TRANSCRIPT 🔗
WEBVTT
00:00:00.080 --> 00:00:10.000
We need to understand that if we want AI to be helping us, we need to put in our effort and our our time to correct Yeah, to build the system first.
00:00:15.839 --> 00:00:16.559
Yeah, let's do it.
00:00:17.920 --> 00:00:18.320
Yeah, you see.
00:00:26.399 --> 00:00:28.719
More appropriate for the brand today.
00:00:29.679 --> 00:00:29.839
Okay.
00:00:30.399 --> 00:00:31.440
See now I'm excited.
00:00:31.679 --> 00:00:37.679
I think what's really good about today's exercise is that I'm gonna question all the numbers, right?
00:00:37.759 --> 00:00:39.200
Yeah, what's the lead source?
00:00:39.280 --> 00:00:40.399
What's this, what's that?
00:00:40.880 --> 00:00:43.280
Yeah, you'll try to understand your data a bit better.
00:00:43.439 --> 00:00:50.240
So actually, yeah that's the underpin of the whole thing of automation, right?
00:00:50.560 --> 00:00:53.200
Your data, data is the most important thing.
00:00:57.520 --> 00:01:00.960
Hi everyone, welcome to the Code Rift Podcast.
00:01:01.119 --> 00:01:09.200
I'm Eric, the vibe coder, and with me I have Yao Hong, my AI orchestrator, and Lin, who is the founder of Dr.
00:01:09.359 --> 00:01:09.760
Bax.
00:01:10.319 --> 00:01:11.439
So welcome Lin.
00:01:11.519 --> 00:01:14.879
Uh, do you mind just sharing a bit more about yourself and Dr.
00:01:15.040 --> 00:01:15.760
Bags as well?
00:01:17.040 --> 00:01:20.400
Right, thank you so much, Eric and Yao Hong, for doing this with me.
00:01:20.640 --> 00:01:24.719
Um, I am the owner of a luxury restoration company.
00:01:24.879 --> 00:01:31.040
We specialize in cleaning, coloring, and repairing bags and shoes.
00:01:31.359 --> 00:01:35.680
Um we are in the luxury brand segment.
00:01:35.760 --> 00:01:46.239
So we on a daily basis there are ladies, men who bring their bags and shoes um for us to upkeep and hopefully do some magic for them as well.
00:01:46.319 --> 00:01:46.799
Yeah.
00:01:47.040 --> 00:01:51.439
So that's the business that I have been in for the past 11 plus years now.
00:01:51.760 --> 00:01:52.400
Yeah.
00:01:52.799 --> 00:01:53.280
Wow.
00:01:53.599 --> 00:01:54.640
All right, cool.
00:01:54.719 --> 00:01:57.519
And and before this, we had a nice chat as well.
00:01:57.920 --> 00:02:05.120
Could you just share a bit about your motivation for you know getting on this call with us and sharing with the rest of the world as well?
00:02:06.000 --> 00:02:14.479
I got reconnected with Yao Kung some months ago, and he kind of like urged me and pushed me to like automate some of my stuff.
00:02:14.960 --> 00:02:16.240
S T U F F.
00:02:17.120 --> 00:02:23.520
So um, and I had a deep thought about it, and it got me really interested actually.
00:02:23.759 --> 00:02:38.800
So at the same time, I'm also doing this like post system um to link up my customer service like from the front end all the way to the back end, um, back of house, and then back to our um customers again.
00:02:39.120 --> 00:02:45.120
Yeah, so um
Load full transcript
everything is in progress now, and I'm seeing a good results.
00:02:45.280 --> 00:02:58.000
Um, we're trying to automate some of our replies, we're trying to gather some of the data that we have had for the past 11-ish years and putting it into this central system.
00:02:58.240 --> 00:03:02.719
Now, but at the same time, I all my staff are mixed up.
00:03:02.960 --> 00:03:05.439
S T A F F, yeah.
00:03:05.759 --> 00:03:14.000
Learning how to use this new system, um, really pushing themselves to connect the different dots together.
00:03:14.479 --> 00:03:23.520
So I'm thinking like how as a founder and as a steward of the company, I can help value add um for my people.
00:03:24.000 --> 00:03:33.120
Yeah, and I know Lynn, you mentioned that you you would eventually hope for a fully automated dashboard where you don't have to ask anyone, you don't have to press any buttons.
00:03:33.360 --> 00:03:33.599
Yes.
00:03:33.759 --> 00:03:42.000
Um, but I think just for the purpose of this one hour, uh, we also uh asked you to export some of your data for us.
00:03:42.080 --> 00:03:46.879
Uh we've cleaned it up already, so that's uh so no one's uh details are going to be leaked.
00:03:47.120 --> 00:03:50.479
Um but we're just going to briefly see what we can do in an hour.
00:03:50.719 --> 00:04:07.840
Our goal for this is really just to show everyone and hopefully more business owners as well that you might not need to build a full production app to make your life easier, but at least knowing the full gamut of like what's possible, I think we'll will greatly improve your working life in some sense.
00:04:08.000 --> 00:04:08.479
Yeah.
00:04:08.800 --> 00:04:10.639
Yes, I look forward to that.
00:04:11.039 --> 00:04:11.439
Yeah.
00:04:11.680 --> 00:04:12.800
Alright, alright, let's go.
00:04:12.960 --> 00:04:15.520
Alright, so I'm gonna just share my screen.
00:04:15.759 --> 00:04:18.160
I have this thing called warp.
00:04:18.560 --> 00:04:23.199
Warp is basically another form of terminal, but Yao Hong asked me to download this the other time.
00:04:23.279 --> 00:04:26.800
So I'm just going to uh so you can have taps, yeah.
00:04:26.959 --> 00:04:31.439
Yeah, so and and don't have to worry about finding your window.
00:04:32.000 --> 00:04:34.399
Leno is like, why is the screen so black?
00:04:37.279 --> 00:04:38.399
Don't read my mind.
00:04:40.000 --> 00:04:41.279
I'm sure many people are thinking that.
00:04:42.000 --> 00:04:44.480
You could change color lah, you could change it to white if you really want.
00:04:44.639 --> 00:04:46.319
Or pink, pink, pink also can yeah.
00:04:46.720 --> 00:04:47.439
Yeah, let's do it.
00:04:48.480 --> 00:04:48.800
Pink on.
00:04:48.879 --> 00:04:49.279
Yeah, you see.
00:04:49.519 --> 00:04:49.680
Wow.
00:04:54.800 --> 00:04:56.079
Okay, very nice.
00:04:57.279 --> 00:05:00.399
More appropriate for the brand today uh point.
00:05:00.720 --> 00:05:00.879
Okay.
00:05:00.959 --> 00:05:02.480
I mean see now I'm excited.
00:05:02.720 --> 00:05:03.360
Yes, all right.
00:05:03.519 --> 00:05:04.800
So put to the black.
00:05:05.120 --> 00:05:08.639
So Claude basically released this new thing called uh Claude Auto.
00:05:09.600 --> 00:05:14.399
Which is which, if you look at this little chart here, hopefully it's simple enough to understand.
00:05:15.199 --> 00:05:24.000
In the previous episode, we used this thing called bypass permissions, which is at the bottom right here, which is as you can see, very low on safety, um, but very high on task autonomy.
00:05:24.079 --> 00:05:33.040
So we built Brian and oil um analysis app in a very short amount of time, but that was actually not the safest thing to do, especially with company data.
00:05:33.279 --> 00:05:33.439
Right?
00:05:34.000 --> 00:05:43.439
So now with this thing called auto mode, as you can see, my mouse, uh, it basically goes up in terms of safety, yet still retaining some of the task autonomy uh that you can do.
00:05:43.839 --> 00:05:51.839
So before this session, uh Lynn mentioned I think one of the things that she wanted to do was to create a dashboard, right?
00:05:52.079 --> 00:05:59.120
Do you mind just explaining a bit more on this dashboard, especially for those who are just like listening in and might not see our screen?
00:05:59.600 --> 00:06:06.079
So we've been around for 11 years, and obviously we have um we've been very grateful for our journey.
00:06:06.319 --> 00:06:10.720
We have a lot of clients who are repeated clients who come to us regularly.
00:06:11.040 --> 00:06:17.519
At the same time, um there are clients who reach out to us through different platforms as well.
00:06:18.160 --> 00:06:20.399
So on a monthly basis, Dr.
00:06:20.560 --> 00:06:28.639
Bex actually spends some ad dollars on Google, on Meta, and also on IG itself.
00:06:28.879 --> 00:06:41.279
Moving forward, there are plans for us to um understand our data better and then spend money on ad dollars or advertising budget on different other different platforms.
00:06:41.519 --> 00:06:46.800
But until then, we want to very be very cautious about how we spend our money as well, right?
00:06:46.879 --> 00:06:51.680
We want to reach the right audience, we want to reach new audience.
00:06:51.920 --> 00:06:52.560
Yeah.
00:06:53.120 --> 00:07:00.800
So I do really want to understand is our marketing dollars really working for us now?
