 00:16:22,080
I'm gonna go ahead and click go.
383
00:16:22,470 --> 00:16:24,180
And you can see it's currently puzzling.
384
00:16:24,180 --> 00:16:26,940
It's currently thinking it's
booping, it's gonna try to
385
00:16:26,940 --> 00:16:28,470
create some sort of a dashboard.
386
00:16:28,950 --> 00:16:34,380
Now, Claude Code really likes JavaScripts,
so my guess is it's going to create
387
00:16:34,380 --> 00:16:36,510
some sort of a JavaScript dashboard.
388
00:16:36,900 --> 00:16:40,950
Um, these JavaScript
dashboards are usually probably
389
00:16:40,950 --> 00:16:42,960
going to be done in React.
390
00:16:43,140 --> 00:16:46,200
React is a JavaScript library
that's really good for like.
391
00:16:46,475 --> 00:16:50,765
Creating websites basically,
and in turn data visualizations.
392
00:16:51,215 --> 00:16:52,445
Um, let's see what it's thinking.
393
00:16:52,445 --> 00:16:54,160
So it's entered planning mode.
394
00:16:54,830 --> 00:16:55,120
Whoa.
395
00:16:55,920 --> 00:16:57,060
Okay, here's the plan.
396
00:16:57,060 --> 00:16:57,990
I guess it already planned.
397
00:16:57,990 --> 00:17:02,730
So it said, uh, Avery's exported
these CSVs, and this is the data.
398
00:17:03,060 --> 00:17:06,210
We're gonna build a single
self-contained HT mal file with
399
00:17:06,210 --> 00:17:07,858
embedded CSS and JavaScript.
400
00:17:08,098 --> 00:17:12,810
Use chart js for the charts, parse all CSV
data and embed it directly as JavaScript
401
00:17:12,839 --> 00:17:16,470
objects so the dashboard opens instantly
to the browser with no server needed.
402
00:17:16,890 --> 00:17:19,140
It's gonna have KPI
cards, views over time.
403
00:17:19,140 --> 00:17:20,250
Top 15 videos.
404
00:17:20,535 --> 00:17:25,275
Traffic sources, audience, age,
geography, new versus returning viewers,
405
00:17:25,275 --> 00:17:26,775
subscriber versus non-subscriber.
406
00:17:26,775 --> 00:17:30,645
Top playlists and content
performance scatter.
407
00:17:31,125 --> 00:17:35,625
Interesting style will be YouTube
studio inspired dark theme.
408
00:17:36,225 --> 00:17:40,095
And, uh, okay, let's go ahead and
approve that and see how it does.
409
00:17:40,365 --> 00:17:44,835
Now, just for reference, so most of you,
I'm assuming, don't have domain knowledge
410
00:17:44,835 --> 00:17:46,455
of what YouTube studio looks like.
411
00:17:47,054 --> 00:17:49,574
Um, this is kind of what YouTube
Studio looks like right now.
412
00:17:49,635 --> 00:17:53,955
Um, it has my latest video, which was
she became a data analyst in 67 days.
413
00:17:54,705 --> 00:17:56,895
Um, how many views that has,
what's the click through rate?
414
00:17:56,895 --> 00:17:58,335
What's the average view duration?
415
00:17:58,390 --> 00:18:04,300
My current subscribers, which is 65,000
and a summary of the last 28 days.
416
00:18:04,810 --> 00:18:09,040
Um, it's not very graphics based.
417
00:18:09,040 --> 00:18:10,990
It's not very chart based.
418
00:18:10,990 --> 00:18:13,300
Like, I don't think there's
any charts on this page.
419
00:18:13,480 --> 00:18:13,930
Right.
420
00:18:14,440 --> 00:18:20,290
Um, there's like a lot of cards
with like their own like almost
421
00:18:20,290 --> 00:18:22,060
ads for different YouTube things.
422
00:18:22,540 --> 00:18:25,210
Um, if you go to analytics, this
one's like a little bit more of
423
00:18:25,210 --> 00:18:26,260
what we're trying to look for.
424
00:18:27,120 --> 00:18:31,199
Um, this is basically what would
be beating on the overview page.
425
00:18:31,229 --> 00:18:35,129
You basically have your views
over the last 28 days, your watch
426
00:18:35,129 --> 00:18:37,620
time, your subscribers, and your
revenue of the last 28 days.
427
00:18:38,250 --> 00:18:41,100
You have a little realtime
counter for your subscribers and
428
00:18:41,100 --> 00:18:43,020
your views in the last 48 hours.
429
00:18:43,680 --> 00:18:47,190
And then you have your top content
in this period, which is interesting.
430
00:18:47,190 --> 00:18:50,160
My, my shorts, there's a few of my
shorts who actually, that actually
431
00:18:50,160 --> 00:18:51,540
do really well, which is interesting.
432
00:18:52,110 --> 00:18:54,060
So this is kind of what we have to beat.
433
00:18:54,540 --> 00:18:57,660
Um, it's very tab based,
which I kind of don't love.
434
00:18:57,720 --> 00:18:59,760
It'd be nice if you could
just like customize your own
435
00:18:59,760 --> 00:19:00,695
version of this, I guess.
