Leveraging AI

142 | AI Meets Automation: Build a Content machine that converts and scales with Keith Moehring

• Isar Meitis, Keith Moehring • Season 1 • Episode 142

Share episode

Content creation takes time—but not anymore. This live session will teach you how to transform your content strategy using AI and automation, saving you hours every week. You’ll learn how to build a seamless, automated content workflow that identifies key insights, pulls relevant references, and drafts SEO-ready articles—all in a few clicks.

Our special guest, Keith Moehring, Managing Partner at L2 Digital and marketing powerhouse, will guide you through a practical demonstration. Keith’s expertise in automation and AI isn’t just theoretical—he’s used it to revolutionize workflows for businesses of all sizes. He’ll break down complex processes and teach you exactly how to combines tools like Make and Claude/ChatGPT to simplify and amplify content creation.

We’ll dive into real-world examples:
- Create content from scratch, referencing other sources automatically.
- Use Google Sheets to smartly direct workflows using a “reference table.”
- Optimize your output with integrated keyword strategies.

This isn’t just another webinar where we tell you what’s possible

About Leveraging AI

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!

Speaker 3:

Hello, and welcome to another live episode of the Leveraging AI podcast, the podcast that shares practical, ethical ways to leverage AI to improve efficiency, grow your business and advance your career. This is Isar Metis, your host, and we're going to talk about the topic that maybe is the most common usage of AI today. Generative AI today, which is content generation. Now, lots and lots of people are generating content with AI right now. And the reasons are very obvious. It's very easy to do. You generate, you can generate social media posts, you can generate blog posts, you can create images and videos, and literally any kind of content you can imagine can be generated with AI, but there is. a few problems with the way most people are doing it right now. The first problem is that it sounds vanilla, like literally your content is going to sound like everybody else's content, because this is how these tools work, unless you give it additional information on how to write like you. The other problem is that it's not optimized for your audience. So without telling it exactly who's your ICP or who you're writing for, what's the platform, what's the goal, it's, Again, gonna write a very generic thing that may or may not achieve the goals, most likely not. It's also not optimized. Or, your keywords or the things you're trying to optimize it to, depending on the industry you're in, if you're writing blog posts and so on. And the other problem, which is one of the bigger problems is that most people are just using it for the content creation itself, meaning the very It's one step out of a long step of content generation. There's still ideation and research and summary and keyword research and tone and branding and content review. And all of these things are actually a part of creating content. And yet most people use it just for the content creation. They're missing out on actually using this for all the other steps of content creation. And so there's a lot more that you can do, even if you started using AI for content creation. So there's two ways to solve this, or at least some of it, one of it is to start paying for additional tools to like writer or Jasper, who are built for content creation, and they're going to solve some of these problems, but they're not going to solve all the other steps in the process. The other option is to build an automation with tools like make or Zapier or any 10 that will combine a lot of these steps into one automation and will allow you to run it as a content machine without you having to do or. Not having to do anything or having to do a lot less in the middle. So our guest today, Keith Mooring is the CEO of a marketing agency called L2 digital. And he has been in leadership positions in the marketing agency space for years. And in the past year and a half, he has built more and more automations around his business. To make his life easier and provide more value to his customers faster. Now, Keith and I have met in an AI conference in Cleveland a couple of months ago, and his presentation absolutely blew my mind because what he did is he built content machine using make plus. I don't even know how many other data sources to really build it for his audience, optimize for keywords, connecting to two different things in his company to make sure it's the right tone. And with people in the loop to evaluate the different steps of the process, which are critical for you to get proper content before you send it out. Lucky for us, he's going to share with us today exactly how to do this. So we're going to start with an introduction to What are even tools like these automation tools that I mentioned, make, and then we're going to dive into how to do the entire content generation process, connecting multiple aspects of data in order to get content that is optimized for keywords, optimized for your audience, speaks your language, your tone, your, and so on, while still allowing people to interject in different steps of the process. I find this. Critical for the future. And I find this really exciting and hence, I'm really happy to have Keith as a guest of the show today. Keith, welcome to leveraging AI.

Speaker 2:

Thank you so much for having me. I'm very excited to be here and I love talking about this stuff. So this is going to be a good one.