00:07:01.439 --> 00:07:07.519
For example, like if I were to spend X amount of money on um Google search, right?
00:07:07.680 --> 00:07:21.759
The the words, the keywords, which keyword actually um ultimately not only give me the leads, but also give me a confirmed um service closed.
00:07:22.000 --> 00:07:24.160
Yeah, a case one, for example.
00:07:24.399 --> 00:07:46.319
Um I would also like to um understand in one at one glance, like instead of pulling data from different sources, I hope to see on a dashboard which, for example, is it Google or Meta that's given giving me um better results?
00:07:46.720 --> 00:07:47.040
Yeah.
00:07:47.279 --> 00:07:53.040
Is it a real that's giving me better results as compared to uh word search?
00:07:53.680 --> 00:07:54.319
Yeah.
00:07:54.639 --> 00:08:07.600
So if I if you can if you guys can work this out for me, then you know I I don't need my staff to spend so many hours pulling in the data, like how we traditionally do it.
00:08:07.839 --> 00:08:20.879
And also I'm able to write it, I mean like write down the formulas in so that I know for sure, because like different platforms um you you calculate the ROI differently, right?
00:08:21.040 --> 00:08:24.879
So if we can already write this all in, then that would be perfect.
00:08:25.199 --> 00:08:28.560
And how much time does your staff spend on this these days?
00:08:28.800 --> 00:08:36.879
Um to be honest, it is very um it is not a regular thing that we do.
00:08:37.120 --> 00:08:37.440
Okay.
00:08:37.840 --> 00:08:38.159
Yeah.
00:08:38.399 --> 00:08:41.279
So how often it should actually be regular.
00:08:41.600 --> 00:08:42.159
Correct, yeah.
00:08:42.240 --> 00:08:48.720
So I'm actually trying to build it, but as I said mentioned just now, right, to be really, really, really honest.
00:08:48.879 --> 00:08:52.799
Everyone is working so hard um at this point in time.
00:08:52.960 --> 00:08:56.000
Yeah, we're trying to build the ERP system.
00:08:56.639 --> 00:09:09.600
Um, we're trying to educate our our colleagues to adhere to certain like new standards that we are trying to build and learn and keep strictly to the different processes.
00:09:09.840 --> 00:09:12.240
This itself is already taking up a lot of time.
00:09:12.399 --> 00:09:16.960
Yeah, on top of all the daily tasks that um my managers are doing.
00:09:17.279 --> 00:09:20.320
Yeah, so I do hope to have a regular meeting.
00:09:20.559 --> 00:09:25.919
Yeah, so if they were to do this, then they would it would be quite painful for me as a boss, lah.
00:09:26.080 --> 00:09:32.320
Maybe they will have to take like two days, I would think, yeah, to churn data like that for me.
00:09:32.559 --> 00:09:34.639
Because it's not on a regular basis, right?
00:09:34.879 --> 00:09:40.960
So they have to download all the data and then put it into different matrix, yeah, and then come back to me.
00:09:41.440 --> 00:09:41.679
Yeah.
00:09:41.919 --> 00:09:43.120
Yeah, for sure, for sure.
00:09:43.279 --> 00:09:47.440
And I think this is a classic case of how AI works.
00:09:47.919 --> 00:09:50.559
Oh, yeah, yes, how SME works, I guess.
00:09:51.039 --> 00:09:55.840
Yeah, very, very uh see that every day.
00:09:56.080 --> 00:09:57.679
Always fighting fires.
00:09:59.440 --> 00:10:12.080
Um yeah, and and also I guess how AI also would be able to uh free you up not just for the work you're doing now, but for the work that you would not have been able to do otherwise.
00:10:12.320 --> 00:10:12.559
Yeah.
00:10:12.799 --> 00:10:20.000
What I'm gonna do is I'm going to um just kind of copy whatever we just talked about here.
00:10:20.159 --> 00:10:20.399
Okay.
00:10:20.639 --> 00:10:24.240
There are applications out there that let you talk to your computer.
00:10:25.360 --> 00:10:32.799
So honestly, whatever you just said would have been processed quite well by an LLM.
00:10:32.879 --> 00:10:44.000
So what I'm gonna do is I'm going to switch to this thing called plan mode, pressing shift and tap, um, shift and tap to switch into plan mode, and then I'll just put it in.
00:10:44.159 --> 00:10:45.919
And so you can see it's quite messy, right?
00:10:46.000 --> 00:10:53.279
Like it like um not that your thoughts are oh yeah, my my thoughts are messy.
00:10:53.600 --> 00:10:53.919
Okay.
00:10:58.720 --> 00:11:04.720
Okay, I'm just going to add in that the the main task is to make a new dashboard for this, right?
00:11:04.879 --> 00:11:10.320
Based on what you told us, and then based on uh a bit of what you typed to us as well.
00:11:10.480 --> 00:11:17.759
But uh mostly based on what you told us, uh, which is yeah, what we talked about over WhatsApp before this call.
00:11:18.159 --> 00:11:23.279
Okay, so so we're just gonna go into a plan mode, and what are we building in this session?
00:11:23.440 --> 00:11:27.759
A live working dashboard connected to real data or a polished demo prototype.
00:11:28.159 --> 00:11:39.279
Um so I'm going to Okay, so um Okay, we don't have any APIs, which is basically how your data would connect in a live way, right?
00:11:39.360 --> 00:11:41.360
Without you having to export data.
00:11:41.919 --> 00:11:45.120
So I think we'll just do a working prototype with sample data.
00:11:45.360 --> 00:11:50.480
And then for data sources, uh we already have a clean uh data source.
00:11:50.559 --> 00:11:53.120
So I'm just gonna copy the file name and paste it in here.
00:11:53.440 --> 00:11:53.759
Okay.
00:11:54.159 --> 00:11:54.720
Yeah.
00:11:55.440 --> 00:11:59.120
But right, if we have access to the API, then it will be live.
00:11:59.919 --> 00:12:08.879
So you would have to check with your team tomorrow after you installing clock code and then you can uh access everything via API.
00:12:09.200 --> 00:12:09.519
Okay.
00:12:09.679 --> 00:12:10.000
Yeah.
00:12:10.240 --> 00:12:11.440
But I also think what you're doing.
00:12:11.600 --> 00:12:12.720
Basically they're not scared of me.
00:12:12.799 --> 00:12:14.799
Like every day I ask them a different thing.
00:12:15.759 --> 00:12:16.960
That's okay, that's normal.
00:12:17.360 --> 00:12:18.159
The boss is 11.
00:12:18.720 --> 00:12:19.039
Okay.
00:12:19.840 --> 00:12:21.440
They're quite receptive, eh?
00:12:22.799 --> 00:12:23.279
Cool, huh?
00:12:23.840 --> 00:12:24.559
Yeah, I think so.
00:12:24.879 --> 00:12:36.399
No, as in I think I think a very important trait of being a company that is you know future proof is one that is also thinking about how it can help its employees to grow.
00:12:37.600 --> 00:12:38.639
And I think this is yeah.
00:12:38.879 --> 00:12:45.679
And my team, they are really like, I think I'm really thankful for them, like, because they are they really look for problems.
00:12:46.080 --> 00:12:53.120
Like they really they really feed back to the developer and say, you know, there's a problem here, there's a problem there, like how can we do it better?
00:12:53.279 --> 00:12:54.879
And yeah, vice versa.
00:12:55.120 --> 00:12:57.519
So happy to see.
00:12:58.399 --> 00:13:02.799
Yeah, and I do want um definitely my brand to be future proof.
00:13:03.600 --> 00:13:04.240
Yes.
00:13:05.360 --> 00:13:14.720
Yeah, and and if you're there, there are some organizations out there that are that are fully using plot code.
00:13:14.879 --> 00:13:19.440
So these are very, very future-oriented organizations.
00:13:19.600 --> 00:13:31.600
Um and and even for the non-technical folks they are that are using it, they they find their productivity kind of skyrocketing, and they also find themselves growing because they are working in new ways, basically.
00:13:31.840 --> 00:13:32.320
Yes.
00:13:32.559 --> 00:13:36.159
So yeah, that's just something to think about.
00:13:36.879 --> 00:13:46.320
So the idea is that you are doing things, not just automating the old ways, but maybe you start questioning does it make sense to do even do it this way?
00:13:46.559 --> 00:13:46.720
Right?
00:13:46.799 --> 00:13:48.080
Is there something better?
00:13:48.159 --> 00:13:54.720
Yeah, and yeah, when you start trying to solve problems, that we actually can be quite interesting what people do.
00:13:55.440 --> 00:13:55.919
Yeah.
00:13:56.720 --> 00:13:59.840
So here's what the here's what Clock Code is proposing.
00:13:59.919 --> 00:14:00.240
Okay.
00:14:00.399 --> 00:14:07.759
Uh, there are 659 deals with source attribution, funnel stage, deal values, response times.
00:14:07.919 --> 00:14:11.919
Uh, it already has found that WhatsApp is 89% of one deals.
00:14:12.320 --> 00:14:16.960
Uh, Instagram and Facebook bring leads that barely convert, so that is a funnel.