436
00:19:00,980 --> 00:19:05,570
It has your audience channels, your
audience watches, those types of things.
437
00:19:05,930 --> 00:19:10,250
So we'll see if cloud code can kind
of beat this and what it looks like.
438
00:19:11,270 --> 00:19:14,600
Uh, right now you can kind of see that
it's just extracting and preparing
439
00:19:14,600 --> 00:19:16,400
all the CSV datas for embedding.
440
00:19:16,820 --> 00:19:19,340
And then the next step will be
to build the H TM L dashboard
441
00:19:19,640 --> 00:19:22,970
and then verify dashboard
renders correctly in the browser.
442
00:19:22,970 --> 00:19:23,900
It's been working for about.
443
00:19:24,010 --> 00:19:28,330
Three minutes and it's still
thinking we'll go ahead and
444
00:19:28,330 --> 00:19:31,360
fast forward until Claude tells
me something more interesting.
445
00:19:31,390 --> 00:19:32,020
Right.
446
00:19:32,320 --> 00:19:32,710
Alright.
447
00:19:32,710 --> 00:19:37,660
I just finished the dashboard here
and, uh, it has the KPI cards and
448
00:19:37,660 --> 00:19:39,190
then the 10 interactive sections.
449
00:19:39,190 --> 00:19:41,950
It has this little preview for
me over the right hand side.
450
00:19:42,340 --> 00:19:43,090
I'm not.
451
00:19:43,500 --> 00:19:44,190
Optimistic.
452
00:19:44,190 --> 00:19:48,120
I don't think it's gonna look that good,
but let's go ahead and see how it looks.
453
00:19:48,450 --> 00:19:51,540
I'm gonna go back to my analysis
page and then I'm gonna open up
454
00:19:51,540 --> 00:19:53,340
the dashboard here separately.
455
00:19:53,940 --> 00:19:54,390
Okay.
456
00:19:54,390 --> 00:19:56,070
It doesn't look as bad as I thought.
457
00:19:56,550 --> 00:20:00,330
Lots of scrolling on the dashboard.
458
00:20:00,810 --> 00:20:03,240
Um, but at least it has
a lot of information.
459
00:20:03,240 --> 00:20:06,450
So as total views, watch hours,
subscribers gained revenue
460
00:20:06,840 --> 00:20:08,580
impressions, view, duration.
461
00:20:09,405 --> 00:20:12,195
Um, the daily views versus
the seven day moving average.
462
00:20:15,075 --> 00:20:17,504
Peak periods, which is interesting.
463
00:20:18,014 --> 00:20:23,655
Top 15 videos by views and the
revenue, the traffic source.
464
00:20:23,655 --> 00:20:25,545
So search is 31%.
465
00:20:25,875 --> 00:20:26,295
Oh wow.
466
00:20:26,295 --> 00:20:27,675
So 31.4
467
00:20:27,705 --> 00:20:28,754
versus 31.
468
00:20:28,754 --> 00:20:33,045
So I guess search by itself
actually is my number one source.
469
00:20:33,195 --> 00:20:36,970
Um, but browse and suggested I feel
like are so similar and that would be.
470
00:20:37,300 --> 00:20:38,050
52.
471
00:20:38,860 --> 00:20:41,620
Um, and I've always linked these
together, so that's interesting.
472
00:20:42,490 --> 00:20:42,760
Okay.
473
00:20:42,760 --> 00:20:45,730
Then you do see that this is the
interesting thing where my search
474
00:20:46,060 --> 00:20:48,250
average duration is quite low.
475
00:20:49,030 --> 00:20:51,940
Um, oh, and I guess this is red.
476
00:20:51,970 --> 00:20:54,370
'cause it's low and green if it's good.
477
00:20:56,169 --> 00:20:57,100
So that's interesting.
478
00:20:57,100 --> 00:20:58,330
So external, okay.
479
00:20:58,780 --> 00:21:00,340
Top country views.
480
00:21:00,735 --> 00:21:06,165
The age distribution for views and
watch time subscribed versus non
481
00:21:06,165 --> 00:21:09,014
subscribed, new versus returning users.
482
00:21:09,014 --> 00:21:11,294
And then CTR versus view.
483
00:21:11,655 --> 00:21:13,485
Each bubble equals a video.
484
00:21:13,725 --> 00:21:17,235
Size is the watch time,
color is the subscriber.
485
00:21:17,235 --> 00:21:19,395
Rate impressions, and
then click through rate.
486
00:21:19,455 --> 00:21:22,754
So this has a ton of impressions, a ton of
impressions, but low click through rate.
487
00:21:23,385 --> 00:21:24,584
But the green.
488
00:21:24,790 --> 00:21:26,440
Is lots of subscribers.
489
00:21:27,010 --> 00:21:28,210
So what is this one?
490
00:21:28,270 --> 00:21:29,890
This one is, Tableau is
easier than you think.
491
00:21:29,920 --> 00:21:33,580
Oh, it's a short, so there's
no subscribers coming from it.
492
00:21:34,240 --> 00:21:37,480
There's a lot of views and a decent
amount of a click through rate.