Speaker 3:

Yeah, listen, I, you and I chatted a few times, during the conference and after the conference and I follow a lot of people and I build automations myself. And really the stuff that you were doing was thought after. And again, we're going to, we're going to explain to people how to even use make for those of you don't even understand how it works, but I understand how it works and I use it regularly and it still blew my mind because the way you put the process together was amazing. So I suggest we dive right in. You can walk us through this for those of you who are joining us live. So first of all, thank you so much. I see already a few people, sharing where they're from. And, a little bit about themselves. So please go ahead and do that. Like both on LinkedIn, as well as in the zoom, tell people where you're from, tell people what your role is in the company, what are you trying to learn here? And I will try to take that into account when we do this. If you have any questions and you're here with us live, please write them in the chat, I'm monitoring both the chat on zoom and I'm monitoring the chat on LinkedIn live. So wherever platform you're joining us from, feel free to ask any questions and I will. Try to pay attention as much as I can and respond to them either in the chat or I'll ask Keith the question so he can answer and then we'll answer it in the live. If you're not here joining us live, you're missing out. We do this every single Thursday. So come join us in the following weeks. And we're going to drop a link in the show notes where you can sign up to join us. So it will be easy if you're listening to this after the fact, for those of you who are just listening to this in the podcast, afterwards, we're going to explain everything that's on the screen. So you're not missing out on anything. And with that very long technical aspect, I will let you lead the conversation. Keith, the stage is yours.

Speaker 2:

Okay, so you want me to share my screen then?

Speaker 3:

Yes, please do.

Speaker 2:

All right, let's do that. I'll go into presenter mode here. Okay, AI powered automation. the idea, what we're going to try to talk through today and I'll give you a high level overview like Isar just said though, but it's, what we're trying to do is, Take a standardized process, something you guys do on a regular basis, and build it so that we could automate 70, 80, even 90 percent of the entire workload. and things that if we build it the right way, as soon as one thing happens, a couple minutes later, we have a polished asset that we can then review and then get out into the world. So real quick background. So I started L2Digital, it was in 2020 when I started it, and the whole idea was to build scalable sales and marketing platforms. so build the technology, the integration, the processes, and the assets to help smaller and mid sized companies scale their growth. and, Things are going really well. And then a friend of mine introduced me to a technology that kind of rocked my world a little bit. The technology was called IntegraMAT and which eventually becomes make, but at the time it was IntegraMAT. And if it was, it's an integration system. So if you've ever used a system like Zapier, which connects one technology to another technology, IntegraMAT is a lot like that, but on steroids. So it gives you not the only ability to connect to tech on one side and the other side, but. Connect multiple texts in the middle, but then a conditional logic. So if this, then go down this route, if this go down that route, it was a, if you've ever thought about things in a programmatic way, it's the greatest tool ever. so I started integrating it into a lot of what I was doing and it was going really well. but the problem was, eventually I got to a point where. Capacity wasn't enough to, to didn't match what the workload was. So I needed help. I needed to bring in some, some support. And at the time the company was me and my cat. And for all of those who've had cat colleagues, they're not the best. they're talkative. They will interrupt the meeting anytime they choose to, but generally speaking, they don't get a lot done. So I need to help. I needed something to really take some of the workload off of my plate so I can get more done. Luckily for me, this was around the same exact time that Open AI released chat GPT. So I started playing around with this tool and it, I'm sure like all of you, it just blew me away what it was capable of doing. And so I started introducing it into this project and this type of project. All of a sudden it is like one of my best friends. We, I started using it for writing emails, drafting reports, blog posts. Explaining third grade math concepts to me so I can explain them to my daughter, building out a brainstorm, like brainstorming ideas, writing code strategies, general companionship. it was everything I needed at the time. So what I decided to do was it, I didn't have the revenue yet to hire someone. At the same time, I didn't want to bring on an intern that I had to train for three months and they would go on their way. So what I decided to do was I, Named chat GPT, my intern. So I actually just added a browser tab or a bookmark to my browser so I can open it whenever I needed to. and it was great. Things were going perfectly for a long time, but then more and more, I kept using it, the more problems, challenges kept to kept arising with how I needed to use the tool and what it was capable of. A couple of them, big ones were for starters. Every time I needed something, I had to go to chat GPT. I didn't, I had to go to its office and I had to come prepared with a full prompt and I essentially had to change my processes and add an additional step. Now it did take some of the workload off my plate, but I still had to go one other technology, one other place to get some stuff done. if I needed to do math. Or any sort of processing of unstructured data, forget it. the math, it just predicts the next character. It actually doesn't solve the math problem. and then the unstructured data, if the data isn't clean, it isn't an exact format it needs to be in to be reviewed and analyzed the stuff I was getting back was completely bonkers. it, I needed to. Before asking it to do anything, I needed to have all the context needed to assign it the project. I needed to do the research. I needed to go pull the brand and style guide. I needed to pull past examples of blog posts. I needed to do all this additional work to be able to assign it a project. So, it was a lot more, it was a lot of extra work on the front end for me to do a lot of this stuff. because in, in many cases when I would go write a blog post, I have a lot of that in my head already. the chat GP did not, so I had to bring all that stuff to the conversation. I had, I worked with a couple of independent contractors. And some of them are tech savvy, some are not. So the less tech savvy, I had to train them on how to use the tools. And even then, they were relatively disinterested in utilizing it to its full capabilities. So despite training, they didn't put in the extra effort to get the full benefit and value out of the tool. So the results were mediocre at best. And then finally, it never, it doesn't integrate with any of the technologies I use. On a daily basis, like it doesn't integrate with HubSpot. Doesn't integrate with Google Analytics. It doesn't integrate with Google Docs. you can build them, but out of the gate, out of the box, chap, GPT doesn't do all that kind of stuff. So again, I had to go into those tools to get what I needed out of it. Then to bring those to the conversation, rather than it being able to do all of that work on its own. So this was a struggle. I was,

