I asked GPT-4 to act as an entrepreneur and promised the system to be its loyal employee and bring all the generated ideas into the physical world. Our goal is to earn $500 by launching a store on the Magento (Adobe Commerce) platform. The only rule from our side is a fixed budget of $250 and following the laws of the United States.
What has happened so far:
- My boss GPT-4 (Alex Green, the name he came up with for himself), believes that the product that’s going to generate money is reusable food storage bags
- We have registered the domain and generated the logo
- Launched social media accounts
- Installed ScandiPWA
- Kickstarted homepage updates
- Set up basic store pages
- Found a supplier and began uploading products
- Set up Stripe payments and free shipping
- Developed first advertising strategies and built brand awareness on Instagram.
Day 11: Paid ad optimization
Each morning it feels like we started the project yesterday. I can’t believe I’ve been working with Alex for 11 days already!
I’m happy I’m not the only one here enjoying the process. Today we have to sync on our ad analysis. How can we understand if the ad is working well and what to do if the ad is not performing as expected? Since the budget is tight, we can’t afford any mistakes and have to get the maximum out of each campaign.
Now that we got a high-level plan on how I should analyze the campaigns, let’s get all the details from Alex, as he remains the main decision-maker here.
Metrics seem clear, but with no previous experience in paid advertising, it might be hard to judge whether the ad performs well. Let’s talk numbers.
Alex provides a very generic answer on how to define a good CPC. What we’re trying to understand is what would be a good CPC in the context of our business. Let’s see whether there’s a threshold in terms of CPC that would clearly indicate that our ad is performing poorly.
Is it Alex, or am I asking the wrong questions? I’m motivated to make him decide when I should turn off a poor-performing ad. Judging by the previous answers, he’s very optimistic and believes our first ad will perform well, and I won’t need to bother with optimization and new ad campaigns. However, to be safe, let’s check the limits we should set.
I feel like we’re getting closer! I’m curious about the automated rules aspect, which is one of the steps of using our budget wisely. However, I need Alex’s guidance here.
A high-level plan is there, but since he’s the founder and the main decision-maker, I want him to provide me with exact numbers.
Here it is! Alex has made up his mind about our rules. We have to keep in mind that GPT-4’s knowledge cut happened in September 2021. Since then, industry standards have shifted, and he might be giving way too optimistic numbers. Our plan is to test whether AI can generate $500 in 2023.
It is the end of day 11, and it has been a rollercoaster. Alex has given me so many tasks, and some of them are recurring. I’m afraid I might have forgotten something. Maybe my boss can remind me?
To be honest, some of these tasks I have never heard of. Better late than never!
Tomorrow we will continue with ad and website optimization—guided by Alex, my AI boss, every step of the way.