493
00:21:37,990 --> 00:21:38,260
Okay.
494
00:21:38,260 --> 00:21:38,740
Interesting.
495
00:21:38,740 --> 00:21:39,100
I'd almost.
496
00:21:40,185 --> 00:21:44,625
Remove shorts from this because they
don't really compare top playlist.
497
00:21:44,655 --> 00:21:45,495
This is interesting.
498
00:21:45,495 --> 00:21:47,985
So SQLs data analyst, this is something
I've been really interested in.
499
00:21:48,375 --> 00:21:50,865
This playlist is doing quite well.
500
00:21:51,014 --> 00:21:53,055
Uh, average due duration.
501
00:21:53,055 --> 00:21:54,435
So shout out to my Kenyans.
502
00:21:54,435 --> 00:21:56,445
It looks like you guys
watch my videos the longest.
503
00:21:56,445 --> 00:22:00,315
Other than us and India, why aren't
you guys watching the videos longer?
504
00:22:00,345 --> 00:22:02,504
Same with Indonesia and Pakistan.
505
00:22:02,504 --> 00:22:03,090
Come on guys.
506
00:22:03,160 --> 00:22:03,610
Come on.
507
00:22:03,610 --> 00:22:05,475
Maybe it's 'cause I talk crazy.
508
00:22:05,475 --> 00:22:05,895
I don't know.
509
00:22:05,985 --> 00:22:08,115
This dashboard is okay.
510
00:22:08,325 --> 00:22:09,915
I don't think it's anything amazing.
511
00:22:10,065 --> 00:22:13,845
I mean, obviously I didn't have to make
it and it was quick, so I appreciate that.
512
00:22:13,935 --> 00:22:19,365
There's not like any crazy insights in
terms of like, is it better than, than
513
00:22:19,365 --> 00:22:22,274
the YouTube, you know, studio mode.
514
00:22:22,305 --> 00:22:23,445
Probably not.
515
00:22:23,534 --> 00:22:26,055
There's some things I like
maybe more and some things.
516
00:22:26,179 --> 00:22:30,350
Uh, I don't like, I mean, I don't love
scrolling on dashboards really that often.
517
00:22:30,350 --> 00:22:33,260
But then the other equivalent is
you have to tab it like this, right?
518
00:22:33,260 --> 00:22:35,450
So are you gonna tab or
are you gonna scroll?
519
00:22:35,450 --> 00:22:38,030
It just, I guess, depends on how
you like your information viewed.
520
00:22:38,030 --> 00:22:39,710
I'd rather tab to be honest.
521
00:22:39,770 --> 00:22:43,730
Um, because then I can actually like
choose where I'm going to versus if I want
522
00:22:43,730 --> 00:22:45,710
to get to, you know, the traffic sources.
523
00:22:45,710 --> 00:22:48,710
I have to go by the
top 15 videos by views.
524
00:22:48,980 --> 00:22:49,790
So on and so forth.
525
00:22:49,820 --> 00:22:50,720
This isn't bad.
526
00:22:50,810 --> 00:22:51,440
It's not great.
527
00:22:51,440 --> 00:22:52,070
It's not bad.
528
00:22:52,100 --> 00:22:53,600
I'm actually just gonna ask Claude.
529
00:22:53,600 --> 00:23:00,290
I'm gonna say review the dashboard,
find the pros and cons of your
530
00:23:00,290 --> 00:23:08,450
data displayed and the, um, UI and
create a second better version.
531
00:23:08,780 --> 00:23:10,160
So I'm basically telling.
532
00:23:10,649 --> 00:23:13,439
Claude, you go, Hey, go look at
your dashboard, see what you did.
533
00:23:13,439 --> 00:23:16,620
Well see what you didn't do well,
and then recreate it based off
534
00:23:16,620 --> 00:23:17,850
of, you know, your findings.
535
00:23:17,909 --> 00:23:20,760
Um, this is something I found that's
really interesting is when you have AI
536
00:23:20,760 --> 00:23:24,750
grading ai, it often works better if
you give it to like a different model.
537
00:23:24,750 --> 00:23:28,290
Like I gave this to, you
know, chat GPT or GPT 5.2
538
00:23:28,290 --> 00:23:29,100
or something like that.
539
00:23:29,595 --> 00:23:32,085
Or Gemini or something like that,
it might do a little bit better.
540
00:23:32,445 --> 00:23:37,095
Um, but I'm actually interested to see how
it does, it looks like it's struggling.
541
00:23:37,095 --> 00:23:42,945
It's trying to open the dashboard,
uh, in Chrome and it's not working.
542
00:23:43,004 --> 00:23:45,525
Let's see what it's trying to do now.
543
00:23:45,675 --> 00:23:47,445
Okay, let's see.
544
00:23:48,075 --> 00:23:51,615
It's been trying to open up the dashboard
for quite a bit here and it looks like
545
00:23:51,615 --> 00:23:55,275
it's really struggling to, when this
sort of thing happens, it's a big red
546
00:23:55,275 --> 00:23:59,265
flag to me because it keeps trying to
do this and eventually it's gonna give
547
00:23:59,265 --> 00:24:02,685
up and it's going to just probably
guess what it looks like instead of
548
00:24:02,685 --> 00:24:03,885
actually knowing what it looks like.