00:14:17.919 --> 00:14:21.519
Um so you don't I mean I I wouldn't trust this immediately.
00:14:21.600 --> 00:14:25.120
So feel free to feel free to just jump in as well, Lynn.
00:14:25.440 --> 00:14:30.879
Um then there were four 404 deals that were stuck in engaged.
00:14:31.120 --> 00:14:38.720
So that's a big opportunity there, with response time varying wildly, which likely correlates with conversion.
00:14:38.960 --> 00:14:42.879
So, what it's gonna try to build is a single HTML dashboard file.
00:14:43.039 --> 00:14:46.240
How I see it, it's just something you can open and then it opens your your browser.
00:14:46.639 --> 00:14:53.120
I think it's it's quite cool because it already kind of realized that I mean we are doing a live session now, so it's not gonna over overbuild it for us.
00:14:54.399 --> 00:14:54.879
Yeah.
00:14:55.200 --> 00:14:58.080
But it's a good uh kind of like a proof of concept, right?
00:14:58.159 --> 00:15:02.080
That you can bring it to the team to idea upon it and without spending too much time.
00:15:02.399 --> 00:15:02.799
Yeah.
00:15:02.960 --> 00:15:03.600
Yeah.
00:15:03.919 --> 00:15:06.879
And ideally, we would have done a design phase before this.
00:15:06.960 --> 00:15:10.639
I would kind of draw it out as well, like how I want it to look like.
00:15:10.960 --> 00:15:15.919
But we'll also just trust the system and see what it comes up with based on its own.
00:15:16.480 --> 00:15:18.799
Let's scroll down and see what's the build plan.
00:15:18.879 --> 00:15:26.960
Yeah, so um this HTML dashboard file is going to answer six of your questions with charts and KPI cards.
00:15:27.200 --> 00:15:34.159
Uh so what it will do is parse the Excel to JSON and build a section by section, which okay, we don't have to go through that.
00:15:34.399 --> 00:15:38.639
Um so this is a plan that uh we would typically read um as well.
00:15:38.879 --> 00:15:40.559
So you run Dr.
00:15:40.879 --> 00:15:45.200
Bags, uh, but has no clean way to see which channel brings revenue versus enquiries.
00:15:45.360 --> 00:15:49.600
Um managers need two days to do this, uh, or even more, right?
00:15:49.759 --> 00:15:51.440
You have a sanitized Excel report.
00:15:51.519 --> 00:15:58.559
Yes, the goal is to build a visual marketing dashboard within one hour, and that you can glance at and understand where the money where your money is working.
00:15:58.799 --> 00:15:59.120
Okay.
00:15:59.919 --> 00:16:04.720
Um and then there's some of these key stories here, which we talked about.
00:16:05.039 --> 00:16:11.279
They are telling you the kind of um software packages or software that they'll use.
00:16:12.000 --> 00:16:15.279
Um so step one, they will they will read.
00:16:15.679 --> 00:16:17.360
Is that what you do all the time, Yahoo?
00:16:17.919 --> 00:16:18.480
Yes.
00:16:18.799 --> 00:16:19.039
Wow.
00:16:19.279 --> 00:16:29.440
In fact, this step is very important because this step you you need to kind of read the plan and figure out whether it's going the right direction and then you start changing.
00:16:29.840 --> 00:16:30.559
Yes, okay.
00:16:30.799 --> 00:16:38.480
Because a lot of a lot of times I see um folks, they actually just trade to solutioning, right?
00:16:38.559 --> 00:16:42.960
And you end up spending a lot of time trying to course correct along the way.
00:16:43.279 --> 00:16:49.200
But it's actually easier when you do a proper plan, you start from there and then and then you start making changes.
00:16:49.279 --> 00:16:52.399
Like, for example, some of these things, if you don't like it, you should just highlight.
00:16:55.519 --> 00:17:03.200
For example, now let's say we go down and say that okay, we want to step two, build the dashboard HTML, row one, you have KPI cards, right?
00:17:03.519 --> 00:17:08.640
So this part here, you you start thinking whether it makes sense to have total leads, right?
00:17:08.799 --> 00:17:13.359
Uh one deals and win rate percentage,
total revenue, right, average response time.
00:17:13.680 --> 00:17:16.160
And please jump in anytime, Lynn, uh, as you're reading as well.
00:17:16.400 --> 00:17:21.920
Like if anything jumps out, just just say, oh, actually, I don't really want to see it this way, I want to see it the other way, right?
00:17:22.000 --> 00:17:23.519
And then you yeah.
00:17:24.160 --> 00:17:31.359
Now understand why why my developer always asks us to give constant feedback whenever like something is launched.
00:17:31.599 --> 00:17:42.400
Yeah, so yeah, like how to better communicate with him would be actually to draw a plan or to to explain to him.
00:17:42.640 --> 00:17:52.400
So as we build our entire ERP, nobody in the world, I I don't think there's a restoration company in the world that has an ERP system as tight as ours.
00:17:52.720 --> 00:17:58.799
Because um it is it is a traditional business in 2026, right?
00:17:59.440 --> 00:18:12.960
So for a restoration business to run in Singapore, fully in Singapore, um, and not like what our competitors do to run overseas, we need to really watch the KPIs.
00:18:13.119 --> 00:18:13.279
Yeah.
00:18:14.079 --> 00:18:25.599
So like that is the business, that is a big part of what I do on a daily basis, yeah, to make sure that the team runs effectively and efficiently.
00:18:25.759 --> 00:18:26.160
Yeah.
00:18:26.319 --> 00:18:32.160
So all these little things that I'm seeing here would be connected to the back of the house.
00:18:32.400 --> 00:18:32.799
Yeah.
00:18:32.960 --> 00:18:33.599
In the end.
00:18:33.680 --> 00:18:35.759
So yeah, I mean, like, thank you for doing this.
00:18:35.839 --> 00:18:39.119
I will continue reading, and if I have continue to tell you.
00:18:39.279 --> 00:18:39.519
Yeah.
00:18:39.920 --> 00:18:43.680
In in real life, uh, what would happen is that this is just the first layer.
00:18:43.839 --> 00:18:44.079
Yeah.
00:18:44.559 --> 00:18:49.920
You can then add the data from other sources uh from ERP, and then you make it even more robust.
00:18:50.559 --> 00:18:51.039
Yeah, yeah.
00:18:51.200 --> 00:18:56.880
Like obviously, that one you have to sit down and think quite deeply now how you how that can be done.
00:18:56.960 --> 00:18:58.400
Uh, what needs to go in?
00:18:58.480 --> 00:18:59.039
Yeah.
00:18:59.599 --> 00:19:04.720
Alright, so row one, KPI cards, row two, channel performance.
00:19:04.960 --> 00:19:12.319
Uh, row three would be the funnel, which is the funnel visualization, from a new inquiry to being engaged and being won or lost.
00:19:12.559 --> 00:19:22.640
Row four is the revenue and timing, which is your revenue by channel, and then uh timing-wise would be the deals by the day of the week to find best closing days.
00:19:22.799 --> 00:19:23.440
Interesting.
00:19:23.680 --> 00:19:26.240
Uh row five would be response time impact.
00:19:26.480 --> 00:19:31.440
So uh scatter or grouped bar, response time versus conversion outcome.
00:19:31.680 --> 00:19:34.240
Row six,
campaign performance.
00:19:34.319 --> 00:19:43.920
Uh so there'll be a table with your campaign name, leads, wins, conversion rates, revenue, and answers which ads or keywords work.
00:19:44.000 --> 00:19:47.440
Okay, then there'll be step three, which is the polish and brand, which will be the brand colours.
00:19:47.599 --> 00:19:50.000
Do you have any design materials?
00:19:50.240 --> 00:19:52.640
Uh website website thing.
00:19:53.039 --> 00:19:54.400
We do, we have a website.
00:19:54.640 --> 00:19:57.279
Okay, drbs.com.
00:19:57.920 --> 00:19:58.799
Perfect.
00:19:59.119 --> 00:20:00.559
Um, okay.
00:20:01.119 --> 00:20:05.359
I'm going to ask Claude to oh, okay, never mind.
00:20:05.599 --> 00:20:07.599
Okay, I'll just take a screenshot first for later.
00:20:07.839 --> 00:20:10.960
Just take a screenshot and put it in a pick up as you pick out the colors.
00:20:11.359 --> 00:20:15.200
Yeah, but it's I'll just let it go first because now I can't add a photo.
00:20:15.759 --> 00:20:18.720
Okay, so you'll use the brand colors and all mobile friendly.
00:20:18.880 --> 00:20:20.559
Oh, we don't really need that, but sure.
00:20:20.720 --> 00:20:22.160
Okay, why not?
00:20:22.480 --> 00:20:29.680
Um so the files is gonna create some files, it's gonna refer to some files, which is the data files.
00:20:30.079 --> 00:20:49.200
Um there's a verification where you run a Python script uh on my computer, and then it will open this thing in the browser and you check the dashboard and verify that no customer names are leaked, uh, which we have done already.
