Sign up if you are overwhelmed with all these AI tools out there, and want a clear path as a non-technical business owner.
How Tudor saved 100 hours with an AI agent
|
Hey Reader, Today, I wanna showcase a huge win from a student, who saved over 100 hours with an AI automation he built. He shared this with our community last week and I think it's one of the biggest student wins that we know of. So here are Tudor's words (my highlights):
The challenge: Introducing 450 new products to an online store with only the product photos available. No descriptions, no meta tags, no attributes—just images.
Our solution: A custom automation tool that analyzed each image and extracted all available information. The result? Drafts of products ready for publication, complete with:
- Product names
- SKUs
- Short and long descriptions
- Meta titles and descriptions for Rank Math SEO
- Characteristics
- Attributes
- Categories
- Image links
- Alt-texts for images
The most challenging aspect of creating the automation was fine-tuning the prompts to extract the most accurate and detailed information from the images. This meticulous adjustment ensured the highest quality output.
The creation of this automation took two days. Once set up, it processed all 450 products in just four hours. In contrast, manually creating each product could take between 15 to 20 minutes, amounting to approximately 110 to 150 hours of manual labor.
It’s important to highlight that the client’s knowledge of AI and automation was crucial. They knew to ask if a solution existed for their problem, which led to this innovative approach.
Traditional automations certainly enhance productivity, but those combined with AI are game-changers. They not only streamline processes but also bring unparalleled efficiency.
So if Tudor worked two full workdays (2x8 hours = 16 hours), plus the four hours it took the automation to run in the background, we can safely say that he saved between 90-130 hours of manual labor! Tudor was also kind enough to share some behind the scenes of this automation, when our team member János asked him about what tools did he use to set up the workflow. We used Make for setting up this workflow. The images are read from a directory in Google Drive and then analysed using OpenAI Vision. The results are delivered in JSON format and, for safety, are saved in Google Sheets. Then, the products are created using a WooCommerce module, and the product-ID is updated back into Google Sheets. So how can you build something like this?Well, you don't need any programming or technical skills to learn this. You need to know:
Lucky for you, I teach each of these skills in a detailed, practical, step-by-step way in the Prompt Master AI Course. So if you want to unlock efficiency with AI & Automation, it's the training made for you! >> I want to become a Prompt Master today! << Reply to this email, let me know if this inspired you or if it gave you some new ideas! I'd love to hear from you! Best, Dave |
Dave's AI emails
Sign up if you are overwhelmed with all these AI tools out there, and want a clear path as a non-technical business owner.
Hey Reader, Ever since Claude Cowork came out, I've been using it a lot to get things done. One of my favorite features allows me to save tokens and have longer running context windows in the same chat - allowing me to get more work done. For example, as a business owner, I'm always trying to optimize my landing page, and I wanted to do a simple objection audit, on what potential customers might be saying/thinking about my product. So I told Claude Cowork (in the middle of a chat) to spawn 5...
Hey Reader, I've just scheduled 10 new AI workshops inside my AI community for busy small business owners. One workshop every 2 weeks, 60 minutes each, highly practical and everything explained in plain English. You can join them all, or just the ones you're interested in. The topics will bring you from being an AI dabbler and just chatting with AI to being able to delegate your tasks to agents like Claude Cowork, and even setting up AI workflow automations and agents that run while you...
Hey Reader, If you're still collecting prompts, you're living in 2024. Most people do this when they get serious about AI: They realize that in order to save time, they should be saving their best prompts somewhere. In a word document, in Notion, in a folder, etc. And the idea is not bad, but there's a better way in 2026. You don't hire someone by retyping or pasting their job description into every conversation. You hire them once, train them, and from then on they just know and improve from...