88 | Boost business growth with AI infused LinkedIn strategy w/ Celeste Yamile

Are you aiming to leverage AI for data-driven decision making and to significantly enhance their LinkedIn strategy?

Join us for a session on how to upgrade your LinkedIn strategy using GPT-3 as your personal data analyst. Celeste Yamile, a seasoned expert in blending AI with digital marketing, will guide you through a practical workflow that leverages AI tools to refine and perfect your LinkedIn content strategy.

Discover a Three-Step Revolution:
Data Harvesting: Learn how to extract valuable data directly from your LinkedIn profile.
Insightful Analysis: Celeste will demonstrate how to transform raw data into actionable insights using AI.
Strategic Implementation: Find out which content drives engagement and how to replicate success.

Celeste’s approach isn’t just theoretical; it's a battle-tested method that has significantly boosted her digital presence and can do the same for yours. Whether you’re aiming to enhance personal branding or amplify your business’s impact on LinkedIn, this webinar will equip you with the knowledge and tools needed.

Celeste's practical methods have empowered countless professionals to optimize their digital strategies effectively. Her ability to turn complex data into straightforward, executable strategies makes her sessions particularly valuable.

About Leveraging AI

• The Ultimate AI Course for Business People: https://multiplai.ai/ai-course/
• YouTube Full Episodes: https://www.youtube.com/@Multiplai_AI/
• Connect with Isar Meitis: https://www.linkedin.com/in/isarmeitis/
• Free AI Consultation: https://multiplai.ai/book-a-call/
• Join our Live Sessions, AI Hangouts and newsletter: https://services.multiplai.ai/events

If you’ve enjoyed or benefited from some of the insights of this episode, leave us a five-star review on your favorite podcast platform, and let us know what you learned, found helpful, or liked most about this show!

Transcript

Isar: 0:00

Hello and welcome to a live episode of Leveraging AI, the podcast that shares practical, ethical ways to leverage AI to improve efficiency, grow your business, and advance your career. This is Issar Metis, your host, and we have a special topic for you today. As you probably know, LinkedIn is a business goldmine, but it's only a goldmine like a real goldmine, meaning you need to know how to mine the gold in order to actually benefit from it. Now, when AI started coming out and content creation suddenly became easier for people who are struggling with it. many people jumped in and started creating AI content. The problem is they're just creating more. Content instead of developing a strategy based on actual real data from linked in itself to help them create content that will actually convert and drive business. So the problem is the questions you're probably asking is, okay, so what do I post? What days do I post it? What time of the day? What topics will drive the most engagement for my audience? What drives sales? From my audience, what people actually click to go to my website and so on and so forth, all these questions, you don't have to guess this data actually exists in combination of LinkedIn data, plus some other sources. And if you know how to mine that data, going back to my example, so pun intended, if you know how to mine that data, if you know how to analyze the data. It will tell you everything you need to know, and then you can use AI, not just to analyze the data, but also to create the right topics and post it at the right time, which will drive engagement. Our guest today, Celeste Jamile, is a LinkedIn content guru. Her company, Temporal Labs, helps businesses and individuals Create LinkedIn content that converts and she does it at scale because it's based on actual data. So she takes away the guessing game by taking data from LinkedIn and other sources and using AI to analyze them and then create the content versus let's just create content, brush it on the wall and see what sticks. Example for what I just said is her latest post from today. So thank you for that. We didn't plan that, but great post today is called a strategy I used to go from 248 to 27, 000 views on my videos. So that's obviously doesn't happen by luck. It doesn't happen by just posting videos. You get to these kinds of numbers. When you have real strategy and real process behind it. And Celeste is going to share with us exactly what's her process. So you can do it as well and have a systemic scientific way to create content that converts on LinkedIn. This is obviously extremely example, extremely important for anybody who's in business today. And so I'm really excited and honored to welcome Celeste to the show. Celeste, welcome to Leveraging AI.

Celeste: 3:34

Thank you. that was a really nice introduction, by the way.

Isar: 3:38

this is what I do.

Celeste: 3:40

Yeah, but you're absolutely right. It's not luck. And I share that post sharing my process that the way I use AI is to create the strategy and to optimize the content creation. So in that case for the post, I was Focusing a lot on the hook and that the idea was valuable. you need to validate your ideas with data, right? And also sharing content that is just strategic according to the goals of your audience and the thing points, but of course, any type of strategies, it's going to be useful if you don't deliver in the content. So you start, you promise something, you optimize that with data, but we need a lot of practice to be able to master the content because, even someone that like knows nothing about content, but just create something really valuable can create something that resonates with others. But here, I'm here today to share how to optimize that. Also for the ones that we are just starting so we can optimize as much as possible. So in the level, whatever level we are, like if we are beginners, very medium level or advanced, we can increase the results that we already have. So yeah, that's the goal. So I'm going to start sharing this screen.

