AI Automation: How to Speed Your Work

Happy 2026. Hey, how's this for a New Year's resolution? How about you Master AI marketing? The AI Business Society gives you live training with experts who are getting real results. No hype, no fluff, just proven workflows that work. And you've got access to an incredible library of training from many of the incredible guests that you've heard on this show. So secure your AI transformation by visiting socialmediaexaminer.com AI welcome to the AI Explored podcast, helping you put AI to work. And now, here's your host, Michael Stelzner. Hello, hello, hello. Thank you so much for joining me for the AI Explored podcast brought to you by Social Media Examiner. I'm your host, Michael Stelzner, and this is the podcast for marketers, creators and business owners who want to know how to use AI. Today, I'm going to be joined by Rick Mulready, and we're going to explore AI automation. If you've always wondered whether or not artificial intelligence can help you automate a lot of the things you don't like doing or the things that you just frankly don't have time for, this is going to be the episode for you. We go really deep into, into how to actually set up AI automations. I think you're absolutely going to love it. By the way, if you're new to this podcast, be sure to follow this show. And you do that by simply clicking the little follow button on whatever app you're listening to this podcast on. And with that, let's transition over to this week's interview with Rick Mulready, helping you simplify your AI journey. Here is this week's expert guide. Today, I am very excited to be joined by Rick Mulready. If you don't know who Rick is, he is a coach and AI strategist who helps online businesses increase their efficiency and profitability using AI. His membership is the AI Playbook Premium community and his YouTube channel is at. Rick Moretti. Rick, welcome to the show. How you doing today?

I'm doing great. Thanks for having me on. I'm excited about this. How much time do you have? We can chat about this forever.

Yeah. Super excited to have you here. Today, Rick and I are going to explore how to use AI automations to speed your work. Before we go there, Rick, for those that are fans of the other shows that you've been on, you came from the marketing world and obviously I'd love to hear a little bit of your journey. Like, how did you get into AI? Start wherever you want to start.

You know, it's funny because when I first heard about ChatGPT, it's. It's one of those kind of weird things where I remember exactly where I was. I'm here in San Diego. I was in the car, I think I had just gotten a haircut or something like that. And I was driving out, I was stopped at a light, and I was listening to a podcast, and they were talking about this thing called ChatGPT. And of course, I'd heard about it but didn't know what it would blow up into. And that was very early on. So what chat CBT, November of 2022. Is that right?

November 30th? Yes, November 30th. Man, I got that date locked in.

And this was probably January of like, so just like two months later. And I was. I had my mastermind at the time where I was coaching online businesses, and they started bringing up. They're like, oh, you know, I started using ChatGPT to do this. And one of my jobs, if you will, as a coach is to keep them focused and not chasing shiny objects. So I was just like, all right, guys, stay. Don't get distracted by this shiny tool. And not like, two weeks later, after telling them that, again, this is very beginning of 2023, I was trying to come up with podcast titles and topics, and I was like, all right, I'm going to try this out. And I was blown away. And from that moment forward, I was like, this is going to change everything. And so for the past little over a year and a half now, I've just been obsessed. And having been in the online business space for ten and a half years now, I was just. I take all that knowledge and now I'm like, all right, well, how can I incorporate AI into running an online business so I can make it more efficient and, you know, increase profitability and all that stuff. But also knowing online businesses and having been in that world for so long, I know what they struggle with. And so how can I help them incorporate AI and leverage AI in their business? Because as you know, Mike, and everything that you talk about here in the show, it's like, if you're not embracing AI, all the other online businesses are, and you will be left behind. And so that's how important this is.

Well, and for those that might recognize Rick's name but can't place where. Rick was well known in the Facebook ads world, and he spoke often at social media marketing world, many, many times he's been involved in our different communities, and he's been on Amy Porterfield's podcast. So Rick, I have to ask, like, you made the full pivot, so there's people that are thinking about making the full pivot. Talk to me a little bit about what that's been like.

