Hi everyone, Glen from Solutions 8 here and here we are in the Solutions 8 test kitchen. It's actually physically my kitchen that I've got my office set up in. but this is where I'll be, running tests, experimenting with things, playing with things. And what I wanted to do is shoot you a quick video on how I use the natural language API tool, from Google and incorporate that, with ChatGPT. With some other, tools, this is for copy and in particular finding positive copy that Google's going to look at favorably. Now, when we are creating ad copy, now there's generative AI tools coming out, inside Google now. at the time of this recording, Gemini Ultra was just released today. So that will be interesting to see how all that pans out and how it compares with GPT, but at this stage I'm using. GPT four plus. and in this example, I'm gonna show you how to use the cloud natural language tool, and chat GPT to create more copy ideas, add ideas so that you can have, with a view of improving click through rate. And conversion rate in your ad copy. in this example, I'm just going to use solutions eight. I'm just going to grab all the copy. That's on our homepage, come into the natural language tool under demo. You'll see here, it says, try the API. Just paste everything in there, hit it, run it. It then outputs all this gobbledygook and. sentiment. I want to click on the sentiment tab and you'll see here that anything green has a positive sentiment, which is Google's natural language tool. it's API saying this copy is deemed positive. Google likes positive sentiment in ad copy. So I've gone through and I've just copied everything that's green and I have this document here now. Then what I do is I've created a prompt. I come over to chat GPT and I go to GPT for now. What I like to use is a GPT, an actual GPT there's two. I like to play with one school professor synapse. One's called super synapse. Now it's made by, These guys over at Synapse Labs, I actually like using these GPTs because it's acts like a bot or an agent. I'm going to click start, fire up the SuperSynapse what I've done is I've created this prompt. And, in this, I've got, I want you to act as an expert Google as copywriter. You have been conversing with Google as 20 years. You utilize the styles of legendary copywriters. chat GPT or any large language model likes to use markdown. Now, markdown is like a simplified version of HTML. And you'll see that headings are determined with these hashtags. Lists are done like that, bullets like that. And bolding, Is done like this. So there's two stars asterisks on the site. So I bolded that to make ChatGPT aware that this is important. from a HTML perspective, if you wrap some words in a HTML tag with bold, the search engines determine based on the tags attached to keywords if something's important or you want to pay attention to. Now, what I've done is I've got, 14. Very famous copywriters that renowned. and then I pumped it and said, I've grabbed copy from this website. I've told it, I've run the copy through the natural language demo, looking for highly rated, positive sentiment. Usually I'm using the copyright on my 15 headlines, full descriptions for each of the legendary copywriters. then this means 15 headlines for each for the first couple of when asking to you moved to the next, make sure you've brought 15 headlines, four students for each legendary corporate before we move on to the next legendary copywriter. Each headline, must be on its own line. Make sure they were high, right? High and seven, blah, blah. Can you help me with the split? So then I. Again, I use this. So this is a heading one tag. I'm going to copy this, come over to chat CPT, paste that there. Now I'm going to grab all of this positive sentiment copy from our website, it'll do a bit of analysis. This is how they've written this. GPT. It's giving you a quest. We'll start with, for David Ogilvy. So Ogilvy was, the first legendary copywriter on the list there, David Ogilvy. So they've kicked off with that, expand up the bar. I like this process. And I like to have, chat TPT go through all of them because there's all different types of headlines that you can use in descriptions. continue to the next one. So now it's going to say, sure. The next one should be Bill burn back. So this now it's going through each legendary copywriter and it is, based on its knowledge. It's tells you what his style is like, and it will then start writing copy around his style. Okay. and you essentially start getting a whole heap of different headlines and descriptions in different formats that you probably wouldn't, Even consider now, sometimes these are a little bit long. The headlines you might just need to tweak them and just them. Same with descriptions. They can go over 90 characters, going to grab another text document. And I'm going to grab all these headlines and I'm going to grab these descriptions. I've only done two, but ideally for this exercise, I would do all of the, legendary copywriters just so I can get different styles of copy and I can go through the headlines. I can go through descriptions and go, I like that. I like how that's worded or that really encapsulates what I'm trying to get in ads and you essentially can have a massive repository of copy that you can refer to when you split testing ads and copy. So I'll just copied. all that into a text doc, what I'm going to do is, copy all of that. Now come into another version of here. I'm just going to paste all of that I've just copied. Click analyze. Now this is probably what you'll get. Satellizing. And what should happen is because we've given positive sentiment to chat GPT and it's created different styles of copy around these copywriters, we theoretically should get positive sentiment back from our copy. So that's why I'm running this test start again that paste in my copy. from chat GPT, I'm not a robot go and we want to get the sentiment we got one there, one yellow one, but pretty well, most of the copy that we've got here is all green. So that's how you can do it with chat GPT. Now to use GPT 3. 5, if you got the free version, I find it's not as good, but if I'm using GPT, And I'll put these links. There's the GitHub prompt, so if you come over to SuperSynapse, this prompt is too long. If you click on the prompt here, if I copy this and I come into ChatGPT, what I want to do is add a link. Now the problem with this is you can only have up to 1, 500 characters and the super synapse is 3, 975. So that's why you can always use the synapse COR. If I copy that prompt. I can paste that in there and that's actually too long itself. grab the prompt, and just paste it in there and you're more or less done. Here it is. It starts. So you would do the same process. it's hit and miss. It's very spasmodic. You don't get the same consistency with 3. 5 as you do with four. but you can still get through it. and it's faster, it's way faster. So if I was to Copy that, prompt, and then I'll put in the same copy from our Solutions 8 web page homepage. You can see it's way quicker at doing the headlines, but like all the descriptions, yes, continue to the next. I hope you've enjoyed the video. We'll put links to, in the description below for the cloud natural language. Like I said, it's been around for a little while now. It's nothing new, but for those of you that don't, or weren't aware of it, it's a great tool to use. Ideally, what I'd like to do is create our own, or external API tool that we can use plugging into vertex, which is Google's natural language tool. In light of the fact that Bard Ultra was released today, I think, apparently it's supposed to be a GPT4 killer. We'll be testing that just to see how that goes. But if this has been valuable, please, Leave a like and comment in below and if you've got any further questions about this tool or anything else, feel free to pop them through. Until next time, have a great day. Bye.