549
00:24:03,915 --> 00:24:07,005
Although it should be able to like
read the HTML that it created.
550
00:24:07,035 --> 00:24:11,085
But I get nervous when it like starts
to do these like failures and repeat
551
00:24:11,085 --> 00:24:13,425
itself over and over again because
eventually it's gonna give up and
552
00:24:13,425 --> 00:24:14,565
it's just gonna make stuff up and I.
553
00:24:14,625 --> 00:24:15,465
Done this enough.
554
00:24:15,465 --> 00:24:19,215
I've spent hundreds of hours analyzing
data with Claude that I know eventually,
555
00:24:19,275 --> 00:24:20,835
uh, it will make something up.
556
00:24:20,835 --> 00:24:23,565
Basically, it's like, this is what I think
it looks like, and you have to be really
557
00:24:23,565 --> 00:24:27,375
careful because you, unless you're paying
really close attention, you can actually
558
00:24:27,375 --> 00:24:29,145
see what's going on in these log files.
559
00:24:29,565 --> 00:24:31,785
You might not notice it,
it might not tell you.
560
00:24:31,785 --> 00:24:33,795
So that's something I have a red flag.
561
00:24:33,795 --> 00:24:36,735
I'm gonna be looking really
closely to see what it says and
562
00:24:36,735 --> 00:24:37,515
actually make sure that it's.
563
00:24:37,560 --> 00:24:40,830
Talking normal versus this
is gonna make something up.
564
00:24:40,889 --> 00:24:45,060
Alright, so after about five minutes,
it did a full review of V one.
565
00:24:45,360 --> 00:24:48,149
Some of the V one, uh, cons
were three outta the seven
566
00:24:48,149 --> 00:24:49,710
charts are completely broke.
567
00:24:49,800 --> 00:24:51,090
Uh, no month over month.
568
00:24:51,090 --> 00:24:56,190
Trends missing, computed efficiency
metrics, no upload frequency analysis,
569
00:24:56,190 --> 00:24:59,760
post data completely unused, no
content category grouping, all
570
00:24:59,760 --> 00:25:00,750
these different things, right?
571
00:25:00,780 --> 00:25:02,610
Well, I mean, like it is working.
572
00:25:02,639 --> 00:25:03,899
We just saw the graph, right?
573
00:25:03,899 --> 00:25:04,205
Like all this.
574
00:25:04,520 --> 00:25:05,629
Stuff is working.
575
00:25:05,629 --> 00:25:09,290
All of this is here, so I don't
know why it thinks it's broken.
576
00:25:10,155 --> 00:25:13,305
The truth is it doesn't actually
see it, it doesn't actually know
577
00:25:13,305 --> 00:25:14,865
what's going on, is my guess.
578
00:25:15,105 --> 00:25:18,225
Or it's just not being rendered
correctly when it's trying to to
579
00:25:18,285 --> 00:25:20,505
view it, it can actually view it.
580
00:25:20,715 --> 00:25:24,615
And so it tried to, you know, uh,
it says it's building V two now, but
581
00:25:24,615 --> 00:25:26,865
it's not, it's literally stopped.
582
00:25:26,865 --> 00:25:30,855
So maybe I'll say, you know,
keep going and we'll see if.
583
00:25:30,905 --> 00:25:35,795
It actually does build version two, but
at this point I'm not super optimistic.
584
00:25:35,795 --> 00:25:36,754
We'll, we'll see how it does.
585
00:25:36,845 --> 00:25:37,235
Okay.
586
00:25:37,235 --> 00:25:41,885
After some coaxing, I think it got
this new version of dashboard two here.
587
00:25:41,885 --> 00:25:43,504
Let's see how it looks.
588
00:25:43,565 --> 00:25:44,195
Okay.
589
00:25:44,285 --> 00:25:46,565
Oh, and look, it did go to a tabbing.
590
00:25:46,625 --> 00:25:47,825
Oh, it's both tabbing.
591
00:25:47,885 --> 00:25:48,155
Wow.
592
00:25:48,155 --> 00:25:49,805
It's like it was listening
to our conversation.
593
00:25:49,805 --> 00:25:52,415
I was like, I like tabs
more, and I added tabs.
594
00:25:52,685 --> 00:25:53,795
This is interesting.
595
00:25:54,635 --> 00:25:57,725
Uh, this is like the
number of views on a day.
596
00:25:58,980 --> 00:26:00,450
I don't get why this is here.
597
00:26:00,450 --> 00:26:01,620
That's interesting.
598
00:26:02,250 --> 00:26:04,649
Um, let's see.
599
00:26:04,649 --> 00:26:07,230
Subscriber efficiency per 1000 views.
600
00:26:07,590 --> 00:26:09,240
Oh see this is actually interesting.
601
00:26:09,240 --> 00:26:12,120
So this, this is normalizing it by views.
602
00:26:12,120 --> 00:26:17,054
So what video brought in the most
subscribers per 1000 views it got.