It's been great. And I actually get that question quite a bit because it's sort of a fear invoking thought for so many people. And it was for me as well. I mean, essentially, in 2023, just a super long story short, I went through burnout and I had to take a step back from the business. You know, I had my podcast, the Art of Online Business and I've been podcasting that show I've had for. I had for eight years and I had a previous show before that. But anyway, I just been doing this like coaching online businesses for so long and everything. I just reached burnout. I had been burnout for a long time, but just finally realized it in 2023. Took a step back and then during that time I stepped back. But I was also building an AI coaching chatbot version of myself. And this was before people were building these things. And I call it Pick Rick's Brain. And it is literally trained on my 10 years of running an online business. And I was working on this while I was on probably not the smartest thing, but I was working on this during my. My sabbatical essentially. And so I came back from that thinking I'm going to go all in on AI because I just find it so fascinating. I could, I saw the benefits of it. I saw where like, things are changing so fast that people even today have no idea where to start with it. And I also think there's a. A perspective that needs to be had, is that we are, we are in like the.0001% of this whole AI journey. And the fact that people are listening to this show right now and, and subscribe to this podcast is like you're way ahead of almost everybody else out there. And so I ended up selling my podcast in the fall of last year, in 2023, and just made the full pivot into, you know, I'm serving the same audience, but just serving it in a different way. And I'll be honest, like at the time we're recording this episode, I'm still building that up. You know, you mentioned the very beginning. I have the membership. I decided to kind of take a break from podcasting and go all in on YouTube. And that's been amazing. It's grown way faster than I had expected. So it's been fun, but not without, ooh, am I. I'm going to go do something completely different. Is this a smart thing to do?

Well, for folks that don't know Rick, he's a very good educator, very good communicator. There's a lot of videos, I believe, that you've done in our studio that have gone really big on our YouTube channel. And what I love about you is you dive deep, you really try to understand these things, and then you try to communicate them in a very clear way. And if there's anything in the world of marketing and business needs right now, it's clear educators and communicators. So that's a transition to my next question, which is there are plenty of people listening right now, whether they be creators or marketers or entrepreneurs, maybe are dabbling with ChatGPT and AI, generative AI in general, but they're not yet understanding the benefits of automation. So talk to us a little bit about why AI and automation together together, which is the current area that you're dabbling with, why that might be something they ought to pay attention to.

It's kind of the sweet spot right now. And I say right now because in a matter of, you know, six months, it could completely change and we could be more towards actual automated agents and AGI, meaning, like you tell an agent something to do and it does it all by itself, like, and. And that's it. But we're not quite there yet. However, the real win, I think, is the ability to take what you're doing with say, ChatGPT or Claude or what have you, and then not just have it do one piece of your workflow, but actually let's create an automation where you're, if you will, for lack of a better way to say it, like you're knocking out the entire workflow using an automation that will do all these steps and then AI within those step. So let's take this for example. If you are putting together a podcast episode or a YouTube video, there's obviously research that goes into it and like what is the introduction and all this other research? Well, that all can be automated and using a tool like we're going to talk about, like make.com a lot of people use Zapier, but within that, you're using ChatGPT, for example, to do the research to give you bullet points about what to talk about during the episode. Then after the episode is done, it can take the transcription, for example, all automatically write the show notes for you, create 18 pieces of content that you can post on social media. And where a lot of people are doing it these days is they're just doing one piece of that in a silo, if you will. So it's like, okay, I'm going to put my prompt in the chatgpt to come up with bullet points, but then it's a one off and then they go back and they do it for another piece of that workflow where, okay, it's super helpful, but it's also kind of inefficient. So why not create an entire automation that does those things for you along the way and as sort of checkpoints, if you will, like approval status for like, okay, it's come up with five Instagram posts before it gets posted. You have to approve it. But that's all an automation that generally either yourself, you would be doing it all those steps or somebody on your team would be doing it. So why not create an entire automated workflow rather than just the siloed pieces of that workflow?

And what is the upside to doing this? What have you experienced yourself?