Isar: 4:48

Yeah, fantastic. so yeah, let's just dive into your process. I think the key here, and that's maybe your biggest and most amazing differentiator is the data side of things. Like a lot of people know today, how to create content with AI and the people who know it better know how to create it to sound like them and so on. But your really unique thing is that you've learned how to harness and harvest the data from LinkedIn itself in order to actually make this a lot more scientific. So let's jump in. And by the way, for those of you who are listening and not watching the screen, because you're not on LinkedIn right now, first of all, join us every time we do these live. So you can see this live on LinkedIn, but if you're not, if you're just listening, we're gonna describe everything that's on the screen. So if you are, driving or walking your pooch or doing whatever it is that you're doing when you're listening to the podcast, you can still follow with us.

Celeste: 5:38

Yeah. So the first thing that I'm going to use is ChatGPT. And for this, we have this workflow for LinkedIn. So of course, we need LinkedIn data. And the way that you can gather it is that LinkedIn already gives you all of all the things that you need. So if you go to your profile. Right now, I'm on my LinkedIn tab and in the top right quarter, I see an icon that says export. So you need to make sure that you have selected the data of the last year of the last year. You'll see a button to make that happen. And also, you start exporting the data, you click the button and you will have your. Analytics ready to go. So the next step is, by the way,

Isar: 6:25

for those of you who are, again, are listening, it doesn't give you the data right away. Some of the data, it has to compile and then sends you an email with the rest of it. So there's some that you can get really quickly and some of it comes a few days later.

Celeste: 6:38

Yeah, the great news is that, for example, you can analyze the last 30, like the last year, so you can have as much data as possible. But if you want to see how are you improving, then you can select, that you want the last 90 days, the last month or the last two weeks and something like that. So it depends on the type of things you want to analyze. But the next step after that is to go to. To your Google drive, and then you upload that data to Google. And this is pretty important because we, the download that we just did, we are going to have all this data compiled together and ChatGPT needs, needs to needs this like smart, small pieces of content to analyze. So once I open this in Google drive. I have my file and I will go to again, file, I will go to download and then I will go to tab separated values or comma separated values. This is just a way to download, the data so you can have ChatGPT can interpret this better. And you will do this for every single one of these tabs. So I will do this for engagement. Then I will click posts. Like the next tab that I have, because it downloads like all your data, it downloads your engagement, the top posts that you have, it downloads the followers. And what I like about the followers, it's really cool because here you can see my dark past, in the screen, because when I started, I just got one new follower per post. I was getting like zero followers every time I was posting and it was increasing until I was getting like 200 followers per post I was doing once I have the strategy. So you can, with all of this data, you can really analyze how are, how has been growing and everything, but yeah, it's amazing

Isar: 8:31

again, for those of you not watching the screen, we're looking at an Excel table or Google sheets in this particular case that starts a year ago, because that's the data we downloaded and it shows every, The date of every post and how many you followers you got. So there's a date, number of followers, date, number of followers, and the numbers in the beginning are 1 0 0 0 3 11 8 0 0 2. Very small numbers. I'm not trying. No, I think this is awesome because this is a year ago. And now every post is in the dozens of new followers and sometimes in the hundreds of new followers, meaning this process works now, as far as the specifics of what, of what Celeste is saying is that it comes when you download the data From, LinkedIn, it comes in several different tabs and Chachapiti doesn't know what to do with the other tabs. So you basically save each tab as a separate file, so then you can load each separate file to Chachapiti. Okay, so now we have those files, what do we do then?

Celeste: 9:30

Yeah, so now once we have these files, we go to ChatGPT and here you can see that I already did this because I wanted to take the time to really think about the questions that I wanted to ask and really think about the strategy I wanted to develop. So you go to ChatGPT and you have an option to upload your files.

Isar: 9:53

So

Celeste: 9:54

you start loading the charts that we just downloaded and we download it one by one. So this means that we have, four charts on the screen right now. And I say, I start with something important. I say, okay, analyze the data internally. And once you understand all the things that are going on, answer, okay. And I will start asking you questions because I want to give chatgbt this time to start, To start analyzing because if you just bombarded chat with questions, it will be like, okay, here's the first thing I found. And probably it's not pretty accurate. So you want to make sure that you do this thing first. And then here's when things start to get interesting because, I say, okay, from this chart, that is a chart of top posts, give me the URL of the ones of the 10 posts that have more like significant follower increase. So after I asked this question, it started, it gave me a chart with the date of the post URL, the impressions, engagements and follower increase that I was having. And this is, this has been pretty useful because now I can click in the post URL and I see what are the exact posts that are giving me more followers. So I say, okay, if I want to increase, The audience that I have, if I want to grow, what are the types of things that I need to keep posting in order to be able to achieve that, right? And the same happens with, for example, the posts where I have less followers. And I asked to have like most updated data. And this is pretty interesting once I was analyzing at this, because in the chart that I'm seeing right now, that I'm looking at right now, I see that, for example, I have a post with 80, 80 K of impressions, 18,

Isar: 11:51

000 impressions, just over almost 19, 000 impressions. That's huge.