603
00:26:17,395 --> 00:26:19,800
And that's really
interesting because like.
604
00:26:20,790 --> 00:26:25,125
Yeah, you know, something like
this one, I analyze this many jobs.
605
00:26:25,125 --> 00:26:27,555
Like this is getting 37.
606
00:26:27,645 --> 00:26:31,335
Let's see, it says, oh yeah,
37 subscribers per 1000 views.
607
00:26:31,365 --> 00:26:32,325
See, that's interesting.
608
00:26:32,355 --> 00:26:35,235
I think this is like the most
interesting graph it's created so far.
609
00:26:36,045 --> 00:26:38,055
Um, let's see here.
610
00:26:38,445 --> 00:26:39,525
This one's interesting.
611
00:26:40,215 --> 00:26:42,735
Watch time, duration by source.
612
00:26:43,125 --> 00:26:46,815
Um, and then this is the average
duration and this is the watch time.
613
00:26:47,745 --> 00:26:50,775
I don't think that's
very useful comparison.
614
00:26:51,705 --> 00:26:53,475
Um, yeah.
615
00:26:53,475 --> 00:26:54,285
Here's my funnel.
616
00:26:54,285 --> 00:26:56,175
I guess this is the number of impressions.
617
00:26:56,175 --> 00:26:57,105
This is the number of views.
618
00:26:57,105 --> 00:26:58,605
This is watch greater than one minute.
619
00:26:58,605 --> 00:27:00,045
This is the subscribers.
620
00:27:00,585 --> 00:27:01,575
That's kinda interesting.
621
00:27:01,575 --> 00:27:02,685
I like that idea.
622
00:27:02,745 --> 00:27:05,445
This is views versus average duration.
623
00:27:05,625 --> 00:27:06,705
I don't know.
624
00:27:06,735 --> 00:27:07,065
Okay.
625
00:27:07,575 --> 00:27:10,665
Overall, like this is, this is just fine.
626
00:27:10,665 --> 00:27:13,995
I think this is nothing
amazing, nothing terrible.
627
00:27:14,025 --> 00:27:15,885
What I think where it
gets really powerful.
628
00:27:16,185 --> 00:27:20,534
Is where instead of me just saying,
analyze this, where me as like a
629
00:27:20,534 --> 00:27:24,495
data analyst, me as a domain expert
come in and be like, I have things
630
00:27:24,495 --> 00:27:26,655
that I actually want you to look at.
631
00:27:26,985 --> 00:27:29,235
I have my brain, I know it's important.
632
00:27:29,504 --> 00:27:33,345
Help me to do the actual
dirty work of the analysis.
633
00:27:33,405 --> 00:27:37,635
So for example, um, one thing that I
think is, is really powerful or would
634
00:27:37,635 --> 00:27:43,575
be really interesting to see also what
monthly heat map grid 12 monthly cells.
635
00:27:44,175 --> 00:27:45,645
I don't even see where that's at.
636
00:27:45,705 --> 00:27:46,815
Did you guys see a heat map?
637
00:27:46,935 --> 00:27:47,895
Am I blind?
638
00:27:47,895 --> 00:27:50,235
Uh, is it like in the old version?
639
00:27:50,235 --> 00:27:53,595
If I refresh the old version,
I don't see it there either.
640
00:27:53,895 --> 00:27:56,715
So I'm actually gonna call
Claude out real quick for that.
641
00:27:56,715 --> 00:28:02,504
I'm gonna say, um, where,
where is the monthly heat map?
642
00:28:02,565 --> 00:28:04,125
Oh, it's calling.
643
00:28:04,260 --> 00:28:04,875
Oh, okay.
644
00:28:04,875 --> 00:28:09,045
It's calling this thing a heat map, which
it's hardly a heat map, but that's fine.
645
00:28:09,225 --> 00:28:10,635
Uh, it's calling.
646
00:28:11,370 --> 00:28:12,360
This a heat map.
647
00:28:12,600 --> 00:28:15,960
I mean, that's a terrible
heat map if I'm being honest.
648
00:28:16,080 --> 00:28:18,960
So one thing I think would be really
powerful or be interesting actually
649
00:28:18,960 --> 00:28:22,620
for me to see as someone who's, you
know, invested in this data set is
650
00:28:22,620 --> 00:28:26,370
something like it tried to make with
this, uh, bubble chart right here.
651
00:28:26,370 --> 00:28:29,189
I really like bubble charts 'cause it
can show you a lot of variables at once.
652
00:28:29,520 --> 00:28:33,600
Uh, but I don't think this is quite what
I want in terms of the bubble chart.
653
00:28:33,810 --> 00:28:37,530
So I'm actually just gonna say,
I'm actually just gonna tell
654
00:28:37,530 --> 00:28:38,580
Claude what I'd like to see.
655
00:28:39,510 --> 00:28:44,070
Please make just a standalone bubble chart
of the click-through rate on the x axis.
656
00:28:44,100 --> 00:28:51,750
The views on the Y axis where each circle
is equal to a video, the size is equal
657
00:28:51,750 --> 00:28:55,800
to the number of new subscribers, and
the color is the percentage of those
658
00:28:55,800 --> 00:28:59,010
viewers that came by the search traffic.
