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 |
Sign up if you are overwhelmed with all these AI tools out there, and want a clear path on your AI journey.
Read time: 3 minutes Hey Reader, It is one thing to know the potential of AI Language models like ChatGPT or Claude, but it's also important to know their limitations. In this email, I want to show you 5 things you should avoid when using ChatGPT (or Claude or Gemini or LLama, etc.) 1/ Treat it like a know-it-all search engine ChatGPT is not a search engine. It is simply a very expensive predictive keyboard. All it does is it just guesses what's the best next word to say in a scenario. It...
Hey Reader, One of the most common requests I hear from clients is that they want a custom version of ChatGPT for their business that uses their knowledge. Whether it's a chatbot on their website, WhatsApp, Instagram, etc. all they want is to have it use their knowledge. So in this email, I want to teach you how to build such a thing. I just created a custom chatbot for my website in 40 minutes, you can give it a try on this website (chatbot bubble in bottom right corner). It has access to...
Read time: 3 minutes Hey Reader, It's been a while since I last wrote this newsletter to you. The last few weeks have been hectic, and I only now have some time to sit down and focus on teaching. 4 steps to succeed in AI in 2024 With over 12,000+ AI tools online, and all these new language models that are coming out, it might feel hard to stay updated. Let alone if we think about the new image and video generative models, voice cloning tools and use-case specific tools like AI integrations in...