Celeste: 11:56

Yeah, but it's interesting. Let me tell you why, because with the follower increase, I have 30 new followers with this post. So lots of impressions. That's nice. 30 followers. Cute. But now, in the chart where I have, the ones that give me more and not the ones that give me less, I have another post that has 12, 12, 000, which is less. First of all, it's those impressions, but what happened here? I have like more than the double of that of new followers. I have a 97, 97 new followers. It's Whoa, are you telling me that impressions are not the same as followers? So this type of vanity metrics, like art, I love impressions, right? But are they actually being useful? So what I did in this I just need to analyze what are the things that I'm doing in these types of posts that are not giving me, that are not helping me to grow, but are giving me a temporary, a temporary win. But it's just the amount of impressions I have today, but it's not going to help me to keep growing my audience.

Isar: 13:04

So I want to pause it just for just a second to do a quick summary and also talk about the pros and cons. first of all, this is incredible, right? We took data from LinkedIn that is free. You have access to your own data as long as you've been posting. if you haven't been posting on LinkedIn, maybe you have a trick for that as well. But if you have been posting on LinkedIn, then you can see all that data and you can download it and you can use it. What? Chachapiti does, which is really magical. It goes to the four different files and combine them in its own head, to one big database of information. And then it can combine all the parameters together. So basically the date of the post, a link to the post, because that's what, Celeste requested the number of impressions for each post, the number of engagements of each post, meaning people who, liked it or wrote a comment and so on. And the number of followers that were added because of this post, or it's not really because of this post, but it's in the same day so that it doesn't really know whether it comes from that post, but it's people who started following you at that day. And what she found out is that there's no direct correlation between the number of impressions and the number of new followers. Like in some cases, there are higher number of engagements with less followers, right? And for Celeste specifically, her goal was to grow the audience. And in this particular case, that means that you need to optimize for the posts that achieve that versus the post that gives you higher engagement, which again, depending on your goals, like you can say, I want to get a lot of engagement. That's fine. It just depends on what you're trying to drive. So that's where we are. We have this data. We have the links to all these posts, the posts that drove a lot of engagement and the posts that drove a lot of, followers. What do you do next?

Celeste: 14:51

Yes. So the next thing is the analysis, right? Because I have, if you notice the way I am prompting this and you need to be careful that you learn how to prompt because just because you know how to write, does it mean that you're going to be able to express your thoughts in a way that a machine can understand? Because we forget that. Because ChatGPT sounds like our little friend, we forget that it's a machine, right? But this is pretty important. For example, I'm giving it, I'm saying, okay, from this specific chart, I want you to give me this. And another thing is that I'm specifying the format where, like, where I want to get the information. In this case, I specified that I wanted a chart format. We are going to see another type of format, in the next steps. Thank you. We also, I also specified the date, impressions, engagement, like all the columns that I wanted to get in my chart. So I could analyze everything. So it's not log that I'm having this output that allows me to.

Isar: 15:52

So going back to good. Prompting, you need to tell it what hat it's wearing. In this case, probably like a social media analyst, you need to tell it what you want it to do. So describe the type of data and what you're looking for. And you need to specify the format of the outcome, because the format of the outcome could be a tweet, could be a blog post, or in this particular case, could be a table. And if you're doing a table, tell it exactly what you want in the columns. So you're going to get the exact outcome you want. And even within the columns, you can tell it What format you want it, like date and time, just date. do you want it in thousands? Do you want it in hundreds? Like whatever you want as far as the outcome so you don't have to reformat it afterwards for whatever need that you have. So you can specify the format in very higher detail, and then you'll get the kind of results that, Celeste is getting. Okay. awesome. What you do next?

Celeste: 16:44

What I do next is to start analyzing. of course I already said one part of the parts of the analysis, but the second thing I noticed is, as I told you, this post, like the post that has 80, 18, 000, was about AI. It was about artificial intelligence, but it was about artificial intelligence, like itself. It wasn't about AI plus content, but like almost Seven of the posts that I have in the top are about AI plus content. So I already see what are the topics that are allowing me to grow. So I know that I don't, I only, I don't need to post only about AI, even if it's that, even if that's trendy, that gives me views, but that's not helping me to, to Yeah. But when you're down in a specific topic in my, like in my case, Is where I see more growth. So that's also one of the things I noticed. And now what I do next. Other types of questions that I like to ask is for example, what's the average amount of engagement that I get through the week. And again, as we talked before, I asked to have the information in, in the graph. So I can see that visually, I'm a visual person, I like it. And now I see that the day where I have more engagement is usually on Mondays and Wednesdays, like the best day it's a Monday. And the reason of this, it's because I start, I see after analyzing this that the audience that I have takes LinkedIn as a job. So it's usually content creators or people that have a business on LinkedIn. So they take this, this LinkedIn game as a job. So they usually are pretty active on Mondays and they, on Fridays, they're like, okay, like maybe a little bit less of commitment on Fridays. So if I want to increase my engagement, I already see that probably I can live. the days I post, instead of being a Friday, maybe on Thursdays? Because, I can get an increase on engagement there. And if, if you're looking at this right now on Thursdays, I don't have a lot of engagement, but it's pretty decent. It's still pretty decent. And the reason that I don't have a lot of engagement is because I don't post this day.