659
00:28:59,040 --> 00:29:02,130
This way, I'm able to see the click
through rate, the views, the number of
660
00:29:02,130 --> 00:29:04,140
new subscribers, and the percentage.
661
00:29:04,455 --> 00:29:08,235
Coming from search all in one place,
and that'll let me see outliers
662
00:29:08,235 --> 00:29:09,824
a little bit better visually.
663
00:29:10,274 --> 00:29:15,345
Um, because for me data is really hard
to understand unless I can visually
664
00:29:15,345 --> 00:29:18,820
see it and visually understanding
it, uh, makes it really helpful.
665
00:29:20,385 --> 00:29:20,595
Okay.
666
00:29:20,595 --> 00:29:24,465
Traffic source data is only available at
the channel level by date, not per video.
667
00:29:24,525 --> 00:29:24,885
Hmm.
668
00:29:24,945 --> 00:29:25,695
That's interesting.
669
00:29:25,695 --> 00:29:30,075
Didn't earlier, didn't you tell
me, Claude, that there was a video?
670
00:29:30,075 --> 00:29:31,485
I guess it's by aggregate.
671
00:29:31,635 --> 00:29:36,015
So it turns out that even though on
YouTube studio, you can see how viewers
672
00:29:36,015 --> 00:29:39,675
found this video and see that search
was, you know, 60%, that that is not
673
00:29:39,675 --> 00:29:41,695
available in the dataset that we have.
674
00:29:42,025 --> 00:29:46,015
There is, that is not included
in the export in YouTube studio.
675
00:29:46,015 --> 00:29:49,345
So in order to get that data, we'd
have to like take a screenshot,
676
00:29:49,765 --> 00:29:53,815
uh, or, or jot down these numbers
right here, or use the YouTube API
677
00:29:53,815 --> 00:29:55,285
and that's for a another video.
678
00:29:55,285 --> 00:29:56,275
So we're not gonna do that today.
679
00:29:56,755 --> 00:30:00,505
So instead we're gonna just go ahead and
kind of create a similar bubble chart.
680
00:30:00,865 --> 00:30:04,255
Um, but instead of the color
being the percent of search.
681
00:30:04,640 --> 00:30:07,580
Will make it the view time,
the average view duration.
682
00:30:07,610 --> 00:30:10,880
So it's really not that much different
than this chart, to be perfectly honest.
683
00:30:10,880 --> 00:30:12,560
I would've liked to have
been a little bit different.
684
00:30:12,890 --> 00:30:14,390
Um, but I guess we
didn't give it the data.
685
00:30:14,600 --> 00:30:18,950
However, I did notice on the first version
right here, it gave like this little
686
00:30:18,950 --> 00:30:24,800
optimization down here where you have
high impressions, low CTR, which basically
687
00:30:25,010 --> 00:30:27,080
it says thumbnails and tidal problem.
688
00:30:27,110 --> 00:30:28,220
Top left quadrant.
689
00:30:28,280 --> 00:30:31,160
While high impressions,
low CTR are down here.
690
00:30:31,325 --> 00:30:36,155
It's not the top left quadrant right here
and it, but that does mean that there I
691
00:30:36,155 --> 00:30:37,895
could improve the title and thumbnail.
692
00:30:37,895 --> 00:30:39,635
So I just got the quadrant area wrong.
693
00:30:39,725 --> 00:30:42,035
High CTR, low views.
694
00:30:42,095 --> 00:30:45,065
Well, we don't have views on
this chart anywhere actually.
695
00:30:45,095 --> 00:30:47,525
So high CTR, low views.
696
00:30:47,525 --> 00:30:48,485
It doesn't even make sense.
697
00:30:48,775 --> 00:30:49,195
Right.
698
00:30:49,525 --> 00:30:52,435
It says it's the bottom right,
but that doesn't make sense.
699
00:30:53,095 --> 00:30:55,675
Uh, videos in the top right
are your proven winners.
700
00:30:55,705 --> 00:30:58,045
I don't have any with high
impressions and high clickthroughs,
701
00:30:58,045 --> 00:30:59,305
so I have no winners, I guess.
702
00:30:59,725 --> 00:31:03,355
Uh, anyways, let's go ahead and
say, okay, instead of doing the
703
00:31:03,355 --> 00:31:06,685
percent by search traffic, make
it the average video duration.
704
00:31:06,955 --> 00:31:08,275
Also, please exclude.
705
00:31:08,455 --> 00:31:12,115
All shorts, or I guess rather
make two separate charts, one for
706
00:31:12,115 --> 00:31:14,455
shorts and one for longer videos.
707
00:31:14,515 --> 00:31:16,525
Because previously it
had put those together.
708
00:31:16,525 --> 00:31:16,825
Right.
709
00:31:16,825 --> 00:31:19,255
And that's where you, I mean,
this is a short right here.
710
00:31:19,285 --> 00:31:21,925
This is a short right here.
711
00:31:21,985 --> 00:31:23,125
And this is a short right here.
712
00:31:23,125 --> 00:31:24,260
So basically all of the red.