Speaker 3:

I want to pause you for just one second to say how. These challenges exist literally everywhere. So I teach, courses, regularly, by the way, for those of you who are listening, there's another course opening on November 18th. So if you want to join a course that's been running for a year and a half and hundreds of companies have been through, it's your opportunity to do that. But, within those courses and within my consulting and speaking on stages, I get to interact with a lot of people and the same problems everybody have. And sometimes for you, a lot of it is external. People that work with you, but for many organizations, the people in the company, okay, our people are not techies. They don't know how to do this. There's definitely no way they're going to integrate, our CRM with chat GPT. so it doesn't help them on the day to day. And it's too many. steps along the way to jump through to do this. So it's a serious problem having that fear of technology or just not being experienced enough, and they're not feeling comfortable. And then you're like, I'm just going to do it my way because I don't understand this whole process.

Speaker 2:

Yes. That happens all the time. And even if you train like a client, for example, on how to use it or just do it for this one little process, they will always revert back to it if they are not fully comfortable using the tech, the way it needs to be used. but. So I was voicing my concerns about chat GPT to a friend of mine. And he's have you tried playing around with using make? So formerly IntegraMAT using make with the GPT or chat GPT integration. What? I had no idea that existed. So I jumped in and started playing around with it and what ultimately came out of it just blew my mind. So you can use make to go out to your share drive and pull in a document. You can go out to HubSpot, grab some data. You can go out anywhere you need to go, grab data, and then compile all of that. And then send all of that information over to a GPT with a prompt and get back that finished product. In other words, all the prep work that had to go into getting that final output out of chat GPT, I can automate a good chunk of that with using make. So I started using it for this project and started building process automation for this type of project and this type of project. Soon enough, I had a full content marketing specialist at my disposal and I can manage most of it through an email address. Like I could literally just send a prompt to an email and I can get an output in my inbox real quick. So what I'll do, what we're going to do here is I'm going to walk through. At a very high level, how these tools work because a fundamental understanding of how these integrations operate is key to being able to build these kind of more advanced automations to take a lot of this workload off of your plate and automate a lot of that effort. And then once I go through that at a high level, we'll do a real simple, tangible example. and then I built one specifically for this where we'll get into and I'll walk it through step by step exactly how it's built. That'll show you how to build like a full content production automation. So the integration tools, there's a ton of them out there. Zapier make now what all of these companies. lack in terms of logo diversity and, creativity, they more than make up for in capability. So these things are extremely powerful and they all generally work the same way. And there are three main components to how these things work. There's a trigger, there's a couple operations, and then there's a final output. So I'll dive into each of these and explain how they work. So on the trigger, so the trigger is simply, something happens that starts the automation. So there's two main types of triggers. There's a time based trigger, which will run at a certain time interval or date or whatever it is. So I can set it to run for run every minute. Five minutes, every hour, every night at 12 o'clock, every week on Sunday at 1130, whatever that time is, I can set it up so that every time that hits, it'll automatically run. The other type of trigger is an action based trigger. In other words, some event happens that sends information into the automation and it triggers. The next series of steps. A couple examples of this would be a new row is added to a Google sheet or a, a form gets completed on your website. Those would be examples of triggers. And what's nice is when a trigger happens, not only does the automation start, but a packet of information gets sent into the automation. In other words, the trigger grabs some form of data. A good example, like the easiest way to understand it is someone fills out a form. every field, they feel like figured are filled out. that's a mouthful. Every field they filled out within the form itself, all that data can be sent over into the automation. And so now to start this automation, I've got a packet information to work with. And so what it'll do is the trigger will then send that information as an input into that first operation. And if the operations are simply a function or a set of instructions to process that data in a specific way and create some form of output. So that packet of triggered data goes in to the first operation. And on the other end of it, a new packet of information is created, based on that, that data was put in and whatever rules or instructions are as part of that first operation. So now, in other words, in this automation, I've got two packets of information that I can play with. And what's nice is I can send either or both. Into that second operation. And so now that second operation has a lot more to work with than the first one did. And so it has a series of instructions and steps that it's going to follow. And it's going to take the provided information and generate its own output. And with these automation tools and integration tools, you can put as many of these operations in places you want. there's two here, but the one I'm going to show you probably has three. 13 to 15 operations that happen between the trigger and the output. and each of them has an input and creates an output. And then finally, that final output there, we need to send it somewhere. So that final step is that output. So that last packet of information, whatever that is, gets packaged up and then sent off to wherever that needs to go. Whether it's creating a doc, sending an email, generating a, a report, and then saving that in some sort of database. All of that, that, the way these tools work and with the many different technologies they integrate with, I think Make integrates with over, I'm not mistaken, like 900 different technologies. Yeah, I could be wrong on that. it's a ton. So really any marketing tech or sales tech that you're using can probably integrate with these systems or at least integrate through an API and send that information off.

