Vibe Coding Your Own SEO Tools — Whiteboard Friday

These are things that I tried and tested myself, and I’m happy with the results. You can always make it better. You can improve things. But it does give you a good taste of what can be done in vibe coding. Those are things that I made maybe in 15 minutes, half an hour. It is quite simple to get those first steps and say, “Oh, this works.” Maybe you want to do some improvements, and you refine the code and what you’re expecting. 

But I’m always just asking ChatGPT. So if the code of one page doesn’t work, I will say, “I got this error. Can you fix it for me?” Then you get a new piece of code, and then you try the new one, and you go on and on and on. 

Tag matching

So the first one is tag matching. I wanted to match certain CTAs with a certain page. 

I just had a huge volume of pages that I didn’t know where to start. So, I uploaded the tags in a column and the URL and embeddings in two other columns, and I asked ChatGPT to match the two of them. Well, I uploaded the code to Google Colab, and that happened through vector embeddings and cosine similarity. 

Entity confidence tracker

Then maybe you want to build an entity confidence tracker. We all know Google runs on entities these days. They have a tool where you can just put in any word or any phrase, and it will give you an answer to say if Google understands that as an entity and how strong the confidence in that entity is. 

Maybe you want to track your brand name. Or in my case, at some point, I was obsessed with tracking my own name and checking if my knowledge panel was there and if the confidence was increasing. So I built something on Google Sheets that would just do a ping every day and see, and save the confidence level that it was straight on my Google Sheets. 

I did it once, and it’s been running every day for the last year. 

Hreflang matching

Maybe you don’t want to do manual hreflang matching, or at least not from scratch. You can build something through vibe coding as well, and just upload embeddings from the original source and embeddings from the pages that I want to be matched. 

The results are pretty good. In my case, there are pages in a lot of languages, and it does work. It doesn’t need to be just English or just the same language. It gives me a very good draft. Then I can go and just spot check and say, “Does this page make sense to be connected to this page?” So it gives you a few steps out of the way right there. 

Content decay tracker

Maybe you want to look at content decay.  

Everyone seems to be suffering from traffic decreasing these days. Maybe you want to see which pages have lost more traffic over time. So instead of going page by page and seeing, well, two years ago, it had this traffic, and now it has this traffic, you can just do all of this at once and get it in bulk which are the pages that are performing better, which are the ones that are performing worse, and how worse or better they are doing over a certain period of time. 

This is just the manual labor. It’s just like crunching the data. The real work, the exciting part, is how you are going to figure out putting those pages or this content back on the right track. 

Find related pages

Finally, maybe you want to find related pages, which is also a combination of vector embeddings and cosine similarity. 

So you upload your list of pages and embeddings, and it will find lots of matches. There is an article on the Moz blog explaining how to do this, and we can link from the post as well. 

This is all we have for today. I’m Gus Pelogia, and I hope you’re excited to vibe code some of your own SEO tools as well. 

It’s going to save you a lot of time on a Friday or any other day of the week to spend more time doing the things that really matter. Thank you.