Isar: 19:08

Yeah.

Celeste: 19:09

So even if I don't post, I, I still think that there's opportunity to grow my engagement on those days, because it's already pretty decent, even if I don't post. So it's just something about analyzing the data and understanding how it works.

Isar: 19:22

I want to touch on what you just said, just like on the underlying concept of this. You need to remember that the fact that you don't post on LinkedIn doesn't mean there's no activity around you on LinkedIn because your post, yes, it gets the most amount of attention probably in the first 30 minutes and then maybe a few hours, but it's still there. Like I get. They're really weird ones. a few weeks later, somebody will comment on a post that I did a few weeks ago. I'm like, how did you even find it? That's buried like the height of the Eiffel Tower scrolling down on LinkedIn to find it, but it still happens. But definitely within the following day, following two days, people are still commenting on older posts because that's when they got in and that's what the algorithm showed them. And You can still benefit from additional engagement, especially if you engage back, if people comment on your post or like your post and you go back and you connect with them or comment back or ask them a follow up question. you can drive additional engagement without posting. And again, the graph that's on the screen right now is clearly showing that there's three days of post, which shows a lot more engagement, but there's still 40 to 50 engagements. on days that do not have posts, just because people are still engaging with posts from previous days. This is phenomenal.

Celeste: 20:31

Okay. So I see that according to my data, on Saturdays or Sundays, I don't get a lot of engagements here. And that's because usually like in general, it doesn't need to be like this for you. But most part of profiles are not active on these days. So I see that in my strategy, I usually post my. My post of promo where I promote my services and everything else, helping people on Wednesdays, because this allows me that, as you said, the post keeps showing to other people. if I post on Friday, a promotional post, it will almost die the same day because LinkedIn usually promotes, the 1st hour, then the next 6 hours and then in the next 24 hours. on Sundays, I don't get a lot of engagement already. But yeah, that's the goal. And the next And that's the last question that I like to ask to chat TV team is what is the amount of impressions that I get through the week. And again, I want to see these type of analysis in a graphic too. So I can analyze that with my own thoughts easier. And I see that again, on Mondays, I usually get much more impressions. And I I want to analyze this. I can also ask for the links that like for the posts that are giving me these, the biggest amount of impressions, but the way I like to use this data, it's to learn how to grow, engage and monetize an audience. So to grow, like we already saw the first workflow where I analyze what are the things that helped me to have more followers and grow a community. To engage, I have the second question where I ask what type of engagement I have through the week and I can analyze if the days I'm posting are actually the best ones for my type of audience that I'm getting. And then to monetize my audience, I usually like to have this amount of impressions. Because, for example, when I work with or collaborate with brands I like and they say, Hey, can you help us to promote this post or this tool? I say, okay, yeah, but I will do it on Monday. Like it's always like that. I will do it on Monday or I will do it on Wednesday because I know that I have more reach on those days and I can make sure that the workflow or the value that I'm adding to that company or to the audience it's trying to like reach the most amount of people or also if I want to grow the audience. And I have a piece of content that I know it's really valuable. We usually, we have this feeling, right? When we create content, we are like, Oh my gosh, this is the content is one of the best ones I have found. or it's adding a lot of value because I have this new piece of information that I didn't have before. And I think it can be useful for more people. I usually recommend these to post on the, I usually recommend to post days on the days that you have more reach because something's going on there. Maybe you have more movement in your audience. Maybe, yeah, you have something going on. And I thought this wasn't really important. Like you hear people on LinkedIn talking a lot about, what's the most important thing that you need to comment a lot. Some people like to complain that they don't want to comment one hour per day to be able to grow their accounts. But it's just the way the algorithm works. It's built to. To create networking, it's built to connect professionals. So the way the algorithm works is that it's just that when you, when the algorithm knows that you have connection with someone else, like in the comments, in the DMs, it will promote your content. yeah,

Isar: 24:19

absolutely. I want to add one thing to what you said as far as the importance of this. a lot of people, when they define when they want to post and so on, just go to blogs that say, Hey, the best time to post on LinkedIn is on Wednesday at 10 a. m. And I'm like, that's ridiculous because that's specific to your audience, your content, your type of stuff, your industry, it's different for every single individual. And so posting when everybody else is posting. First of all, it's not always the best idea because then everybody else is posting and there's more noise to compete with. But also you have the, the opportunity right now to literally look at your data and see what's working and what's working and what's not working or what's working better or what days. And you can even run an experiment, just test it out for a month and a half. And just say, I'm going to just post on Mondays and Thursdays moving forward. And I'm going to post this on Monday and this on Thursday. I'm going to see if there's a difference. And you can test different things out or different things in different weeks and see what actually works best for your audience with your topic, with your niche and make decisions based on actual data versus on general data that everybody else is using.