Speaker 3:

and so I want to pause you just for one second. again, for those of you who've never used these kinds of tools before, there's a few words that scare the hell out of people. It's integration and APIs definitely are on the list. And the cool thing about all these tools is that they make you not know anything about this, right? So what these tools have done is that, okay, we will do all the heavy lifting. We will connect behind the scenes with all those different technologies through whatever means needed. Most APIs, but not all of them. And you don't need to know anything about this. All you need to know is where the data is coming from. And this could be You said 900. The reality is it doesn't matter how many, because all the main tools that we're using are in there, right? So if you're using the main email platforms, whether it's Outlook or Gmail or whatever, it's going to be there. If you're using CRMs, and there's four or five CRMs that 98 percent of the world is using, They're going to be there. If you're using an ERP system, it will probably be there. If you're using a marketing automation tool, it will probably be there. And so unless you're using something that is homegrown, that nobody has heard of, it will probably already be connected. And really all you're doing, what this provides, I always to laugh about these tools, that they're the glue of the internet right now, right? They allow you to connect together any tools that you're using to any other tools, transferring any pieces of information you want from one to the other, By while doing specific operations in between. So the data that you pass over makes more and more sense to the next system that you're passing it to. So it's literally an amazing tool that requires zero programming, technical API skills, and just understanding what Keith just told you on how these things work. Some experimentation, YouTube videos, and you can build literally any automation you can imagine.

Speaker 2:

Yeah, I think that's a really good point to emphasize is you don't have to know how to code to use these tools and just have to understand how data, what data is available and how to process it and ultimately where it needs to go. So they're very cool. They're very powerful. They will give you a bunch of tools and weapons at your disposal that you wouldn't have had otherwise and would have otherwise had to pay developers thousands of dollars to get access to. Agreed. this is how the integration tools work at a high level, an abstract view, but in many ways you need to see a tangible example to really drive this point home. I've put together a very quick, we'll talk through this one at a high level pretty quickly, but in Make, this is how one of these workflows would be set up. And activate it. So we'll take writing a case study as an example, very simple example. So if it was for a client of mine, we have a Google form. And after the production team gets done with a project, they fill out the Google form. And as soon as they fill out that form, what happens is a row is added to a Google sheet. And as part of that row has all the information. The, production team entered into that form. In other words, everything they added in about that project and how it was completed is now available in this row. And so because that row was added now automatically I've got, I've automatically triggered my automation. Because there's a new row on my sheet and that sheet is attached to this automation, so it automatically runs. And that initial packet of information is everything that's available within that specific, that row that was just added. So I've got date, I've got name, I've got client, I've got industry, I've got all that information available to me within this automation. So what this, the scenario here is going to do is going to take that first packet of information, essentially that row data and send that off to a open AI assistant. So if you've ever used, OpenAI's custom GPTs, assistants are a lot like that. Essentially they're the developer side of chat GPT. They're very easy to set up. I'll show you one in a little bit on how these work, but essentially you pre program this assistant. With a prompt, with files, with background data, whatever is needed, you build that into the assistant by default. And what's nice is you can, with these assistants, you can put the data in as placeholders. So for example, like the company completed a, the blank project for blank, which our company name, and I can insert that information into the prompt via that trigger data. In other words, the company completed a, content project for company X, which is a 150 person company and blah, blah, blah. In other words, I personalized the assistance prompt with the data from the form itself.