713
00:31:24,850 --> 00:31:29,170
Uh, dots on this page were shorts, so
it doesn't really make sense to have,
714
00:31:29,290 --> 00:31:33,490
you know, shorts and long videos on the
same page because they're quite different
715
00:31:33,520 --> 00:31:36,970
products and quite different audiences and
quite different purposes, to be honest.
716
00:31:37,030 --> 00:31:39,610
Okay, I'm gonna hit allow and
let's see what it creates here.
717
00:31:39,850 --> 00:31:43,330
So finally, after about seven
minutes, uh, I think it finished.
718
00:31:43,600 --> 00:31:46,300
Um, I did notice there was
a few funny things going on.
719
00:31:46,300 --> 00:31:48,670
Like for instance, there
was some issues with the.
720
00:31:48,980 --> 00:31:51,260
Number of data we were trying to look at.
721
00:31:51,260 --> 00:31:54,020
It looks like, like in terms of context
windows, that makes me a little bit
722
00:31:54,020 --> 00:31:57,650
nervous and it was having a hard
time actually screenshotting them.
723
00:31:58,610 --> 00:32:02,390
Um, because there is a lot of, uh,
different, uh, bubbles going on, a
724
00:32:02,390 --> 00:32:03,770
lot of different data being displayed.
725
00:32:04,340 --> 00:32:06,470
Um, let's see how it went.
726
00:32:07,190 --> 00:32:11,900
Okay, so here is our click through versus
bubble chart, and we have it for shorts
727
00:32:12,440 --> 00:32:14,330
and we have it for long form views.
728
00:32:14,330 --> 00:32:14,660
So.
729
00:32:15,840 --> 00:32:18,960
Um, this is interesting to me.
730
00:32:19,470 --> 00:32:24,420
Um, you obviously have like, almost,
uh, I forgot the, what this is
731
00:32:24,420 --> 00:32:27,240
called, but like this like shape
where it's like l almost, right,
732
00:32:27,240 --> 00:32:29,160
which just goes down and then, right.
733
00:32:29,970 --> 00:32:33,240
And then it looks like we just
have some huge outliers and shorts.
734
00:32:33,780 --> 00:32:36,000
Um, this interest, this is
interesting to me 'cause now.
735
00:32:36,465 --> 00:32:37,784
I can like, interpret this data.
736
00:32:37,784 --> 00:32:40,125
In fact, let me ask Claude
how it interprets this data.
737
00:32:40,575 --> 00:32:42,254
Um, okay.
738
00:32:42,284 --> 00:32:45,615
How do you interpret this data?
739
00:32:46,095 --> 00:32:48,524
What action should I take?
740
00:32:49,034 --> 00:32:51,615
Uh, we'll see what it says
while I, I give you my thoughts.
741
00:32:51,615 --> 00:32:54,375
So what, what is the size of the
bubble that's number of subs?
742
00:32:54,705 --> 00:32:56,625
So even though, like I was saying
earlier, even though these, these
743
00:32:56,625 --> 00:32:57,705
have huge click through, right?
744
00:32:57,705 --> 00:33:01,905
They have low subs, um, this one's
the closest one, so data analyst,
745
00:33:01,905 --> 00:33:05,294
mock interview, we're still getting
a decent amount of subscribers, but
746
00:33:05,294 --> 00:33:10,574
not even really then we're, we don't
get meaningful number of subscribers
747
00:33:10,574 --> 00:33:12,675
till about this video right here.
748
00:33:13,590 --> 00:33:17,220
Um, and then these are obviously where the
subscribers are, are quite substantial.
749
00:33:17,790 --> 00:33:20,940
Uh, the color is the video duration.
750
00:33:21,150 --> 00:33:25,080
Um, I don't think I asked
for the that, did I?
751
00:33:25,500 --> 00:33:28,440
If I did, I didn't mean
to, what did I say up here?
752
00:33:28,440 --> 00:33:30,810
I said that the, oh yeah.
753
00:33:30,810 --> 00:33:32,580
I make it the average video duration.
754
00:33:32,580 --> 00:33:35,405
I meant a VD uh, wait, that is.
755
00:33:36,554 --> 00:33:38,865
Average view, duration,
not video duration.
756
00:33:38,895 --> 00:33:43,935
Ah, that's my fault for, for
saying that, but eh, okay.
757
00:33:43,935 --> 00:33:46,485
So this video right
here, this is 45 minutes.
758
00:33:46,485 --> 00:33:46,725
Okay.
759
00:33:46,725 --> 00:33:47,655
Yeah, that makes sense.
760
00:33:48,225 --> 00:33:48,705
Okay.
761
00:33:48,705 --> 00:33:50,294
So, um, let's see.
762
00:33:50,475 --> 00:33:52,425
So the color's basically meaningless.
763
00:33:52,455 --> 00:33:57,435
I mean, I guess we can say that
the, the interviews, which are
764
00:33:57,435 --> 00:33:59,985
usually the longer videos, um.
765
00:34:00,570 --> 00:34:01,710
Don't get a ton of views.
