Let’s say you’re running your Ecom brand. You’re struggling to keep up with customer support tickets and orders, putting out fires. It’s busy, but the sales are coming in, so everything seems okay, right? But at the end of the month, you do your accounting, crunch the numbers, and wonder where did all the profit go?
Well, this happened to us in the past, and this is why we’re so big on tracking metrics daily with a great dashboard. It’s like a Fitbit, but instead of for your personal health, it’s for the health of your business. There are many dashboard tools out there, and we like to use Triple Whale. But in this video, we’ll show you how to make your own dashboard with Code Interpreter.
If you’ve never used Triple Whale before, they have many features and modules. But the one we’ll focus on today is their main dashboard. We can see different tiles of metrics. The top ones are the ones we pinned as most important, but as you scroll down, you’ll see critical information from Shopify, ads, and some other expenses near the bottom. So everything you need to get a pulse on your business is right here.
But these tools cost money. With Code Interpreter coming up, we can use this instead by creating our own dashboard. We’ll start by downloading exports of Shopify and ads data, and then we’ll bring that into Code Interpreter to create the dashboard.
The first thing we need to do is go to the reports section on Shopify. There’s a bunch of standard reports available, and we’ll be using a couple of these. The first one is the sales over time report. But we won’t be using the default report. We’re going to add two additional columns: the customer type and the net quantity. This will give us information on whether it’s a first-time or returning customer, and also the total number of items sold, which don’t necessarily correspond to the number of orders because sometimes someone will order more than one item at once. For this example, we’re going to look at the last seven days.
Okay, now that we have this, we’re going to export it and move on to the next report. For the second report, we’re going to use the online store conversions over time. In this case, we can just use the standard report again and look at the last seven days. And we can export.
Next, we’ll head over to Meta Ads. First, let’s set the time range to the last seven days, so we’re matching the time range of our Shopify data. And then we’re going to filter the ads, so we’re only showing ads that had delivery. I’ve also set up a columns template, which I like to use when exporting. But for the purposes of what we’re doing here, all we need are Impressions, clicks, amount spent, purchases, and conversion value. And finally, we’re going to break the data down by day, and then we’re going to export.
With our raw data, we can head over to Code Interpreter to populate our dashboard. I asked Code Interpreter a series of questions until I was able to recreate the Triple Whale dashboard. So you can kind of see there’s a bit of a conversation going on. You’ll start to see some semblance of a dashboard showing up, but it took a little bit of trial and error to get to something that I was happy with.
And once I did get something that I was happy with, then you can ask Code Interpreter to generate a prompt, which it will create in the form of Python code. And then you can use that Python code later in other chats to create the dashboard that you want.
Eventually, I got three separate scripts. The first one processes the Shopify sales data, the second one processes the Facebook ads data, and the third one pulls data from both sources. Now that I have the exported data from Shopify and Facebook and the code snippets, I cannot upload them all to Code Interpreter. Normally, you can only upload one file at a time, but I’ve added them all into a zip file, so that’s one hack we can use to upload them all in one shot.
So what I’ll do is I’ll upload my zip file first. And I also have a prompt that I’ve written to instruct Code Interpreter what to do with these files. And so let’s send that through.
And now Code Interpreter is going to do its thing. So I’m going to just speed up through this section.
And there we go. So we see three different sections. The first section is the Shopify sales data, so we can see revenue, number of orders, AOV, how many new customer orders we got, etc. The second section is the Facebook ads data, so how much we spent, our ROAS, CPA, CTR, CPC, etc. And we also have some hybrid data, so the margin, which would be total revenue divided by amount spent, or contribution margin. And finally, we have our variable expenses like cost of goods and shipping costs and payment gateway, which are going to be different for every business.
What you see here is essentially a recreation of the Triple Whale dashboard directly into Code Interpreter. The dashboard we created is simpler, the layout isn’t as fancy, and we focused on just Facebook ads. But to be able to put this together within a day just shows how powerful Code Interpreter can be for your business. And while you can simply use Triple Whale, there are some advantages in creating your own dashboard. First, it’s customizable. If there are specific metrics that you want or you want it to look a certain way, then you can do that. But it’s not perfect. What I’m thinking of doing next is continuing to build this dashboard out further with Code Interpreter, so maybe make it look better or make it so that it can automatically pull the data from Shopify and Facebook ads. Let me know in the comments below if this is something that you’d like to see. Thanks for watching this video, and see you in the next one!