00:20:49.440 --> 00:20:52.240
And then you can test on phone.
00:20:52.480 --> 00:20:56.799
Okay, no, I don't know if you can test on your phone, but sure.
00:20:57.119 --> 00:20:58.720
Um let's go.
00:20:58.880 --> 00:21:04.559
Okay, so we're just going to Can we also give like advice on what we should do?
00:21:04.960 --> 00:21:09.119
Yes, what you don't don't don't do that now.
00:21:09.359 --> 00:21:10.160
Just build it first.
00:21:10.640 --> 00:21:11.200
Okay, sure.
00:21:11.759 --> 00:21:13.200
Remember that thought, remember, hold that thought, yeah.
00:21:13.440 --> 00:21:14.319
Clear context and go.
00:21:14.559 --> 00:21:20.799
Yeah, because what happens is that the context is actually uh uh very critical in this stage.
00:21:20.960 --> 00:21:26.799
Yeah, you don't want to give it too much context until it goes uh it gets uh bit confused.
00:21:27.279 --> 00:21:38.079
Okay, additional thoughts, um advice and actionable uh insights insights on what to do based on the data.
00:21:38.720 --> 00:21:41.920
Um just wait for it to do it.
00:21:42.079 --> 00:21:46.960
I'll just approve it's yeah, you didn't you didn't do the uh accept auto.
00:21:47.359 --> 00:21:50.960
Actually, this auto mode thing is actually not very auto.
00:21:52.079 --> 00:21:52.960
Oh, what is it?
00:21:53.200 --> 00:21:54.000
I haven't tried yet.
00:21:54.079 --> 00:21:54.319
Yeah.
00:21:54.640 --> 00:21:56.559
It is uh getting me to approve a lot of things.
00:21:56.799 --> 00:22:00.720
I think one thing to note is that uh Clockco is not just For coding, right?
00:22:00.799 --> 00:22:07.759
You can use it to like move files around, to rename files, to open files, even to do research for you.
00:22:11.200 --> 00:22:17.680
Market research, uh, we did that last episode, you know, look at what competitors are doing, grab prices off.
00:22:18.000 --> 00:22:24.880
If you think about marketing, you could actually look at what other people are selling or talking about.
00:22:25.200 --> 00:22:25.519
Yeah.
00:22:26.240 --> 00:22:34.640
Or the number of uh like uh if you monitor their polls and see how's the uh results from what they are doing, you know.
00:22:35.680 --> 00:22:37.279
So actually quite quite a lot of things we could do.
00:22:37.519 --> 00:22:38.960
Yeah, yeah, it's so fun.
00:22:39.519 --> 00:22:41.279
Yes, it is quite fun.
00:22:43.519 --> 00:22:52.640
Um maybe as as we usually do in each episode, we have uh another task that we just try to do, try to do alongside this.
00:22:52.960 --> 00:22:54.640
Is that anything that pops into your mind?
00:22:55.279 --> 00:22:55.759
Yeah, yeah, yeah.
00:22:55.839 --> 00:22:59.039
I want to do the before-after picture thing that you suggested.
00:22:59.440 --> 00:23:01.359
Okay, okay, before after picture.
00:23:01.519 --> 00:23:03.759
Because we actually take before all the things.
00:23:03.920 --> 00:23:06.799
Okay, then so where can I get this fast?
00:23:07.200 --> 00:23:08.319
Um, Instagram.
00:23:08.559 --> 00:23:09.599
Okay, I'll go to Dr.
00:23:09.759 --> 00:23:11.279
Bags to get your style.
00:23:11.440 --> 00:23:14.079
Yeah, and then I do need some before and after photos.
00:23:14.160 --> 00:23:14.880
Is it here as well?
00:23:15.200 --> 00:23:18.160
Um yeah, one of the there are some posts that has okay.
00:23:18.319 --> 00:23:19.839
Which one is should I open?
00:23:21.119 --> 00:23:23.119
At the bottom, uh I mean you scroll down.
00:23:23.279 --> 00:23:23.519
Yeah.
00:23:23.759 --> 00:23:26.400
Uh that shoes the shoes before after.
00:23:26.880 --> 00:23:27.200
Yeah.
00:23:27.440 --> 00:23:27.680
Okay.
00:23:28.640 --> 00:23:29.839
You change the colour.
00:23:30.240 --> 00:23:30.720
Yeah.
00:23:31.039 --> 00:23:31.519
Alright.
00:23:31.680 --> 00:23:33.440
Well, from yellow to pink.
00:23:33.599 --> 00:23:34.240
Very cute.
00:23:34.400 --> 00:23:34.640
Okay.
00:23:35.200 --> 00:23:36.880
It was it was pink.
00:23:37.119 --> 00:23:38.079
Oh, sorry.
00:23:38.240 --> 00:23:39.519
It became yellow.
00:23:39.920 --> 00:23:40.319
Huh?
00:23:40.480 --> 00:23:43.039
No, before it's yeah.
00:23:43.279 --> 00:23:45.119
Oh, but your original colour was pink.
00:23:45.359 --> 00:23:48.480
Yeah, I I think the original colour was lightly pink.
00:23:48.720 --> 00:23:51.839
Wait, doesn't it write before as yellow and after is pink?
00:23:52.160 --> 00:23:54.319
I don't know if you're just it became yellow.
00:23:54.559 --> 00:23:55.920
It is colored and it became yellow.
00:23:56.319 --> 00:23:57.359
It became yellow.
00:23:57.519 --> 00:24:00.559
Yeah, you notice the I get it.
00:24:03.200 --> 00:24:04.640
Hue is quite dirty on the left side.
00:24:04.880 --> 00:24:10.000
Okay, you can see how how much I know about skin eyes.
00:24:10.319 --> 00:24:10.640
Yeah.
00:24:10.799 --> 00:24:10.960
Yeah.
00:24:11.599 --> 00:24:12.799
OCD people is like that.
00:24:15.599 --> 00:24:17.119
Okay, I'm gonna open a new one.
00:24:17.279 --> 00:24:19.039
Clot permission auto.
00:24:19.359 --> 00:24:23.599
Um and I'm going to say, I'm just gonna prompt hi Claude.
00:24:23.680 --> 00:24:29.279
Uh, we want to build something that takes uh before and afterback photos to write social media posts.
00:24:29.759 --> 00:24:36.720
Um I have a few photos that I'm going to kind of uh download and drag into a folder.
00:24:36.880 --> 00:24:41.519
Can you just open that folder for me as I drag some photos in?
00:24:41.680 --> 00:24:48.720
And then I'm also gonna give you some examples of uh previous writings uh from their Instagram page.
00:24:48.960 --> 00:24:50.160
It's like talking to your best friend.
00:24:50.319 --> 00:24:50.720
Yeah, yeah.
00:24:50.799 --> 00:24:52.480
It's just like talking to someone like it's it's not.
00:24:52.720 --> 00:24:53.599
Your soulmate.
00:24:53.839 --> 00:24:54.960
Yeah, yes.
00:24:55.839 --> 00:25:03.599
Um I'm not gonna go there, but uh I would think that in a couple of months a lot of us will have to go and see psychiatrists.
00:25:04.640 --> 00:25:13.039
Yeah, um, let's not get too dependent on this, but yeah, I will paste in what I just said um and then I'll let it open a folder for me.
00:25:13.200 --> 00:25:16.079
Okay, I'm going to just go back and approve more stuff.
00:25:16.400 --> 00:25:16.720
Oh.
00:25:17.359 --> 00:25:18.720
Okay, that's what always happens.
00:25:18.880 --> 00:25:21.200
We always get distracted because clawed code is very fast.
00:25:21.440 --> 00:25:25.039
Oh, I seriously think my attention span is much shorter these days.
00:25:25.359 --> 00:25:26.640
So sorry, Lynn.
00:25:26.720 --> 00:25:36.000
Uh we are also breaking your attention span, but we're going to go back uh towards the marketing dashboard, and we're gonna get you to comment on it.
00:25:36.319 --> 00:25:41.680
So for those that don't see the screen, this is a marketing dashboard for Dr.
00:25:41.839 --> 00:25:42.319
Bax.
00:25:42.799 --> 00:25:52.400
It shows that we have 659 leads, one 219 deals, which is a 33% win rate, and there's an average response time of 1 hour 44 minutes.
00:25:52.720 --> 00:25:53.680
That one you can keep.
00:25:53.839 --> 00:25:55.200
Yeah, leads by channel.
00:25:55.440 --> 00:25:56.400
That's very slow there.
00:25:57.440 --> 00:25:59.279
1 hour 44 response time.
00:25:59.599 --> 00:26:00.640
Or is it uh two ways though?
00:26:00.720 --> 00:26:04.960
Is it two ways or okay first reply time?
00:26:05.039 --> 00:26:06.640
Okay, there's leads by channel.
00:26:06.880 --> 00:26:11.920
WhatsApp is the most uh at 405, uh 166.
00:26:12.079 --> 00:26:12.799
Lead source.
00:26:12.880 --> 00:26:14.079
What is lead source?
00:26:14.720 --> 00:26:16.160
Anyone knows?