766
00:34:02,700 --> 00:34:06,000
I guess that's one thing we can look
at it and none of them get a particular
767
00:34:06,149 --> 00:34:08,639
large amount of sub subscribers.
768
00:34:09,600 --> 00:34:10,080
Okay.
769
00:34:10,409 --> 00:34:11,460
Um, let's look at shorts.
770
00:34:11,460 --> 00:34:20,730
So we have Tableau, remote Data,
job, Tableau, Harvard Saturated data
771
00:34:20,730 --> 00:34:24,485
sets, Google Analytics certificate.
772
00:34:25,605 --> 00:34:27,225
And what's the difference between these?
773
00:34:27,284 --> 00:34:27,614
Okay.
774
00:34:28,094 --> 00:34:33,674
So it's almost like we have like a low
line, a little bit higher line, and then
775
00:34:33,674 --> 00:34:36,524
like these three outliers, uh, over here.
776
00:34:36,884 --> 00:34:39,793
So I think I could just basically
take anything that's above.
777
00:34:40,650 --> 00:34:43,469
This like bottom line and try
to make more shorts like that.
778
00:34:43,469 --> 00:34:44,580
That would be kind of my takeaway.
779
00:34:44,580 --> 00:34:46,500
And pay attention to the titles on these.
780
00:34:47,250 --> 00:34:49,440
Um, we're missing such a key metric.
781
00:34:49,440 --> 00:34:53,370
The being able to know like what
the traffic's from is so important.
782
00:34:53,370 --> 00:34:56,489
So we'd wanna try to get
that data for the future.
783
00:34:56,699 --> 00:34:58,650
But since we don't have it
right now, that's my takeaways.
784
00:34:58,650 --> 00:35:02,070
I would just try to make more
videos like these titles in the
785
00:35:02,070 --> 00:35:04,529
shorts and on this one over here.
786
00:35:04,529 --> 00:35:09,090
I mean, really the important thing
is anything I would say that's like.
787
00:35:10,200 --> 00:35:15,509
In this circle, uh, right here, we should
probably include, try to include the
788
00:35:15,540 --> 00:35:17,819
click through rate on most of these.
789
00:35:17,819 --> 00:35:19,290
See if we could improve it.
790
00:35:19,799 --> 00:35:20,819
Um, and on these.
791
00:35:22,064 --> 00:35:22,785
So that's my takeaway.
792
00:35:22,785 --> 00:35:23,774
Let's see what Claude says.
793
00:35:23,834 --> 00:35:28,365
Claude is saying, um, your
biggest videos have the worst CTR.
794
00:35:28,395 --> 00:35:30,194
Yeah, we've known about that.
795
00:35:30,615 --> 00:35:32,924
Higher CTR is good, obviously.
796
00:35:33,495 --> 00:35:35,475
Um, not a whole lot there.
797
00:35:35,475 --> 00:35:37,214
Shorts two massive outliers.
798
00:35:37,214 --> 00:35:37,904
We talked about that.
799
00:35:37,904 --> 00:35:39,314
Shorts don't convert to subscribers.
800
00:35:39,314 --> 00:35:39,899
We talked about that to.
801
00:35:40,319 --> 00:35:42,629
Yeah, I don't think this is
necessarily very meaningful, but
802
00:35:42,629 --> 00:35:45,180
I didn't really come up with that
much better analysis on my end.
803
00:35:45,450 --> 00:35:48,210
I think really, in order for me to
get really meaningful data outta this,
804
00:35:48,210 --> 00:35:51,299
we need to have the traffic source
involved, so hopefully that helps.
805
00:35:51,299 --> 00:35:55,109
You see how I personally
use Claude Code as a.
806
00:35:55,280 --> 00:35:59,540
Helpful tool as a data analyst,
it makes my work so much faster.
807
00:35:59,540 --> 00:36:03,350
Doing all this previously would've taken
me so much time to get through everything.
808
00:36:03,380 --> 00:36:05,150
It does a great job of
creating graphs for me.
809
00:36:05,150 --> 00:36:08,390
It does a great job of coming up with
some sort of suggestions or some sort
810
00:36:08,390 --> 00:36:11,120
of actual analysis and, uh, insights.
811
00:36:11,360 --> 00:36:12,290
That being said.
812
00:36:12,565 --> 00:36:14,245
I still need to prompt it.
813
00:36:14,245 --> 00:36:15,715
I still need to ask it what to do.
814
00:36:15,955 --> 00:36:20,245
I need to, you know, obviously be a domain
expert to try to know what all this stuff
815
00:36:20,245 --> 00:36:22,615
means and to ask it the right question.
816
00:36:22,615 --> 00:36:25,855
So I don't really foresee it
replacing any data analyst.
817
00:36:25,885 --> 00:36:29,995
I kind of just see it being as
the new tool for data analysts to
818
00:36:29,995 --> 00:36:31,750
actually use to do their analysis.
819
00:36:31,750 --> 00:36:34,105
But let me know what you think
in the comments down below.
820
00:36:34,225 --> 00:36:36,715
I appreciate you guys watching
or listening, and I'll see
821
00:36:36,715 --> 00:36:37,525
you in the next episode.