Celeste: 25:33

Yes. And it's pretty useful too. Be able to make the types of things. And I, if you're looking at this right now, you will notice that I was opening my documents to be able to see my carousels and it was because I want to show something. I was creating one of the pieces of content that I thought it was going to be like pretty useful because it's a piece of content that was saying about how, what it was explaining how. Scammers were making money with AI and I wanted to show it to people, how to provide these types of things. So I posted is the first time. And then I posted again, the same piece of content after I was like growing a little bit more of my audience. And you will see, if you're looking at this right now, that the first post has 300 views, like literally 300. And I was like, Oh my gosh, how can this be true? I thought it was going to be pretty valuable. I spent four hours creating this carousel. It can have 300 please. So I was like, okay, there's something going on right here. And I started analyzing these data. Of course I have less data on those days. And I look at this types of statistics that I'm, I was showing you at the beginning, the days where I have more, more engagement, the days where I was able to grow my audience a little bit more, and I was starting to apply this data. And the shocking here, the shocking thing for me here was that the second time I posted this, it got, 50, 56, 000 impressions. Like 300 to 56 and I understood a really important lesson with when I did this at the beginning that it was the fact that your content, like it, it's going to hurt. Okay. It's going to hurt, but your content doesn't matter. Like the content, it can be as valuable as possible sometimes, but it's not going to matter, what the content says, but who is saying that.

Isar: 27:42

I want to add to what you said, because I think it's critical. First of all, I got a question before I'm going to say what I'm going to say. Was the post itself the same or just the content within the post was the same? Did you change like the caption?

Celeste: 27:55

No, nothing. It's the same

Isar: 27:57

thing.

Celeste: 27:59

Yeah.

Isar: 27:59

So I want to say something here that is critical, that there are so many parameters that impact the success of a post and you need to optimize at least for some of them. But the interesting thing is if you know that, and that's where I disagree as far as the content doesn't matter, this is a good piece of content. You spent a lot of time and research and effort. And if you were watching this, you can see it also looks amazing. Like you thought this content is going to be successful. If you post something that you think is valuable to your audience and it doesn't work, try to figure out why. if you already know your audience and you know what works and you're like, holy crap. I thought this is going to be like my best post ever. And I got crickets. Yeah. Something is broken. And assuming, something about your audience, it cannot be random. And this could be, The day you posted it, the time you posted it, what you actually wrote. So maybe the piece of content is awesome, but you didn't use the right hook. Maybe you should have mentioned somebody in the post itself that is relevant to this to get to capture the audience. And if you do this, it's perfectly fine to repost. Old posts, if they did not work or even if they did work. So now you have a bigger audience, more people are following you. Take something that did okay. Six months ago, change the post a little bit. Now that more about your audience research, when to post it and post it again, in this particular case, it went from 300 impressions to what? 56, 000 impressions. So it's. You can reuse good content again and again and get bigger and bigger ripples of impact if you learn in between and make the right adjustments.

Celeste: 29:47

Yeah, that's absolutely right. And, there are more ways to use AI for content. This type of workflow was just for analysis. But I, I have a framework that I like to preach. I always tell people to use this framework. But it's the C framework. And it stands for Structure, Example, and Analysis. Okay. You can always use AI for those three things. And those are the, like my favorite things to use AI for it, because I think some people, fall into the hype of you can create content and ask to have this amount of posts and go viral and be amazing or rocket emoji and everything else. But the fact is that. Because for example, just chat GBT is a probability based model. It creates content based on the highest probabilities that something has to happen, but something is happening. And generic content has a lot of probability to happen because, it's something that we all know, like you can detect AI content because you think that you already know that it feels like it's common. It's a lot of people know that. Using AI to analyze is something other things that I'd like to use it for is that, as you mentioned, there are some pieces of content that I think are valuable. So it's worth for me to do some A B testing. It's not worth it. Only for emails. You can also do some of your pieces of content. for example, I'm here on touch right now, and I'm trying to look for a chat where I have, some words. I have, I have this GPT right now, for example, hook genie. And I want to create hooks for any type of idea that I want for my content. So I can be, okay, I have an idea about X, help me to create some hooks. And this GPT it's trained with some of the examples that I've been collecting from top copywriters on LinkedIn. So it's going to give me information that it's actually useful. I like to make this, I'm gonna, again,