Yeah, I mean you're gonna save so much time by doing that, where, yes, if you do sort of a one off piece of that workflow with ChatGPT, sure, it's gonna save time. But just think about. And one of the biggest challenges like, and I know that you know this and you talk about here in the show, but like one of the biggest challenges for people do I get started with this is they look at something like the example we just talked about of creating a, a podcast episode or, or a YouTube video or what have you. They don't have all the steps broken out that go into producing that piece of content. They just know like, oh, I show up on camera or I get in front of the microphone and I have an outline or whatever, but it's not like mapped out. Some people would call it, you know, an sop, Standard operating procedure for how something is done. It makes it a lot harder to incorporate AI and automation into accomplishing something when you don't have clearly the steps mapped out. And so when you do that, you're like, oh, I can use CHAT CBT to do this and then I can have it, the result of the audio, for example, then the transcription is done. And then the next step of that is I can have ChatGPT read that transcription and then create an Instagram post or a LinkedIn post or whatever it might be. So I kind of look at this as like passive. It's not passive income, but it's passive time Saving, if you will, because there is an element in investment of time to build the automation. But once you build it, it's built.

Yeah. And you're talking about a huge roi, right? Like, Rory Vaynerchuk has this book called Procrastinate on Purpose, which has been out for a long time. But he talks about how when you have to train human, sometimes takes 20 times more than it takes to do the task. But once that has been trained, in this case, we're talking about an AI, there's the forever benefit of never having to do it again. And this is the compounding effect. So one of the benefits of what Rick and I are talking about here today is potentially never having to do that thing again. And with that time, now you can be more creative, you can explore new ideas, you can do that thing you've always wanted to do. That's been on your bucket list. Now, on a little side note, for folks that are regular listeners, they may have noticed that Rachel woods was on the show. Rick, you're not going to be familiar because it hasn't come out yet, but Rachel woods was on the show talking about AI operations. And a lot of what we're talking about here today is very similar to what Rachel has been talking about. So you're going to see some compliments between what Rick and I are talking about and what Rachel and I spoke about. Start with like, how do we even know what can be automated? Yeah, like, because not everything can, Right?

Exactly. And by the way, Rachel is somebody who I learned a ton from early on. She's amazing.

Oh, cool.

Yeah. From an operations standpoint, she's brilliant. So knowing where to. Before I answer that question, Mike, I just want to finish that thought. I was just having as far as like putting the time in upfront and then you're seeing the benefit down the road. And I say down the road, that mean like month after month after month. Like one of our members in the membership, they automated, I think it was weekly emails. So their, their newsletter. And they created this automation that did this for them. They saved literally five hours a week and saved a thousand dollars a month in expenses because they had somebody doing this and that wasn't necessary anymore. So they gained a thousand dollars back from their monthly expenses and they're getting five hours. Five hours a week is a lot. And so whatever you do at that time to be more creative or to spend more time with your family, whatever it might be like, that's what this is about, to free up that time so that you can spend it on whatever you want. But where do you start with all that? I like to look at and it's the worst exercise in the world. But it's so insightful. It has gold nuggets in it and it's doing a time audit. Like where are you spending your time? And I like to tell people do it for like 5 to 7, quote unquote normal business days. So like normal business day would, does not include like you're going through a launch or you're on vacation, you're doing a little bit of work. It's like your normal business days, you're writing down everything that you're doing during the day and how long those things are taking you. And then once you have that list, you kind of go through and say, you know what, these are the quote, lower value activities that I would love to get off my plate. So if you were to hire like a VA, for example, to do these things, those are prime candidates, if you will, of tasks that you could get off your plate or create automations for. So that's kind of where I like to start is like doing that time audit, coming up with all those different things. And the other thing is like what are those? Just time and energy sucking activities that are just draining when you have to do them. So those are also prime candidates to look at. Okay, how do we create an automation out of that? Or you know what, we have to do this every single week and, and it takes us a long time to do it. And so those are great places to, to start. And you know, you might have a list of like five things. You're like, oh, I'd love to automate this or I'd love to use AI to make this stuff easier. Five things can be overwhelming. Like let's prioritize the top thing. Like what's going to give you the most ROI of getting that time back, if you will start there. Love it. And so let's just say you write a email newsletter, you know, and it takes you, however long it takes you. Well, what if you could create an automation or whatever it might be to help you with that and get that time back? Amazing. I got two hours a week back. Cool. I'm gonna go on to the next thing. And it's just you're kind of like taking those things away, if you will, to just kind of move through your business to get as much of those things automated, freeing up as much time as possible. And yeah, that's kind of how I talk about and how I think about moving through your Business to be able to be looking for those things to try to automate.