Speaker 3:

Yeah, and this, and to help people kinda understand in a very quick summary how this works. If you've ever built a custom, GPT assistance are the same thing, but instead of having the user interface that we used to from chat GPT, it connects with the API in the backend, which allows you to then connect it to anything in the world, which is maybe the biggest limitation of chat GPT, which is. Confined to chat GPT. So if you want to have a custom GPT connect to anything else in the world, that's the way to build it. You build an assistant. It's almost identical to how you build GPTs, but then you can connect it to stuff like this. And in this particular example, the prompt that gets filled out and sent to the custom GPT includes. information that make gives it from the form that was filled out in step one.

Speaker 2:

Yeah. And the other thing is not to worry about the coding side of it too, because building out these assistants is just as easy as interacting with a chat GPT. Or yeah, it's very easy and simple. but in this case, I've got a prompt, the prompt is designed to write the case study. So we'll have a title of an introduction. We'll have a challenge statement, a project win statement, that kind of thing. And The and you refine these over time as the outputs come out. But yeah, I built this one out. It's got the full prompt in it. So the input here is the road data. The output at the end of this is a copy for a case study. And so the next step here is I need to contain that case study somewhere. So what I'm going to do is I'm going to. The input on the next operation is the copy for the case study. And what it's going to do is that next operation is going to create a Google doc and then paste that copy into the Google doc and save it on my shared drive. So now I have a draft document on Google drive with that case study. And then the final step for the output in this case. is the output for the operation of creating the doc is a link to the document and other information about the document on Google Drive. So what I'm going to do then is I'm going to add that to ClickUp, which is my project management tool. I'm going to assign it to do to my content editor. I'm going to include a link to the case study within that task, give it a due date of In two days and then set the priority as high. And now I've just, as soon as that form was completed by the production team, two minutes later, my content editor has something to review and a task in ClickUp to make that project actually get done. So I didn't have to draft it and all my content editor has to do is review and approve and then publish. So that's awesome.

Speaker 3:

There's a question. There's a question from Denny, which is actually a really good question because I know the answer, but I'll let you answer it. Are the instructions or prompts Added into the assistant or into make,

Speaker 2:

both, it can be both. So the assistant, when you build those out, you can build it out with like default, instructions. So with th this works a little different depending on the GPT or the generative AI tool you're using. With the assistance. Yeah, you would build it out with the prompt in it, but you can also send a bunch of information over when you call that prompt, with some additional details and instructions is needed. If you're using Claude, for example, you really contain everything within the make. Call or the make prompt, and there's not really much you do on the Claude side, to pre build it, if you will. So the answer to the question is both, depending on the tools you're using. But yeah, this is it. This is the long and short of a very simple example of how you can take a. client success. Create a case study within two seconds using these automation tools. but I thought it would be good if we took a more kind of a deep dive example into the real, like really unlock the power of what these tools can actually do. So what I've done is I've gone through. And it will, when you see it on the make, cause we'll actually open up make and walk through each of these steps, but this is how, this is the number of different operations that are going on within that one make scenario that, we'll take from a thought leadership content perspective. So, anything else you want to cover before I jump into the kind of the main show? No, I think

Speaker 3:

we can jump into the actual live example. I think it's going to be the most clear for people. and we'll, we're going to try to make it. Simplified as possible. So it will be easy for you to follow up even though you can't watch it on the screen, but since you're not watching it on the screen, and if you've never used make before, the way it looks like is every one of those steps looks like a little circle and you start, in theory, you can make it move in any direction because you can move the stuff around, but the common way it shows up is it starts on the left and moves to the right and you can have those intersections where now you can do like ifs. And have a fork in the road and go in one direction versus the other direction, depending on what's happening. So think about a flow of little circle milestones. Each and every one of them is a step with a different tool. And then the progress moves to the left. And now Keith will describe to you what each and every one of those steps and what the process overall does.