00:26:17.359 --> 00:26:18.079
I don't know.
00:26:18.720 --> 00:26:20.960
Okay, there's a source which says lead source.
00:26:21.200 --> 00:26:21.680
That's why.
00:26:22.240 --> 00:26:23.920
So let's leave it there.
00:26:24.079 --> 00:26:27.279
Uh Instagram at 58, Facebook at 30.
00:26:27.440 --> 00:26:29.680
Uh I'm just gonna uh oh sorry, on the right side.
00:26:29.839 --> 00:26:35.599
I think what's really good about today's exercise is that I'm gonna question all the numbers, right?
00:26:35.680 --> 00:26:37.119
Yeah, what's the lead source?
00:26:37.200 --> 00:26:38.319
What's this, what's that?
00:26:38.799 --> 00:26:41.200
Yeah, you'll try to understand your data a bit better.
00:26:41.359 --> 00:26:42.400
So you went into it.
00:26:42.559 --> 00:26:48.160
Actually, yeah, that's the underpin of the whole thing of automation, right?
00:26:48.480 --> 00:26:50.559
Your data, data is the most important thing.
00:26:50.720 --> 00:26:51.200
Yeah.
00:26:51.440 --> 00:26:55.519
If if your data is not right, then your output or your processes won't be right.
00:26:55.839 --> 00:26:56.480
Correct.
00:26:56.799 --> 00:26:59.839
And Yao Hong, here's where I have a question for you, also, right?
00:27:00.000 --> 00:27:03.200
Because you know, this is just one month of data, right?
00:27:03.519 --> 00:27:08.240
So even for one month of data, we are like questioning whether it's true.
00:27:08.400 --> 00:27:10.079
We are we are getting confused.
00:27:10.160 --> 00:27:16.319
Like, how would you recommend a company do this for like, I don't know, like a year's worth of data, right?
00:27:16.480 --> 00:27:17.440
It will get so confusing.
00:27:17.519 --> 00:27:19.279
And like, how do you like verify?
00:27:19.519 --> 00:27:21.200
I think we try to get it right the first time around.
00:27:21.279 --> 00:27:21.519
Yeah.
00:27:22.079 --> 00:27:26.880
Your initial one, you you must make sure that the data is clean, plug all the holes.
00:27:27.039 --> 00:27:29.599
I mean, it's it's literally data engineering, right?
00:27:29.680 --> 00:27:29.839
Yeah.
00:27:30.559 --> 00:27:32.960
We actually go down, it's plumbing, right?
00:27:33.039 --> 00:27:40.319
You have to clean the data sources, you've got to clean any transformations you have to get to what you want.
00:27:40.720 --> 00:27:44.160
No, which I find quite difficult as someone that's non-technical, right?
00:27:44.240 --> 00:27:50.400
And trying to even judge whether the data is clean and judge whether data is correct and and know what to look out for.
00:27:50.640 --> 00:27:58.720
But sometimes uh for businesses, because you you know the numbers intuitively, you can kind of catch quite fast whether it's something is wrong.
00:27:58.960 --> 00:27:59.119
Yeah.
00:27:59.359 --> 00:28:01.200
I mean, this transition period is important, right?
00:28:01.279 --> 00:28:03.119
Because that's what the government wants us to do as well.
00:28:03.359 --> 00:28:03.680
Correct.
00:28:04.079 --> 00:28:09.279
So so managers need to understand that this data needs to be really clean.
00:28:09.440 --> 00:28:19.920
And we need to understand that if we want AI to be helping us, we need to put in our effort and our time to correct to build the system first.
00:28:20.319 --> 00:28:20.720
Yeah.
00:28:21.119 --> 00:28:29.440
You know, I I think as business owners, um, it's very important that we are the engineer of this entire thing that we're looking at now.
00:28:30.799 --> 00:28:36.799
In fact, this is the part where most people say, Oh, AI is not good, then therefore I'm not gonna do anymore.
00:28:37.440 --> 00:28:41.519
Yeah, that's that's the part that most people but it's a it's a fallacy, right?
00:28:41.680 --> 00:28:42.799
Because yeah.
00:28:43.119 --> 00:28:43.359
Yeah.
00:28:45.519 --> 00:28:47.839
The difficult part is always I think now.
00:28:48.720 --> 00:28:56.240
Yeah, but if we were to really press on, um have good friends like Yao Hong and friends like Eric, then we would all win today.
00:28:57.599 --> 00:29:00.640
No, or maybe you could just try this with yourself, I mean, on your own.
00:29:00.880 --> 00:29:02.720
Yeah, but that would take take us 10 years.
00:29:04.319 --> 00:29:05.759
Then the world would be different.
00:29:06.640 --> 00:29:06.960
That's true.
00:29:07.119 --> 00:29:08.240
Yeah, that is true.
00:29:08.559 --> 00:29:09.440
Very good point there.
00:29:09.599 --> 00:29:10.720
Yao Hong, we still have a different thing.
00:29:10.880 --> 00:29:18.000
Actually, I quite uh quite a finding interesting that it says Facebook is only has 13.8% conversion rate.
00:29:18.079 --> 00:29:18.960
That's quite low.
00:29:19.200 --> 00:29:25.920
Yeah, so it's it's pretty interesting because most of our most of our call to action would bring us to WhatsApp.
00:29:27.200 --> 00:29:30.559
Ah okay, so actually the attribution is not correct already.
00:29:31.039 --> 00:29:39.039
That means in terms of the way you design the flow, you must attribute WhatsApp, must have attribution back to what uh Facebook.
00:29:39.599 --> 00:29:41.680
So I mean you can't tag it to WhatsApp, yeah.
00:29:41.839 --> 00:29:44.079
Yeah, so that's why I think this is weird.
00:29:44.319 --> 00:29:53.759
And also, I don't know, like because of the way we design our ERP system, we need to start.
00:29:53.920 --> 00:29:59.680
Remember, just like at the front, um, when Eric asked about the entire flow, right?
00:30:00.079 --> 00:30:03.759
My sales team have to start an order.
00:30:04.319 --> 00:30:15.279
And this order that we start might not have come from WhatsApp, like this specific WhatsApp number, it might have come from other sources, like other WhatsApp numbers that we have.
00:30:15.599 --> 00:30:22.000
But ultimately, maybe the system only captured like it came from resource.
00:30:22.640 --> 00:30:27.519
The system needs to have a bit more granularity that you may need to go back and redesign a bit.
00:30:27.599 --> 00:30:28.160
Yeah, good.
00:30:28.400 --> 00:30:32.079
I see we are we're uncovering some potential issues, yeah.
00:30:32.319 --> 00:30:32.640
Yeah.
00:30:32.799 --> 00:30:39.279
No, I I think it's very important that that Lynn you are like open to even thinking about all these changes that you have to make.
00:30:39.440 --> 00:30:41.440
But um let me just carry on first.
00:30:41.599 --> 00:30:44.000
Okay, because we we can talk about this forever.
00:30:44.319 --> 00:31:01.039
Uh so moving on to deal funnel, all leads is um enhancing okay, and 61% of deals engaged, 33% won, two percent lost, uh deal by channel, which uh revenue by channel, which is a bit off as well, yeah.
00:31:01.200 --> 00:31:05.920
Um, due to the attribution to WhatsApp, uh even though some came from Facebook.
00:31:06.079 --> 00:31:17.200
And then, of course, if you look at the deals, it starts very high at month in on Monday, it goes down uh all the way to Friday, and then it starts going up again on Saturday and Sunday.
00:31:17.440 --> 00:31:19.759
Um deals are the one in blue.
00:31:20.000 --> 00:31:21.440
Or leads are the one in blue, yeah.
00:31:22.000 --> 00:31:22.319
Yeah.
00:31:23.119 --> 00:31:24.960
So you see that actually quite interesting.
00:31:25.039 --> 00:31:25.200
Right?
00:31:25.440 --> 00:31:32.000
Sunday has uh quite like quite a lot of leads on Sunday, but the conversions from Sunday leads.
00:31:32.160 --> 00:31:32.640
I'm not sure.
00:31:32.720 --> 00:31:34.480
Does it trace the conversion?
00:31:34.799 --> 00:31:43.200
I mean, this looks normal to me because on Saturdays and Sundays, most Singaporeans will be at home, so they'll be texting us.
00:31:43.519 --> 00:31:45.920
Now, but my my office will be closed, right?
00:31:46.000 --> 00:31:57.200
So the sales team or or whoever is uh knows how to reply and has been in like my team is very robust, so we will be replying.
00:31:57.519 --> 00:32:04.960
But on Mondays, from Mondays to Fridays, we would be the customer service team would be back at work.
00:32:05.359 --> 00:32:07.279
So they'll close the deals, yeah.
00:32:07.839 --> 00:32:10.160
That's when like the bags come in as well.
00:32:10.400 --> 00:32:17.759
So because we do things fast by Friday, yeah, yeah, it will be cleared.
00:32:18.000 --> 00:32:23.759
Yes, and then we'll be doing other things like following up of orders, yeah, inquiries and things like that.