Cool. I want to take a little side rail and talk about the tech.

Yeah.

And then we're going to get back into kind of the steps to do all this. So tell us about the tools that you're using to make all this happen.

So in terms of the automation I'm using make.com we often hear about Zapier and Zapier is great. The reason I like make better is I'm a very visual person. And so the beauty about think of like people listening to this often, you know, we think about sales funnels or what have you and like visually seeing a sales funnel, for example, that's what make allows you to do with all of these steps. Mapping out a workflow, for example, it's very visual. So you can see like, oh, this is where the input's going to start and this is the over the end when this is the output or 18 different outputs and this is the entire process and what it looks like. So I love that aspect. And it's also che, I don't want to, you know, Zapier is great. Make, it's cheaper.

Well, and just to be clear for people don't even know what make does. Make is a connector, Right. You should clarify that it connects all sorts of different tech together, right?

Yeah, exactly. It's, you know, when you want to connect whatever slack to Airtable, for example, these are tools like Zapier or Make that can do that using, I don't want to get too technical but like using the APIs, be able to connect these tools. So I like to use MAKE for these types of automations to be able to connect these tools together. In terms of AI, I am a big believer in testing to see which of the models will do the best for the specific task that I want. So just perfect example, I was on a coaching call with people from the community earlier today and they were talking about, all right, which model ChatGPT or Claude might be best for this type of activity and this type of activity. And so I've used both enough to kind of have a pretty good idea of which model would be better. But at the same time I was like, look, I would absolutely test both. Like put the same prompts and they.

Change all the time. They keep changing.

Absolutely. So just like test, you can use the same prompt and the formatting slightly changes for Claude versus ChatGPT, but you can use the same prompt and see which, you can test them for free, see which gives you the better output and kind of, you know, kind of go from there. I'm also. I used to hate airtable, but my. I used it in the business for years and I just never could wrap my head around it. Like, why don't you just Google sheets? But then, I don't know, something clicked probably around the same time that I started really getting into AI where airtable is very AI friendly. And what I mean by that is it's very easy to connect to make.com for example. There's a lot of different things that you can do with airtable in terms of the cell, they call them records. And it also has its own AI within airtable that you can use. Airtable is very AI friendly, and so for that reason, I love it.

Okay, I have to ask a couple clarifying questions here. Make.com everybody who's listening. Good chance that if you have any software tool that you're using that has an API or integrations, they might call them. Right. Then there's a good chance that it'll work with Make. So that means you can take the something from that piece of software, push it through make into ChatGPT, and then have it processed and then push it back into airtable is really what I'm hearing say. Right. Airtable allows you, like most people, when they think of a spreadsheet, they think of like just a couple of numbers or words, but it sounds like you can put paragraphs inside these cells inside of Airtable. Is that correct?

Yep.

Okay, so Airtable is kind of like the database, and make.com is like the pipe. Right. And ChatGPT is one of the end points. Is that really what I'm hearing you say?

It's one of the processors. It's a critical cog, if you will, in that process. Okay, yeah. So think of it like. So MAKE is the overall container, if you will, that's allowing you to connect all these tools and yeah, I mean, you nailed it, Mike. Like, airtable is. Is the database and you know, like, okay, great, I want to keep track of the content that I'm posting or whatever I'm doing with this automation. It all lives in this database, I. E. Airtable. And you could do other things with it, approvals and stuff like that. But then, yeah, ChatGPT or Claude is just one piece within that entire automation.

Love it. Quick question. How many podcast episodes have you recorded? How many webinars have you hosted? How many client calls or team meetings have happened that are now just sitting there in your files? Here's the big Unlock. Those aren't just old recordings. They're full of insights about your audience, your brand voice and your customers actual objections. You just need to know how to extract them. That's exactly what AI educator Erica Stanley is teaching AI Business Society members on January 8th. By the end of this training, you'll have a repeatable workflow that turns every past recording into a content and data powerhouse. One that keeps paying dividends long after the mic's been turned off. This training is exclusive to AI Business Society members. But here's the good news. You can join us right now by going to socialmediaexaminer.com AI and start transforming your old content into, into new marketing gold. SocialMediaExaminer.com AI to join right now. Hopefully that was helpful for somebody who's like, maybe not super technical, but trying to understand how these things could all interconnect. I kind of think of it. Rick, you and I are a little bit older, but you remember back in the day when you would go to Radio Shack when you were a kid and you would buy these kits, you know what I'm talking about? And you would connect all these things together. Yeah, but you would connect all these things together and you could do stuff that you didn't realize you could do because you had wires and sensors and all that kind of stuff.