Speaker 2:

Yeah. And and this one, the purpose of this Automation is to, if you say someone publishes an article and you want to write a article or a blog post about that article, but in the style of your subject matter experts, You need to one kind of, if we were taking it as a manual process, what you would do is you would take the article, you would have the subject matter expert read through that article, summarize it, pull out some quotes, and then they would go and they would draft a version of their own article in response to that or commenting on that information. it would match their tone because they're writing it and their style. And then, You would hand that off to your SEO editor. So who would go through and optimize the content to make sure that it has all the right wording in it. It's got all the right features built into it and all that. It's everything's optimized for search performance. and then you would take that article. Pass it along to an editor who would review and improve it, make sure it's all polished and good for the company website or wherever it's going to get published. And then ideally you also have social shares that can be created off of that to promote the article. so maybe we generate two or three LinkedIn shares to talk about and feature the article and drive people back to it. And then ultimately that stuff needs to be reviewed and improved by your editor. So we'll create a task for them. This workflow does all of that. In one and two to three minutes, so I'll walk you through and we'll get into as detailed as we need to on how each step is set up and how it works. So the first part of this. So in this case, this scenario, the trigger for this is called a webhook. And a webhook is essentially a web page or a page on and make site where as soon as information is sent, the runs and triggers the automation. So what I've done and what we have set up here is, let me get rid of this here real quick.

Speaker 3:

And again, I'll explain in more general as always what a webhook is. I told you before that a lot of these tools are already pre connected. Some of them are not connected either at all, or not connected in the way you want them to be connected. And so a webhook is a non developer, so it's a quasi technical option that allows you to add more capabilities to these connectors. So you can, you may connect something in a tool that already exists, but you want to trigger it in a different way that doesn't exist in the tool today, or you want to connect a different tool. Most tools today support these webhooks and they're very easy to build. So that's like a quick explanation of what web webhooks are.

Speaker 2:

Yes, thank you for that. Yeah, that's a good reminder. I have this website, this Google sheet set up. And the idea with this is anybody who finds an article that's worth writing about can add that article directly to this sheet. And so I can add in the date, the name of the article, a link to the article, define a, the topic, the article covers, in this case, I've just, who wrote it. And then I've got The final step here this final column is the trigger column. So in this case, you could set up the trigger so that as soon as a new row is added. It would trigger the automation. the trick there is that the person who's adding in the article may not act fast enough. And so as soon as they enter in the art, maybe only half the information is available and that it triggers the automation. And then all of a sudden it doesn't work. So there's some. Issues with setting that up to run like that. So in this case, though, I built a tool like with Google apps or Google, Google sheets, there's a Google app script tool that you can build. And again, you can use chat GPT to help you program and write these little tools. But the idea with this one is on the backend, as soon as I update this to go, the automation, it's actually going to send this rows worth of data. Off to this automation through this webhook.

Speaker 3:

So again, for those of you don't see the screen, the final column on the Google sheets is basically the trigger. So there's a drop down menu in that Google Sheets that says whatever, but one of the options is go when you switch it to go, that's what triggers the automation. That's basically what that webhook listens to. It's looking for a new, one of those to change to go, and then it will run the thing. If you don't know how to do the script, you could have said, Once there's the number one on this column, do the same thing. And then it doesn't look as fancy as Keith's spreadsheet, but it will do the same thing. Because once the number one, or once you type yes, or once you type go, or once it has any content in that final column, only then it will trigger the row to actually get the information. And that verifies that all the information is there before you send it over.

Speaker 2:

Yeah, so this may be a little bit of a kind of a advanced way of doing it, or you could just do very simply as soon as a new rose added that triggers the whole thing. But the way this works then is so the information comes into the trigger and the that rose worth of data is then passed along to this first operation. So the first operation, and this is one that's natively built into make and what it does is it will take a. I'm open this up here. It'll take a URL. So the information comes into this. And as part of that, what's created is a packet of information, one of which is the article URL. And so I can add that into that first field in this first operation. And what it will do is it will go off the internet and grab and scrape everything that appears on that webpage. In other words, it's going to grab all the HTML. It's going to grab all the content. It's going to grab all the links. Everything that's on that page will come back in this one object. And the, what we, it's not overly usable when you've got all that HTML code baked into it. So the next, so what that output here is the HTML code of the full webpage. So I'm going to pass all that packet of information into that Next. operation, which essentially strips out all the HTML from that text block and leaves only the content behind. And HTML goes in, out comes just the text block of the article itself. real quick, if you're doing, if you're setting something like this up, thing to note is These tools can't go through, and grab content from like a paywalled article. So it's gotta be a free, freely accessible article online. but if you can do that and you can get it in here, then this will strip it out. And I've got, now I've got the content of the article. Just a quick

Speaker 3:

question, because there's a question. How does it strip it out? Is there like a tool built into make that just does exactly that?