Isar: 31:56

I'm gonna pause you for a second. For those of you who don't know what GPTs are, so GPTs are these mini small automations that you can create within ChatGPT if you have the paid version. If you don't have the paid version, start paying for the paid version. It's a night and day difference in the value that you're getting. it's the best 20 bucks a month I've ever spent by a very big spread, but it allows you to create these little automations. But the cool thing here. Is that you can provide these automations with background information, you can upload files, you can upload documents, you can connect it to the internet, you can do multiple things. In this particular case, what Celeste is doing, she's saying, okay, I'm going to look at the people who write the best posts possible. The ones that gets the most amount of engagement on LinkedIn that are preferably in your field and not something else. And they're like, okay, let's learn from them. How do I learn from them? I'm going to, I'm going to add them as examples to this automation to say, okay, these are performing amazing. I want you to use this as the structure, the format, the inspiration, and then we're going to see what she does next. But that's like the baseline work that you have to do in order to get this benefit. And anybody can do this. Just find people in your field, copy their posts and paste them into as reference material to a GPT that you can create. And then what's the next step? How do you actually prompt it to create your posts?

Celeste: 33:15

Yeah, for example, what I was sharing with you, what I was sharing with you right now is a GPT, the, this custom version of chart GPT that I am creating. I can have examples from the top copywriters and I can know how to apply that to my content. in this GPT that I'm doing, I'm uploading the best data that I could get about the hooks. And I say, okay, so GPT, you have this data. According to my specific goals, the audience that I have helped me to create the hooks for my idea. So it gives me around five folks per idea I have. And it's pretty useful because I'm not letting AI creating the content. Like I'm not letting it to do, I'm not automating everything. It's just optimizing as optimization. And the other thing that I was mentioning to you was that I also use AI to add formats to my posts. And this is one of the most useful workflows I found because I'm not a copywriter. And I don't have intention to become a copywriter. Because I'm like more, I like more video. I want to become a business person, right? So we all have different goals. And I see that other way of using AI is to add formats to your thoughts. So in my screen right now, I'm going to put one of the examples of this. And I use a voice extension for chat to PT. And I see that I have my thoughts here. I just say, Hey, GPT, I have this idea of a post. Help me to add the format to this. So it's breaking everything down, it's acting like a copywriter, and it's helping me to create the format. And, yeah, it's basically that, those three things that we were talking about, the C framework, structure, example, and analysis. That's the best way for me to use AI for content, because if you fall into the hype of wanting to create content or wanting to create everything from scratch and become like, become a top voice from GPT content, that's not going to happen. But if you use it to optimize everything, then that's a huge difference.

Isar: 35:30

so let's go back to this. Let's dive into this particular example. If you can zoom in a little bit on the screen and let's go step by step and see what is that you're doing? So you basically click the record button and said, what's the idea that you have? And what did you ask ChatGPT to actually do in there?

Celeste: 35:47

Yeah, this is a cool thing about the GPTs, that once you prompt them, you only need to be like, okay, click, let's go. So I always recommend someone to create GPTs for their own workflows. And actually, I, it took me weeks to build one of these. but I give it for, but these are for my clients. those are the type of army that I give for my clients to use. And it all comes down, as I said, from analysis of top posts. So for example, a LinkedIn post has a structure. It has an anatomy. So it has, for example, a hook, a re hook that supports the hook. It's you can delete these pain points without, going through all of these. Journey or without spending X amount of time, on the workflow so that without do this without this, like the second part of the hook, it's called the re hook and it helps to support your point and cause an, a second, a second emotion that helps for, yeah, that helps you connect with others. that's part of the structure. We have a hook, a re hook. We also use the golden rule, the rule of three, where you usually group elements in, as I said, in groups of three, or the stair format, where you, if you analyze the content from top copywriters, you will see that they usually organize their content or their thoughts, and they go from If they have a bullet point, they will go from what has less amount of characters to what has more. So it will look like a stair format. if they are making a stair with the words and it looks amazing. So this GPT can also help us to make that. And at the end, we have a call to action or a power statement. And this power statement is where you give the closure to all of your posts and you explain what's the main key takeaway for everyone. What's the main message? And as well as CTA, if you want to promote something or if you want to, say, okay, just comment below what you think about this. yeah, this is the way that I usually train these GPTs. And from data, I can see, for example, I noticed that some of the posts don't pass the, 56, 58, sorry. 58 characters per line of text. Because if you pass these 50, 58 characters or six 60 characters, in your, in the screen of your phone, like the next word will go down. So these 60 characters are the perfect length. So it can fit the, it can fit the screen of your phone. Yeah. And usually top copywriters know that, and they only use 60 characters per post. So that's part of the training of some of these GPTs.