Exactly.

This is like that on steroids.

In the modern day version, all the.

Gray hairs are like, oh, I get you. Okay. All right, so let's say I've got a process I want to automate. Where do I start?

I like to start with the, with the end in mind. So like, what is the output? What do you want to accomplish? And then work backwards from there. So for example, I don't know if the audience, I mean, mutual friend, Pat Flynn. I remember last year we were sitting in a coffee shop here in San Diego and we were talking about AI and stuff and he said, you know what I'd love to be able to do? He's like, I'm always out for a walk and I'm having these great ideas and I want to be able to capture those ideas, but then also use the capturing of that idea to be able to write a podcast outline or a video script or what have you. So of course my brain starts thinking about, okay, so this is the end goal. We want to write a podcast script from an idea. So like that becomes the end goal and we start working backwards from there. So it's like, okay, if we want to take his idea and then turn that into the Podcast script. Well, what needs to happen to the idea for us to be able to do that? So in this example here, he was talking about, I want to speak into my phone, and that's all I want to do. And then it just triggers the, you know, in this case, the automation. So it's like, okay, well, if he's speaking in order to. For ChatGPT, for this example, to write that podcast outline, it needs to be a transcript. It's like, okay, so that's the second to last step. And very simply, in this. In this example, so I like to start and just go through the whole process like that. So start with the end goal. What is the thing I want to accomplish? And then what are the steps that need to happen in order to get me there? This is where. And this again, this is the step that most people don't want to do is to stop and think, well, what are the steps to accomplish that?

Yeah, most people want someone else to do that or a piece of software to do that.

Totally.

Yeah.

And think about, like, all right, well, if I were to sit down and write a podcast outline, what does that process look like? So, like, what's the. Yes, the end goal here is to have a completed outline, but, like, how do I get there? And it's the exact same thing here, but you're just getting clear on what the process looks like to accomplish it. And then how do I use AI to do that and automation to do that?

Well, and this is where, when I was talking with Rachel and some other people, they say, start with something you already know how to do.

Yeah.

So Pat already knows how to create a script for a podcast, right?

Totally.

So it would be very easy for anyone listening in this to think about their example. If you already are doing something, all you got to do is document what are the steps involved to get there. Right. But the difference here is you're imagining it's done in a different way. Right. You're imagining somehow it's done in a different way. So how do we change that? I mean, we still document the steps, but we're just hoping that it just goes from him talking into his phone. I mean, like, how do we go from documenting the steps to ultimately. I mean, I guess that's my next question. How can AI help with these steps?

That's really where the understanding of, okay, well, what can I accomplish with ChatGPT? What can it do? Or what can Claude do? Or what have you. You do have to have some sort of basic knowledge of understanding. You know what I can actually Type something into ChatGPT and it will give me some form of output. I can ask it a question and it will give me something in return. And I might like it, I might not like it, but then it's like, oh, well, I understand that I can continue to have that conversation and continue to refine that response and I can keep editing what it's giving me. So it makes it very hard to automate these types of things if we don't understand the possibilities that exist with these tools, which is why people are listening to this podcast, so they can understand it.

Well, yeah, and that's where I think it is important to understand the limitations of these AI systems. Like right now, you can talk to ChatGPT for extended periods of time, which is cool, but I don't think you can upload an audio file yet. And that's where you'd have to understand that you would need some other technology to move that audio file into a transcript. But in this case, you could bypass that if you were aware of the fact that the AI now 4 Omni modal, or whatever it's called, does accept audio inputs. And in that particular case, it's an advantage to know what the limitations are. Right. Because the old fashioned way would be to open up your audio thing on your phone, figure out how to hit record, and then figure out how to get a transcript. Right. And there's nothing wrong with either one of those steps.