Speaker 2:

Yeah, it's a native app operation that's built into make. And so there's code on the back end that actually just goes through any sort of HTML elements that are exist, they'll just completely strip them out. So now I've got the copy of the article. And what I'm going to do is then I'm going to send it into my first of several OpenAI assistance here. And so what I'm going to do is it's going to go in to this first one, which is called the article analyzer. And all I'm doing in this little widget here is I'm assigning, calling out and defining what assistant I want to use within my OpenAI account, defining myself as the user. And then in the message, all I'm doing is adding in that block of text from the article. Now, if I go into OpenAI, and open up that assistant. This is what the assistant looks like on the, in OpenAI side. And so I have the full prompt here. you're a content marketing specialist. Read the provided article and provide a summary in two to three sec sentences. Grab two to three notable or quotable statements from the article. make sure they're pulled verbatim. And then, also grab the author name. And in this situation, what I want to do is I want to send it back in a structured format. So I'm using what's called a JSON structure where I give the data a label and then save that information. So the first label in this JSON structure is summary, and then it'll add in the summary of the article next to it. And then the next one is quotable statements, and then it'll add in the quotable statements next to that. And so what I'm going to do is then I'm going to take this assistant is going to send that information back that it's extracted out of the article, and it's going to pull it right back into the make quotable statement. Scenario in that format. So that's the output. So those of you, I

Speaker 3:

just wanna pause you for a second. For those who are not watching this and just listening to this, first of all, there's a YouTube version of this, so if you wanna watch what we're doing on the screen and you're listening to a podcast and you're not driving right now,'cause if you don't do this. I don't want that on my liability. But if you can't watch the video, there's a link in the show notes that will take you to see the video on YouTube if you wanna do that. But to recap, we've done four steps. So far step number one started the process based on somebody filling up a Google sheets. Step number two, grab the HTML from the article. Step number three, turn the HTML into just the text and step number four summarizes the article and puts it in a format called JSON, which you don't need to know what it is, but it's a standard structured format that multiple types of software know how to use. So think about it. We like to put stuff like that in the table. That's like the digital version of a table. Where things are very clear, what is what, as far as the data package, and then you can send it to multiple different tools so they know what to do with it.

Speaker 2:

okay, exactly. And This and this, after this step again, I'm sorry for the podcast list. This is a very visual type of demonstration. Hopefully you do get a chance to watch the YouTube version of this, but, so once we've got the JSON summary of the article, and now that we've got summary, the growth quotes, we've got the author. There's one of two things that happened. we'll get into the second thing. So the secondary version of this is. Every so often with these GPT or these generative AI tools, they will run into errors and they will return an error. Something won't fire for whatever reason. I'll get into how we handle that at the end, but assuming everything comes back from this tool properly, it's going to go into the next operation. And so the next operation is designed specifically to create a usable variable, off of the JSON that the GPT created. In other words, I'm going to have a independent variable called summary with the description or the summary of the article. I'm going to have a variable called quotable, quotable lines with those built into it. And I'm going to have a variable for author name. And now because I've got each of those individual pieces of information available to me, I can use them wherever needed throughout the rest of this workflow. So now once I've got those, that information saved, the next step is to, and this is probably one of the cooler things that you can do is definitely, I recommend it. It's going to give your automations a lot of power. So in this case, what we've got here is. I've got the summary of an article. I've got quotations. I've got the topic of the article. but I and my company, I have a subject matter expert for content marketing and I have a different subject matter expert for HubSpot. And I have a different subject matter expert for generative AI. So I have all these different topics that we may write about and a subject matter expert for each of those. And each of those subject matter experts has their own unique style and tone. they have their own. Examples of work and social shares and all that stuff. So what I've done is I've created a Google sheet and within that Google sheet is essentially it's a directory of resources specifically related to that topic and to that subject matter expert. In this case, I'm showing now a Google sheet that in column A is a list of topics. So content marketing, paid search, generative AI, and HubSpot. Next to that is a column called semantic keywords. And so we'll get into the SEO side of this here in a little bit, but it's essentially a list of IDs for documents on Google Drive. So this is a Google Doc ID for content marketing semantic keywords. So I have one doc. On my drive with a list of keywords and that's the ID to that specific document. The next column over column C is the subject matter expert tone and style. So I have descriptions of their tone and a description of the style they like to write in and that's saved in a specific doc. I have a, Example blog posts of past posts they've written in a doc and that's in column D. So the ID for that document on my drive is saved there. And then the final doc is, or the final column E is there's example, social shares. Again, I've copied and pasted them all into a Google doc, and I've put the ID of that doc in this row. So within the make automation, what happens is this We'll go in and open up that file and what it's going to do, it's going to filter it so that it only returns the row that matches the topic of the article. And that was something that the user inputted into the spreadsheet when they essentially put the article in to be created. So in column D of that first spreadsheet that we set everything off with, the trigger spreadsheet, I've defined this first article as content marketing. Thanks for watching. Transcribed And so now I'm going to use that phrase to look for the row in my directory that matches up with content marketing. And as part of that, what I'm going to pull in is the ID for the keywords, the tone and style, the blog post and social shares, all related to that content marketing.