Isar: 38:35

Yeah. So going back to what you said before, there is a process that anybody can do, right? You can upload people from your industry and use them as references. And then you can ask your GPT to optimize for multiple aspects. Some of it is the structure, some of it is the hook itself, like what needs to be the hook. Some of it needs to be, how many characters are in a row? How many rows are in a paragraph? How many paragraphs you want to have? How many spaces you want to have? all of these things make a difference as far as how people are going to consume your content. And if you ask the GPT to optimize for all these things, it will. Yeah. And then if you can give it an idea. It can give you a draft for the post that then you can edit and actually post yourself.

Celeste: 39:22

Yeah. And as I said, the best thing that I recommend to everyone is to build your own GPTs or have someone to help you to build the GPTs. But don't do it with prompts, please. don't buy some of those prompts that are out there on the Internet. Like I know they can be pretty useful. Like those guys really spend the time to try to find the best things possible. But even with the best types of instructions. It's not going to create good content because. Because of the training data, it wasn't the right data to create content. If it was just the data for general knowledge. So it's not going to do anything for you and it, but if you don't use prompts and you actually use examples to train your GPTs, they are going to be like 10 times more powerful. And an example of that. Once you have your GPTs, the best thing in the world is that you can put in the bar, you can put at, and then you put the name of your GPT. in my case, and I'm going to show you in my screen right now, I have a GPT that it's called Brainstormer. And this Brainstormer, it's trained on my content strategy, it's trained on, on pain points and different things. And I say, okay, help me to create a month of content. what are some of the ideas that I can create for my, for the whole month? And I'm planning week one, two, three, and four. And after that, I am mentioning at GPT that it's called Hoop Genie Video, because I'm going to create a content for my videos, and it's going to give me the hooks, and I don't need to, here's the thing, you need to create a specific, GPT for every single workflow that you have. So I have a GPT for content ideas. I have a GPT for hooks. I have a GPT for format because, these are like little assistants and you need to be really specific on what you want, but it's pretty amazing because you can be commenting and mentioning your different GPTs in the same chat and you can be using the same information. And it will help you to optimize a lot of your content. So a huge pain point for me and my clients was that we don't know what type of food we can post, or we run out of ideas after three months of posting every day. these types of workflows really help when you're stuck and you can create your own, if you just take the time to analyze everything you want. You collect the data and then you give it to GPT and say, okay, help me to create something similar, please. And you can, yeah, you can do pretty cool things with that.

Isar: 41:53

This is amazing. I want to pause you just for one second to again, summarize this really brilliant segment. what Celeste is doing here, she's saying, okay, to write great content, I need to be a great copywriter, which I'm not. So I will build a machine that will allow me to mimic the work of great copywriters. And that machine is fed by the content of all these copywriters, but each Little cog in the machine will focus on something specific. So she created five, six, 10, I don't know, many GPTs, each one focusing on something very specific. One focuses on structure. One focuses on ideation. One focuses on the hook in the beginning. One focuses like each and every one of them focuses on one aspect of great content writing. But then within a single chat in ChatGPT, so not the GPTs themselves, but in a regular chat, you can use the app symbol. To call any GPT that you want. So any one of these cogs in the machine, so you can go in and say, at name of GPT, this is what I'm trying to do right now. This is the content I want to write. This is the idea that I have helped me come up with a hook and they will come up with a hook. But then within the same context of the same conversation, because you're in the same chat, you just calling a different GPT and saying after GPT, this is what we're trying to do. Okay. I want you to help me come up with the right format for this kind of post and he will do that and so on and so forth. And I want to add something else that will make it, connect this to what we talked about in the beginning. You can also do this with again, what, Celeste is showing us here is that she's planning like a whole month out what to post on which days and you can use. A GPT that was trained on the data you pulled from LinkedIn to tell you what to post on which days based on the data that you have, right? So the, even the scheduler, quote unquote, can be based on a GPT that was trained on the data of what days works best for what kind of content based on your content, your audience, your experience, and so on. And the only thing you need to do is once a quarter, go download the data from LinkedIn, and then you can Upload the new fresh data into the GPT to fine tune it to what's happening right now versus what happened a year ago.

Celeste: 44:10

Yeah, absolutely. and if you noticed, I was looking for a post because you pop up some workload, like some idea that I wanted to show with you. And is the fact that this really works. the fact that I spent whole weeks trying to build this for my clients wasn't luck. And the results are not luck too. Because for example, if I go to my hook genie, and I go to the ideas that it's giving me. the last one, for example, says stop using, this type of workflow to train your GPTs. And that's a post that I'm going to do and start doing this instead. And this is a type of hook that it's for controversy. And it's one of the hooks that I'm going to use for my next posts. And if I go to my data, and I go to my, most viewed videos, for example, I see that this one has 41, 000 impressions. And it has a hook in the video that it's about controversy. It tells you why you should start using Google Calendar and start using other things instead. Because it's more efficient and more productive to use that new thing if you use, your calendar to plan your content and everything. And it was a hook about controversy. And this is the same hook I have right here in my GPT. And again, this is data. This is data. It's connecting the dots between my analytics and, the types of things I'm creating. So I already know because it's based on data, that this thing will work and that I will have a big amount of impressions if I'm able to deliver value. Like after they cook, because that's the thing. You can have the best cook possible, but you need to be able to deliver in this value. So people can be like, this is amazing. I'm gonna, I'm gonna follow up like that. But yeah, that's the last thing I wanted to share.