00:32:24.559 --> 00:32:25.920
Okay, cool, makes sense.
00:32:26.160 --> 00:32:26.319
Yeah.
00:32:26.480 --> 00:32:30.160
Um, and then next there's a response time versus conversion.
00:32:30.319 --> 00:32:32.079
I'll zoom out a little bit.
00:32:32.799 --> 00:32:38.240
So it shows that um for zero to five minutes.
00:32:39.200 --> 00:32:41.359
That well, how do you even
read this?
00:32:41.839 --> 00:32:42.880
Zero to five minutes.
00:32:43.119 --> 00:32:44.720
So you need to make it pink, Eric.
00:32:46.480 --> 00:32:47.359
I'm sorry.
00:32:47.599 --> 00:32:48.880
No, no, you don't have to.
00:32:49.039 --> 00:32:49.119
Okay.
00:32:49.359 --> 00:32:50.640
You don't have to, I was just thinking.
00:32:51.920 --> 00:32:52.640
Okay, okay.
00:32:52.720 --> 00:32:54.880
Yeah, I still don't I'm still trying to.
00:32:55.039 --> 00:32:56.240
Can you can you explain this, Lin?
00:32:56.400 --> 00:32:57.680
I mean, you are the boss here.
00:32:57.920 --> 00:32:59.599
Like I got Lao Hua.
00:32:59.759 --> 00:33:00.400
You need to make it bigger.
00:33:02.640 --> 00:33:10.079
Two of us can Okay, one hour bucket shows 40% conversion, higher than faster buckets.
00:33:10.720 --> 00:33:12.799
So I still can't see young men.
00:33:13.119 --> 00:33:13.440
Okay.
00:33:13.759 --> 00:33:14.640
I'm going in.
00:33:15.119 --> 00:33:15.279
Okay.
00:33:16.319 --> 00:33:17.680
Zooming in, zooming in.
00:33:18.000 --> 00:33:24.079
I guess the intent is higher when people talk longer on WhatsApp review.
00:33:24.400 --> 00:33:24.880
Yeah.
00:33:25.119 --> 00:33:26.720
So that's what the metric is trying to say.
00:33:26.799 --> 00:33:27.039
Yeah.
00:33:27.279 --> 00:33:30.640
But their insight is quite wrong because they're like, you don't need fast replies.
00:33:30.720 --> 00:33:32.720
But actually it's not.
00:33:32.880 --> 00:33:34.559
The one pass out 38%.
00:33:35.119 --> 00:33:35.920
Oh, I understand.
00:33:36.079 --> 00:33:37.839
Higher than faster baskets.
00:33:38.720 --> 00:33:42.319
It's the kind of customer that asks you a lot of questions, but then they will still give you the business.
00:33:42.559 --> 00:33:43.119
Correct.
00:33:43.680 --> 00:33:48.400
And they're saying it only makes out 38.8% of the entire conversion.
00:33:48.480 --> 00:33:49.039
Is that correct?
00:33:49.359 --> 00:33:51.279
Yeah, but in the end, they will still give you business.
00:33:51.359 --> 00:33:59.759
And that's that's the customers that we want to talk to because we believe that educating them about services is extremely important.
00:34:00.079 --> 00:34:00.480
Yeah.
00:34:01.599 --> 00:34:02.079
Okay, okay.
00:34:03.119 --> 00:34:04.880
404 engaged problem.
00:34:05.920 --> 00:34:07.119
Before I went to Hong Kong.
00:34:07.200 --> 00:34:11.519
So basically, we were looking at this entire no, actually, we've been looking at it for like two months now.
00:34:11.760 --> 00:34:19.039
Like this, we realize also, although we don't have data, but like what Yao Hong said, we are in the business every day, so we look at where we can improve on.
00:34:19.519 --> 00:34:21.760
Now that um we are trying to build systems, right?
00:34:21.840 --> 00:34:34.239
We realize that there is a large like customers do not only say yes um to us on the day they inquire with us.
00:34:35.360 --> 00:34:38.159
Yeah, most of us aren't so decisive, right?
00:34:38.320 --> 00:34:42.559
Especially when we mention that these bags are important items to them.
00:34:42.960 --> 00:34:49.119
So it might take more than 24 hours, it might take more than 48 hours, and therefore, like at Dr.
00:34:49.280 --> 00:34:59.039
Bags, we are trying to program our communications with clients um in a more sensible manner.
00:34:59.280 --> 00:35:03.679
Yeah, like maybe we re-engage with them, we re-talk, we talk to them more.
00:35:04.159 --> 00:35:10.559
Yeah, so so this is this is why we also realize that there is potential in this engaged column.
00:35:10.880 --> 00:35:25.039
Yeah, and I feel like through re-engagement, through more engagement, we will be able to um have customers understand us better and trust us with their items more.
00:35:25.199 --> 00:35:25.679
Yeah, yeah.
00:35:25.840 --> 00:35:36.800
And even if we don't they don't say yes to us today, they might remember us for the quality of our replies, yeah, at a later stage.
00:35:36.960 --> 00:35:37.280
Yeah.
00:35:38.960 --> 00:35:49.199
But what I think I will do here just to throw it out there, right, is to look at uh past conversations, measure the time between each messages, right?
00:35:49.280 --> 00:35:58.719
So we have that kind of granularity, and see what's is there a pattern between uh the last message and when they get stuck in engaged, right?
00:35:58.800 --> 00:35:59.920
And then to warn.
00:36:00.079 --> 00:36:08.880
And then from there we can try to then try to uh optimize for the time where there's an automation back to the customer.
00:36:09.199 --> 00:36:11.039
Hey, are you still thinking about this?
00:36:11.920 --> 00:36:12.079
Right?
00:36:12.159 --> 00:36:12.239
Yeah.
00:36:12.480 --> 00:36:20.559
Because I'm not sure if your team do follow up when people are in engaged or like how many times do you message back?
00:36:20.639 --> 00:36:21.280
Yeah, that kind of thing.
00:36:21.360 --> 00:36:22.639
So there's a lot of strategies you can play.
00:36:22.719 --> 00:36:28.559
So from there you can do like testing, like, oh, we send one message at this time, and you can test.
00:36:28.639 --> 00:36:30.239
It's like basically an experiment, right?
00:36:30.320 --> 00:36:34.800
You you send uh after one day, you send a message, or then no reply another day.
00:36:35.119 --> 00:36:36.960
Maybe after three times you say, okay, drop.
00:36:37.360 --> 00:36:39.920
So it doesn't perpetually stay engaged, lah, right?
00:36:40.159 --> 00:36:42.000
Yeah, that that's what I'm doing.
00:36:42.320 --> 00:36:42.480
Okay.
00:36:42.800 --> 00:36:49.199
Yeah, but you your your your your suggestion sounds even more complex, which I like.
00:36:49.360 --> 00:36:50.320
So I wrote it down.
00:36:55.039 --> 00:36:58.079
Because you have WhatsApp uh business as well, right?
00:36:58.320 --> 00:37:07.360
Um there are always ways to kind of build your WhatsApp bots, uh, depending on the complexity, and then you know, maybe just having a nudge, like, hey, are you still
interested?
00:37:07.679 --> 00:37:07.920
Correct.
00:37:08.400 --> 00:37:12.719
Might even increase, uh, might decrease some of these stock deals as well.
00:37:12.960 --> 00:37:13.840
Um but you could start.
00:37:14.239 --> 00:37:17.039
Imagine 10% of this converter is 40 more wins, huh?
00:37:17.119 --> 00:37:17.519
Yeah, yeah.
00:37:17.760 --> 00:37:19.760
So that's yeah, but you could start small.
00:37:20.239 --> 00:37:26.800
I mean, you don't have to go like full, fully like uh WhatsApp agent that can do anything, right?
00:37:26.880 --> 00:37:37.360
But I guess this would be one small problem that if you were to work on, you know, just a kind of notification message, you could actually add some deals as well.
00:37:37.599 --> 00:37:45.519
Um I would caveat against jumping straight to using an agentic AI solution here because you don't understand the problem yet, right?
00:37:45.679 --> 00:37:47.679
You try AI there, it's gonna get confused.
00:37:48.079 --> 00:37:49.519
You've got more confused than humans.
00:37:49.760 --> 00:37:50.079
Yeah.
00:37:50.559 --> 00:37:50.800
Yeah.
00:37:50.960 --> 00:37:51.280
Yeah.
00:37:51.679 --> 00:37:52.320
Yeah.
00:37:53.360 --> 00:37:53.599
Yeah.
00:37:53.679 --> 00:37:57.039
So what I'm doing now is I'm putting them into different baskets.
00:37:58.079 --> 00:38:01.920
Yeah, at this current moment, lah, I'm trying to put them into different baskets.
00:38:02.079 --> 00:38:02.400
Yeah.
00:38:02.800 --> 00:38:03.280
Which is good.
00:38:03.679 --> 00:38:09.119
I mean, it's a good step to classify and and understand your business better.
00:38:09.679 --> 00:38:10.880
So, yeah.