Totally. And it's, it's interesting, right, because we're recording this in early August now and we. I solved this, by the way, for Pat and for. I've been asked this a million times for the exact same thing and solved it very, very easily now. But the funny thing is, is like in two months when, when Apple releases, what is it, 18.1 or whatever, the. Its latest iOS version, ChatGPT is going to be integrated way more into the actual iPhone. That will solve this problem. And I did tell Pat, I was like, well, you can just download ChatGPT onto your phone, have it on your home screen, so whenever you're out, you could just go into ChatGPT and start recording. And he was like, no, I don't want to do that. That's just too much work. I just want to have my voice memo and start recording and then of that it really is understanding what's possible with these, with these tools. And I say tools meaning like ChatGPT, for example, in what's not possible, like you mentioned yet.

Yeah. And for those that are somewhat technical, ChatGPT has an. Something called Whisper, which has got an API which is really good with transcripts. Google has their. Theirs as well. But ChatGPT is slightly better. And I would imagine you could take make.com and you could integrate using their API into OpenAI Whisperer and you can get it done that way. But we're going down a rabbit hole.

I was going to say. That's exactly. That's part of the process, right, what you just described.

Yep. Yeah. So, okay, first we got to identify what are the steps that AI can do, but now it's. Let's talk about the prompting because obviously this is a key part of this, right?

Yeah, for sure. So you keep hearing, we keep hearing prompt engineering. Especially last year in 2023, it was like, if you don't have prompt engineering skills, you are going to be left behind. And it is the most important skill of the next 10 years. Well, I recently did a video on the, on the YouTube channel about why I was saying and try to make the point, stop learning prompt engineering. Because these models, like you mentioned earlier, Mike, are like, these models are changing so fast and getting so, so smart that it's really the ability to be able to, it's. I mean, yes, look, problems, engineering, being able to understand, again, the concept behind it is important. I think what is more important now is the ability to be able to ask a good question, to be able to describe what you want ChatGPT to do. And people listening are like, well, that's easy to do. It's actually very hard. It's very, It's a very hard skill. And something I have to work on all the time is like, how can I ask a question in as such a way that I get the response that I'm hoping for? And, and again, that is a skill that you have to keep working on.

Give us some tips on what you've learned.

So essentially what I'll do is I'll just, I'll start having a conversation with ChatGPT or Cloud or whatever model I'm using. And so I will ask a question and I already know the type of help I'm looking for from it. And so I'll ask the question and I'll see what it gives me, you know, and so just like, for example, how do I figure out. Or I could say, I want you to help me figure out the pain points of my target audience. So, okay, that's a straightforward question, but there's no context to it whatsoever. Like, I'm not telling it who my target audience is and So I could ask that question and it would give me a response. But a better way to ask that question is I could say, please help me figure out. I always like to say, please, please help me figure out the pain points of my target audience. And then I could add to that question, what information do you need in order to give me a complete answer? So that's sort of like version two of the question I've asked. And it's a much better question because now I'm saying I want this help. It's kind of like, tell me how you can help me better. And so it's that I love it. And you keep iterating on that. So if it asks, it'll give you a list of things it wants. And so let's just say you give that in the information to it gives you a response and you're like, this isn't what I was hoping for. And so again, it's like I want to iterate on the, the clarity of the question that I'm asking. And that's where a lot of people stop. They don't do that. And they think, oh, this doesn't work, or this doesn't sound like me, or fill in the blank. And it's not the AI, it's the question and how you're asking it or the information that you're providing it that is lacking. So it's just, it's the ability to be able to clearly communicate what you want. And if you don't know what it needs to answer your question or to help you ask it, what do you need?

You've come up with a really cool. When we were prepping for our notes, you came up with a really cool couple of things that everybody ought to have in their prompts. Do you have that information handy by chance?