Isar: 46:01

That's amazing. Yeah. And again, going back to the beauty of this. So I know some of you are thinking like, Oh my God, but she has been posting for a year. She has all this data, but the cool thing with this process, it doesn't have to be based on your data. You can, yes, you can. You cannot download somebody else's data. But you can copy and paste data from other successful people. And yes, you're not going to have a year worth of examples, but within a 20 minute work. Or an hour work. You can have 50 examples of the top performing posts of people that you are following from your industry in your niche and put them in an Excel file manually, literally copy the post, copy the number of engagement, copy the number of shares, copy the number of, re shares like all the data that you can have, put it in a Google sheets, save it as a CSV, upload it to ChatGPT, and you can start training models. On all the things that Celeste had just taught us. even if you have zero data of your own, because you've never posted. And again, if we're going back to saying Oh my God, I don't have anything. How do I get started? She showed us. And I appreciate that so much, Celeste, that you took us with you on your journey. A year ago, you were getting zero. Engagement on her post, like zero people. And now there's 50, 70, 80, 200, 000 people that are seeing her post, for her most successful post. And that's obviously a huge jump in a single year, meaning anybody can do this. If you follow this really amazing process.

Celeste: 47:37

Yeah. It's well, it's honestly one of the best ways I've. Bow to use AI for, because sometimes your personal judgment is not useful when you want to grow. You're like, yeah, I'm amazing. I know. And then you're like, Oh my gosh, what was I thinking? and it's really common when you're just starting, you keep, you spend a lot of time learning and downloading things and freebies. And then you're like, I'm ready. But It's not going to be useful if you don't open your mind to be failing a lot of the times and can really analyze this with ChatGPT because like it's not lying data never lies. And as, as you mentioned, you don't need to have your own data to be able to create those types of workflows. Like when I was starting, I created, a GPT that is called it is what's called copy mentor before, but now it's copycat. I just changed the name because I think it's cooler. Sorry. And the thing that is GPT makes is that we take the best performing posts, for example, Justin Wellish or Laura Costa or the best copywriters in the world. And then we turn those, posts into templates. And I really love this because I'm like, okay, now I can see the blanks in the things here. And I can see how they are creating their posts and how they are using the audience desires. And I'm going to give you the link to

Isar: 49:03

these

Celeste: 49:05

GPT, if you want to experiment, it's called copy copycat, it creates templates for every single post. And as I said, it's a way to analyze the data. And it's been pretty useful for me to know how to be a copywriter without being one.

Isar: 49:21

Awesome. And we're going to share, we're going to share that link in the show notes. So if you're listening to the podcast, just scroll down or up or however your podcasting platform works and look at the show notes and we'll post that link. Celeste, this was absolutely brilliant. This is really, Really good. And, I really appreciate that you're sharing all this information with us. If people want to follow you, work with you, learn from you, what are the best ways to connect with you?

Celeste: 49:48

Yeah, the best way to connect with me is it's on LinkedIn. I hear you can there you can find all my like all the content that I share. And in the world, you will find a button that it's really obvious there it says my store or you can access, like my Google route, and there we have these resources like the GPT that I'm going to share with you. Where I have the most valuable guides like I just post a guide and then it explodes. It has a lot of views. People love it. They don't load it. And then I shared those resources in the boom road. So other people can access that as well. So you can find This value on gum road or connect with me on LinkedIn and we want to, if you want to work with me together can do that as well to build your audience and your community only doing as well.

Isar: 50:33

Awesome. Amazing. Thank you so much. This was really great. Amazing energy. Phenomenal content. lots of thought behind it. And I really appreciate you taking the time and sharing it with all of us.

Celeste: 50:44

It was awesome. Thanks for having me.

Isar: 50:47

Thank you. Bye everyone. if you are not here live with you're missing out. So we do this almost every Thursday at noon. And there's people on the, on the chat here on zoom and there's people on LinkedIn chatting. And so just join us, follow me. Sorry, mate. He's on LinkedIn. Like I said, I do this almost every single week. And if you do that, then you can join us and ask questions and be a part of the conversation and not just watch the recording with retrospect. That's it. Thank you so much, everyone. Have an amazing rest of your day, an amazing weekend, and we'll see you next week.

Celeste: 51:21

See you. Bye.