00:38:11.119 --> 00:38:18.400
Um, I understand we are almost hitting an hour uh and we still have that one Instagram task.
00:38:18.880 --> 00:38:19.519
Let's finish this one.
00:38:19.599 --> 00:38:20.320
I want to see this one.
00:38:21.199 --> 00:38:25.920
Let me just let's just, you know, let's just wing it.
00:38:26.239 --> 00:38:32.400
Um I'm just gonna paste in the photo and say, hey clock code, I have no time.
00:38:32.559 --> 00:38:50.880
Can you please make uh you know a very good Instagram post uh that uh basically is very short, very readable, um hopefully just you know, uh two or three short lines and then with pretty good um uh hashtags as well.
00:38:51.119 --> 00:38:54.559
Uh these are the photos for you to base it off on.
00:38:54.960 --> 00:39:00.480
Uh Lynn, is there any other things you add to the how you write your social media posts?
00:39:03.760 --> 00:39:07.679
This shows how Eric doesn't not a very design sensitive person.
00:39:10.639 --> 00:39:16.480
We should be talking about the the mood and feel of the images for the the brand brand guide, the brand style.
00:39:16.800 --> 00:39:17.199
Yeah.
00:39:17.360 --> 00:39:18.000
Yeah.
00:39:18.400 --> 00:39:21.519
The new life, making it feel refreshing.
00:39:21.679 --> 00:39:23.280
Yeah, yeah.
00:39:23.599 --> 00:39:25.840
No examples, I'm in a rush.
00:39:26.079 --> 00:39:27.840
The episode is ending.
00:39:28.960 --> 00:39:29.280
Okay.
00:39:30.079 --> 00:39:30.960
He's your best friend.
00:39:32.159 --> 00:39:34.559
This is gun tripping the AI, you know.
00:39:34.800 --> 00:39:35.440
Yeah.
00:39:37.360 --> 00:39:38.559
Okay, this is bad.
00:39:39.760 --> 00:39:41.679
Yellow in, yellow out, thank you.
00:39:42.079 --> 00:39:46.400
Oh, wait, is there a uh picture that I gave it a picture just now?
00:39:46.719 --> 00:39:47.840
Which picture did you give it?
00:39:48.079 --> 00:39:48.320
This one.
00:39:48.719 --> 00:39:50.239
I'm just gonna give it okay.
00:39:50.480 --> 00:39:52.480
Okay, here's one example.
00:39:53.280 --> 00:39:53.760
Yeah, okay.
00:39:54.079 --> 00:39:59.599
Um I'm going to give you one last picture to try on.
00:40:00.400 --> 00:40:07.119
Um, so this shows the the limit of uh creativity in in the LOMs.
00:40:07.280 --> 00:40:07.360
Yeah.
00:40:07.599 --> 00:40:08.880
I struggle with this a lot, right?
00:40:08.960 --> 00:40:10.719
To ask them to write something that's creative.
00:40:11.760 --> 00:40:12.000
Yeah.
00:40:12.159 --> 00:40:15.840
It sometimes gives you very like kind of yeah.
00:40:16.800 --> 00:40:16.960
Okay.
00:40:17.360 --> 00:40:21.199
But likely it's because it's the first time that we're talking talking about.
00:40:21.440 --> 00:40:22.000
Correct, correct.
00:40:22.079 --> 00:40:22.239
Yeah.
00:40:22.400 --> 00:40:27.119
So usually how you make this better is you put in a build a relationship.
00:40:27.519 --> 00:40:29.199
No, no, I mean kind of.
00:40:31.039 --> 00:40:39.920
You actually send it a lot of examples in the past that you have so that it it learns uh your your brand, your your brand uh your tone of voice, yeah, and things like that.
00:40:40.239 --> 00:40:41.039
Identity, correct.
00:40:41.119 --> 00:40:43.119
So it you'll try to write the same style.
00:40:43.760 --> 00:40:44.079
Okay.
00:40:45.039 --> 00:40:45.920
Yeah, okay.
00:40:46.000 --> 00:40:47.119
This is weird as well.
00:40:47.280 --> 00:40:51.840
Now the Adidas is being written in a Ferragamo copy.
00:40:52.320 --> 00:40:56.480
So from dull and dingy to fresh and bright with a star emoji.
00:40:56.800 --> 00:40:57.199
Wow.
00:40:58.480 --> 00:41:00.639
These Adidas Continental 80s were brought back.
00:41:02.000 --> 00:41:02.159
Okay.
00:41:02.639 --> 00:41:03.039
Yeah.
00:41:03.440 --> 00:41:05.119
Lynn, any thoughts on this?
00:41:05.679 --> 00:41:06.719
Very bad.
00:41:09.280 --> 00:41:11.440
You see, the no one can say no.
00:41:12.480 --> 00:41:19.760
No, no, I think maybe maybe this is how Claude Code knows of Eric.
00:41:20.000 --> 00:41:21.119
I don't know, I don't know.
00:41:21.360 --> 00:41:22.159
Uh no, no.
00:41:22.400 --> 00:41:23.360
This is not from memory.
00:41:23.519 --> 00:41:25.280
It's a fresh uh it's a fresh instance.
00:41:25.519 --> 00:41:26.320
Yeah, a fresh one.
00:41:26.559 --> 00:41:28.960
So uh so we should actually feed it more slowly.
00:41:30.960 --> 00:41:33.920
But I understand where you're where you're heading towards.
00:41:34.159 --> 00:41:34.880
Yeah, yeah, yeah.
00:41:35.119 --> 00:41:37.199
And yeah, I think it's important.
00:41:37.360 --> 00:41:44.800
I think if we feed it the correct information, um, yeah, it might likely give us better results.
00:41:45.599 --> 00:42:02.559
So I I think not just information, but um, after you know, feeding in a few or maybe like 50 captions, um, I would also ask it to kind of extract out the principles uh behind some of the marketing copy so that it's not just copying word for word or or line by line, right?
00:42:02.639 --> 00:42:05.280
It's like actually trying to understand what you're thinking.
00:42:05.360 --> 00:42:09.440
And then of course your your marketing team can go in and say, no, that's not what I was thinking of.
00:42:09.599 --> 00:42:11.519
Uh here's the principle instead.
00:42:11.760 --> 00:42:20.000
And and of course, so it's a mixture of like principle and examples so that um you're not just Does it work for videos as well?
00:42:20.800 --> 00:42:24.880
Uh in in a cap you mean in text for videos, is it?
00:42:24.960 --> 00:42:28.320
Or or like or you mean you upload a video and then you write a caption?
00:42:30.559 --> 00:42:31.119
Yeah.
00:42:31.840 --> 00:42:38.559
Um no, I I think for now, quick answer, I don't think the videos would be as good as as yours uh for now.
00:42:39.119 --> 00:42:45.440
Um definitely yeah, I mean TikTok and and reels are getting there.
00:42:45.760 --> 00:43:00.079
But um yeah, I think you still need quite a bit of human intervention for videos, um, just because yeah, there are a lot of limits for for videos, even though there are uh some software packages out there that can edit videos, but it's super basic.
00:43:00.159 --> 00:43:06.079
It's mostly just cut and put a picture on and maybe trim the video.
00:43:06.320 --> 00:43:07.440
Very simple stuff.
00:43:07.599 --> 00:43:09.280
So we are not there for video yet.
00:43:09.360 --> 00:43:10.800
So yeah.
00:43:11.280 --> 00:43:11.599
Okay.
00:43:11.920 --> 00:43:17.920
Okay, I'm just gonna stop sharing my screen so that uh you can get back to your your work and rest.
00:43:19.519 --> 00:43:23.599
Um but I just wanted to uh rest.
00:43:24.960 --> 00:43:26.320
I need to go back to work.
00:43:26.639 --> 00:43:27.599
Yeah, yeah, yeah.
00:43:29.039 --> 00:43:34.719
So but yeah, maybe just any any quick reflections, Lynn, on on the hour that we had today.
00:43:35.039 --> 00:43:40.159
Anything that you would uh start doing differently from today?
00:43:40.880 --> 00:43:45.760
Definitely to understand the the data that we were using just now.
00:43:46.239 --> 00:43:59.599
And to yeah, like what are the different um to clean that data up to so that we can really utilize it to do what I want to do.
00:44:00.000 --> 00:44:10.719
I already know that um the the possibilities that I thought could be materialized can actually be materialized, but my data needs to be correct first.
00:44:11.440 --> 00:44:11.840
Yeah.
00:44:12.800 --> 00:44:12.960
Yeah.
00:44:13.119 --> 00:44:24.800
And actually, maybe just to caveat, the the things that we did today could have actually been done in uh clot.ai session.
00:44:25.440 --> 00:44:26.480
Yeah, what do you have?
00:44:26.719 --> 00:44:28.159
I mean, I'm shooting myself in the foot.
00:44:28.480 --> 00:44:28.559
Right.
00:44:28.719 --> 00:44:30.400
You didn't really need clot cooler.
00:44:30.639 --> 00:44:34.320
I think this was you can have used the desktop app.
00:44:34.559 --> 00:44:34.800
Yeah.