Yeah. And a lot of this I learned from Rachel, giving her full credit. And again, this is something that what I've seen as 2024 has gone on is less important, but it is still really helpful. And a lot of people have heard of this, like, give it a role. Give. When I say it, give the AI a role. You are a world class conversion copywriter. You are best in class. Fill in the blank. So you're basically giving it a filter from which to work. You're telling it, I want you to act as this person to help me in such a way. So it's like I want you to think through the brain lens, if you will, of this person. Perfect example of asking questions if you don't know what a Helpful role is describe what you want help with and ask ChatGPT to give you three different roles. I did this the other day for. I forget what it was.

Oh, that's brilliant. I love that.

Yeah, I was, I was helping one of our members or something with like a sales page or something and I was like, you know what, I know a conversion copywriter, I know a conversion rate optimization specialist, but I wanted it something else. And so I'm like, what are five roles that would be great at answering this question?

Probably growth marketer was in there as my guess.

Exactly. So again, it's the ability to ask that question. So give it a role and then tell it what you want it to do. And so this is where you're giving it the task. And this, again, this comes down to how well can you clearly communicate what you want done. It's very different to say I want you to write a podcast outline for me versus you know, I want you to write a podcast outline for me that is for a 45 minute episode about X, Y and Z. So once you've done that, then you can. What I like to do is give it your tone of voice, your voice. Paragraph. That is a term that I got from Rachel also. And it's basically saying when you're giving me your response, I want you to write it like this. I don't know if you want to go into that, but you can create a paragraph that describes how you speak or how you write.

Love it.

Podcast, transcript, video transcript, emails, blog posts, whatever. You can create that separately and then use that in all of your prompts and then the requirements. So I like to include. So here's a perfect example. So people are writing ad copy for Facebook or Meta ads. Well, if you're using ChatGPT to do that, a great little tip is to say use the Internet. You gotta be using ChatGPT for this because Claude is not connected to the Internet. Use the Internet to ensure that you are using meta's advertising best practices when writing your response. Again, you're kind of giving the hard work, if you will, to the AI because you're telling it, hey, make sure when you answer that this is best practices and use the Internet to find those best practices. So now you're giving it another, another filter and then the two other pieces is AI loves examples. So the more examples that you can give. So let's just say that you want it to write you an email. Very just simple example. And you're not quite sure how to tell it what you want. Your Email to look like. Well, say you find somebody else's email that you love. Just the format of it, copy the email, include it in your prompt and just say follow the same format as this example right here. So now it has something to clearly follow when it's giving you an answer. It's not copying the text or copy within the email. It's like, I like the format of this email. So AI loves examples. And then the final piece of that, of this prompt is constraints. So it's like you're, you're giving it sort of the, the guardrails if you will. You know, like when you're bowling when you're a kid and you put the little bumpers in the gutters so like the ball won't go in. It's the same thing. You're telling the AI to like stay between the, the gutters, if you will. So for example, I would give a lot of the prompts that I do for, for my business is like, I don't serve E commerce business. I just, I honestly never have in ten and a half years. I love E comm, but it's, it's just not a niche that I went into. So that would be a constraint. So I would say, you know, please do not include any whatever I'm asking, E commerce examples, E commerce examples, physical products examples. So that's a constraint that I'm giving it. I'm trying to guide the prompt as much as, or the output, I should say as much as I possibly can. And again, if you all don't know what to put in for some of these things, you can ask it, you know, what is an example of a constraint that I might want to include in this? If you don't know and it will tell you.

Okay, so we're talking about AI automation. We've gone down a deep hole which is really useful because we really wanted to dive into like how to actually prompt the AI to do its part in this. Now zooming back out to the make.com side of things. You got any tips on like what we ought to be thinking about when we're working within make.