00:44:35.679 --> 00:44:41.599
Actually, this would have worked by you just uploading your data into uh especially since it's just one month of data.
00:44:41.840 --> 00:44:42.000
Yeah.
00:44:42.239 --> 00:44:43.679
Um if you just uploaded it.
00:44:43.840 --> 00:44:44.079
Yeah.
00:44:44.480 --> 00:44:50.079
But in um but when I finally get to do this, it wouldn't be a one-month thing, right?
00:44:50.159 --> 00:44:52.480
So it would be uh you need to look at trends and everything.
00:44:52.880 --> 00:44:53.440
Yeah, correct.
00:44:53.519 --> 00:44:56.480
So I'll pull out all my data and understand it.
00:44:56.639 --> 00:44:56.800
Yeah.
00:44:57.039 --> 00:44:59.119
And I think that would be uh yeah.
00:44:59.360 --> 00:45:01.599
How long do you think it would take?
00:45:03.679 --> 00:45:05.440
Not very long, I would think.
00:45:06.000 --> 00:45:07.199
You mean just to understand?
00:45:07.360 --> 00:45:10.239
You mean just to understand your data or how how long?
00:45:10.639 --> 00:45:12.159
No, to really do up with the dashboard.
00:45:12.320 --> 00:45:12.960
Yeah, to build it.
00:45:13.920 --> 00:45:15.360
Given my intellect.
00:45:17.519 --> 00:45:18.880
Sorry, sorry, sorry.
00:45:20.480 --> 00:45:21.519
I like pink.
00:45:22.079 --> 00:45:23.599
I wish your PPC now.
00:45:26.000 --> 00:45:26.719
Not very long ago.
00:45:28.159 --> 00:45:28.480
Yeah.
00:45:30.320 --> 00:45:31.360
I cannot.
00:45:34.639 --> 00:45:37.119
But there's still a process of like a normal human being.
00:45:38.719 --> 00:45:48.400
No, I mean I would as a normal person, like for me, I would actually ask like what are the steps for data, like proper data analysis to make it clear, right?
00:45:48.719 --> 00:45:53.119
Uh I am to train you or tell you what and check with somebody, maybe.
00:45:53.360 --> 00:45:53.519
Yeah.
00:45:53.679 --> 00:45:55.519
And it's good to chat with your tech team.
00:45:56.159 --> 00:45:57.280
Basically, you can send it to me.
00:45:58.639 --> 00:45:58.880
Really?
00:45:59.199 --> 00:46:00.800
Help you, help you vet, help you vet, yeah.
00:46:02.639 --> 00:46:03.440
Well, I mean it's interesting.
00:46:03.760 --> 00:46:05.440
To me, it's always interesting problems to solve.
00:46:05.760 --> 00:46:05.920
Yeah.
00:46:06.719 --> 00:46:07.199
Yeah, yeah.
00:46:07.280 --> 00:46:09.119
So Nightwise for me.
00:46:10.079 -->
00:46:11.360
It's it's problem solving.
00:46:11.440 --> 00:46:11.599
Yeah.
00:46:11.840 --> 00:46:12.639
Yeah, yeah, yeah.
00:46:12.880 --> 00:46:17.119
And then I mean it would it will give you some steps, like you have to clean the data first and all that, right?
00:46:17.199 --> 00:46:22.400
So I mean it really depends how how comprehensive you want it to be.
00:46:22.639 --> 00:46:26.159
Um it can be very complex, yeah, if you want to do it properly.
00:46:26.639 --> 00:46:33.199
Yeah, because you actually need uh proper data warehousing, your data must pipe there from all the sources, clean up.
00:46:34.000 --> 00:46:37.039
Yeah, but I'd rather be complex and then later on.
00:46:37.840 --> 00:46:38.719
It's always like that, right?
00:46:38.960 --> 00:46:40.239
Like, correct, correct.
00:46:40.719 --> 00:46:43.679
Then the simplification comes after the complexity.
00:46:44.639 --> 00:46:44.880
Yeah.
00:46:45.199 --> 00:46:52.400
Also, what we are doing now is a very quick um POT just to look at the numbers, and straight away you see a bit of a discrepancies already.
00:46:52.639 --> 00:46:52.960
Yeah.
00:46:53.199 --> 00:46:53.440
Right.
00:46:53.599 --> 00:46:56.239
And from there, it's it's it's helpful actually.
00:46:56.480 --> 00:46:57.760
Nevertheless, it's too helpful.
00:46:57.920 --> 00:46:58.159
Yeah.
00:46:58.559 --> 00:47:01.920
You you otherwise wouldn't have been able to spot this on your own.
00:47:02.559 --> 00:47:02.880
Yeah.
00:47:03.199 --> 00:47:05.039
Or you spend quite a lot of time making it.
00:47:05.280 --> 00:47:13.199
Definitely, like imagine I make use of all the data and then I spend two hours keying all the things and sorting it out, and then realizing bam, it's wrong.
00:47:13.599 --> 00:47:13.840
Yeah.
00:47:15.119 --> 00:47:16.880
Now we just talk about just talking.
00:47:17.119 --> 00:47:17.760
Yeah.
00:47:18.239 --> 00:47:18.480
Yeah.
00:47:18.639 --> 00:47:20.159
Which there is a lot of trial and error.
00:47:20.320 --> 00:47:22.639
There's a lot of trial and error for this kind of thing.
00:47:22.719 --> 00:47:28.239
So if you do have fires to fight, then I do imagine that you do need to measure that trade-off, right?
00:47:28.320 --> 00:47:31.199
Of like how much time and complexity you want to spend on this.
00:47:31.519 --> 00:47:35.039
Um But actually, actually, I do take back a bit of my words.
00:47:35.119 --> 00:47:49.920
Like if you were to do this in a normal clock chat, I don't think you will get so far, but you you might get uh a dashboard, but you might not get as accurate results and uh comprehensive kind of data analysis, especially within like two or three prompts that we just did.
00:47:50.159 --> 00:47:52.400
Um I think that's just a caveat.
00:47:52.480 --> 00:47:57.280
Uh you might have to prompt a lot more times on a normal chat interface.
00:47:57.519 --> 00:48:01.199
Yeah, because uh what Cloco did was that it created a program in the back, right?
00:48:01.280 --> 00:48:01.440
Yeah.
00:48:02.079 --> 00:48:04.480
To do summation or aggregation of your data.
00:48:04.719 --> 00:48:05.199
Yeah.
00:48:07.440 --> 00:48:07.920
Yeah.
00:48:08.400 --> 00:48:09.280
So yeah.
00:48:10.239 --> 00:48:17.280
And I also learned that we need to communicate, continue to communicate to Claude.
00:48:18.000 --> 00:48:24.400
Yeah, and I I think communicating with an AI would teach you how to communicate with tech people.
00:48:24.480 --> 00:48:26.880
Like that's what I learned as well as a non-technical person.
00:48:27.199 --> 00:48:28.880
Because a lot of times I have ideas in my head.
00:48:29.039 --> 00:48:30.880
Oh, you sound extremely technical to me.
00:48:31.119 --> 00:48:32.880
Oh yeah.
00:48:32.960 --> 00:48:34.800
Um what's me?
00:48:35.119 --> 00:48:36.000
What am I?
00:48:37.599 --> 00:48:38.239
Normal people.
00:48:39.280 --> 00:48:40.079
Yeah, we're all just normal.
00:48:40.559 --> 00:48:46.079
Actually, I mean, yeah, I don't know what this what it means to be technical if you don't have to code with code anymore.
00:48:46.320 --> 00:48:51.760
But but yeah, it's good for uh training our communication skills and just being very clear about that.
00:48:51.920 --> 00:48:53.360
Yeah, I think that's true.
00:48:56.079 --> 00:48:57.280
Okay, alright then.
00:48:57.440 --> 00:48:58.000
Thanks so much.
00:48:58.320 --> 00:48:59.280
Thank you so much, boys.
00:48:59.440 --> 00:48:59.920
Thank you.
00:49:00.400 --> 00:49:01.440
Thanks for coming on.
00:49:01.760 --> 00:49:02.559
Have a great night.
00:49:03.840 --> 00:49:04.480
All right, thank you so much.
00:49:05.840 --> 00:49:06.079
Thank you.
00:49:06.320 --> 00:49:06.880
Yeah, bye.
00:49:07.119 --> 00:49:08.079
Okay, bye.
00:49:10.320 --> 00:49:13.360
Thanks so much for joining us for this episode.
00:49:13.519 --> 00:49:20.719
If you found this helpful, feel free to leave us a rating on your favorite podcasting apps or like, share, subscribe on YouTube.
00:49:21.199 --> 00:49:25.440
And if you want to get into the next episode, feel free to fill up the form as well.
00:49:25.679 --> 00:49:27.760
So, yeah, thanks so much for joining us.
00:49:27.920 --> 00:49:30.800
Uh, really appreciate that you even made it to the end.
00:49:31.199 --> 00:49:33.920
And see you on our next episode.
00:49:34.400 --> 00:49:35.039
Bye.