So let's just say we figured out the workflow or the automation that we want to do by working backwards like we talked about before. So you have this step sort of outlined and the first thing that you're going to want to put in there. And this would be the same for if you're using Zapier. It's like you need the trigger. So like what kicks off this automation? So just as an example for the we'll use the capturing your ideas on your phone. So for me, the automation that I set up is I created a private channel in Slack called Voice Notes. So when a voice note lands in that Slack channel, that's the trigger. So like that's what kicks off this whole automation. And so that's where you want to start is like, all right, what kicks off this entire automation? Maybe it's we have another automation where a new Google Doc being put into a Google folder kicks off the automation. But again, I like that you have to understand what these steps are that you want to that make up your workflow and then you're just putting that, then you're just creating that in. In make. Make, I will say, can be intimidating for people who are just starting out. They have an amazing training library that walks you through. I think it's called make foundation or something. Pretty sure that's what it is. Step by step, it's all free as part of like, it's really, really good. And the other thing just like most other things is like just get in there and start messing around with it. I taught myself and, and I am not a techie person. I honestly, people are like, really, Rick? Like, I am really not a techie person. It's just, it's kind of get in there and just start playing around with it and honestly have fun with it. It's like, what can I automate? What can I automate in my business? Or what can I run an experiment on to try to automate and build this out in make. But it is really important to have those steps outlined and then what is the trigger that will kick off this entire automation?

You mentioned much earlier in the interview that you could have what appears to be a pause in the automation for approvals. Can you talk a little bit about how that works?

I see a lot of YouTube videos out there that are talking about make automations and creating social media and stuff like that, which I would never post something on social without reviewing it first. You know, it's like, yeah, ChatGPT can write a great social media post that is going to go on whatever, LinkedIn. But I want to see it first.

Could be totally wrong.

Yeah, I want to review it first or I want somebody on my team to review it first before it goes out. And so this is another. Another reason that airtable works really well is that you can create sort of that approval system, if you will, so you can have a column in there that is approved or ready to publish or whatever. It is that you want to do and it is a little bit more of an intricate automation but connecting make an airtable in this way so that the content gets created, say let's just call it from the transcript and it writes that LinkedIn post. Well, the LinkedIn post would then go into Airtable and it sits there waiting to be approved before it automatically gets published to LinkedIn. And so a lot of people just talk about, oh yeah, like I can, we can use ChatGPT to write a social media post and then have automation just automatically post it. But it's like, well, okay, but wait a minute, I want to review this before it gets posted to, to the platform. So it's a great way to leverage again the capabilities that exist within airtable to be able to. All right, these are all the posts that I need to, to review and approve. And you might create 30 days of content in a matter of an hour. And so all right, great, we're going to do that, but we want to approve it first before it actually gets, you know, scheduled to. If you're using a social media scheduling platform or what have you, you got to review it first before it goes out.

Rick, thank you first of all for sharing your insights. I know that a lot of people that are listening, this automation thing has clicked for them for the very first time, hopefully. And some of them may want to actually connect with you. So if they want to find you on the socials, what's your preferred platform and if they want to check out your business, where do you want to send them?

Actually the preferred communication platform is, I would say definitely I haven't posted. I say all this, we don't post too often right now on Instagram, but I still check it. DM me on Instagram, YouTube, I'm putting out regular videos talking about these types of things and other AI solutions for online businesses. Again, it's at rick Mulready on YouTube and then I have the school community, the membership like you mentioned, it's called the AI Playbook Premium. But I also have you can go download or you can go use if you will. I created a ChatGPT prompt generator. So it's built for you. All you have to do again, this comes down to it will write the prompt for you, but you have to clearly articulate what you want done. So like I want to write 90 days of emails or whatever it is and it will write the prompt for you. And so that is inside, free inside of. I have another school community for the lead magnet here. If you will. You can just go download it for free. It's school.com, it's s k o O L.

Awesome.

And you can download the prompt generator right there.

Rick, thank you so much for coming on the show and sharing your thoughts with us today.

You bet. Thanks, Mike. Appreciate you.

Hey, if you missed anything, we took all the notes for you over@socialmediaexaminer.com a18 and also be sure to follow this show on that favorite podcast app that you're listening to. And if you like this episode, would you share it with a friend? If you like the show, would you share with a friend? If you want, you can tag me. I'm most active on Facebook and on X Facebook it's Elsner on Exits, Ike Stelzner. And would you also check out our other shows, the Social Media Marketing Podcast and the Social Media Marketing Talk show? This brings us to the end of the AI Explored podcast. I'm your host. Michael Stelzner will be back with you next week. I hope you make the best out of your day and may AI help you become more successful. The AI Explored podcast is a production of Social Media Examiner, AI Business World, early bird pricing ends on January 16th. You can save 300 on your tickets. Register at AIBusinessWorld live today.