Speaker 3:

So I want to pause it just for one second, a, to help people understand what we're doing and B. To say how that connects to what I said in the beginning. And I'm actually going to start with that. Like I said, in the beginning, that part of the problem with just creating content is that it does not take into account your tone of voice. It does not take into account keyword research. It does not take into account your expertise in that topic and stuff that you've written before. And what we're doing here is basically solving for literally all these things in this one step. And the way this was done is in advance. Keith has prepared these reference files that can be used, and this could be different reference files for different topics, right? So for each of those topics that he mentioned, there are different reference files, different keywords, different tone of voice, different referenced past experience on stuff that you want your company to talk about. And. What this amazing step does is it really prevents you from running four different automations, each one for a different topic, which is what I would have done before I learned this trick from Keith, right? So before I saw Keith do this on stage, I literally did this once and then created the automation again to be triggered with the second topic and then created the automation again, created with the third topic. And if you have 20 topics, now you have 20 of these automations, which makes absolutely no sense. So what this step does is it literally says, Oh, If this is your topic, use these three files as references for your tone of voice, for your past expertise, the stuff that you've already written and examples, and for, your keywords. And then you continue with those in mind and you can show us now how this is done.

Speaker 2:

Yeah, and I'll show you here too. So these are the docs that it's pulling that information from so the ID for this doc, you can usually see it in the URL of the Google Doc. You can do the same thing with Word docs and share dry or SharePoint. but like this would be my list of semantically related keywords to content marketing. So everything I read about content marketing, I want to feature and include these specific terms, as the author, here's my tone. Here's my style. Again, it's just a block of text written out, but it's just accurately describes how I write and the style in which I write. And then I've got a list of, okay, here's some example blog posts I've written on this topic in the past. And again, we've got my style, we've got it, but also it's got. Bits of my own expertise baked into it because I wrote these articles, and the final step is example blog posts. So example, LinkedIn shares that I put on about these topics again, copied and pasted verbatim. but now the automation has access. And to all of this information that I can then apply to the next thing that we're going to do, which is going to be to write the article. after it goes through that directory, now I've got essentially a list of IDs that I can utilize for the next few steps. So the first, the next step here is in the next operation is going to go in. To Google Drive, and it's going to grab my tone and style guide and grab the content off of that document. So now I've got that those blocks of text available to me within this workflow. And then the next step is it's going to go in and grab the past article content again. Pulled directly from Google Drive, so I've got the text verbatim sitting there. And then, the next step here is, I've got everything I need now. I've got the summary, I've got quotable links, I've got my tone and style, I've got past, articles I've written. I've got everything I need to go and write this article, to have chat GP, or in this case, we're going to have Claude. Because I like using Claude to actually generate the content. I'm going to have Claude write the article. And so as part of that, I'm going to pass in to this operation. So Anthropic Claude, I'm going to set it up so that messengers messages is from a user. it's a text prompt and I've got my prompt written in here. So you are a content marketing specialist and ghostwriter. You write a. Please write a 300 to 500 word blog post based on a recent article about and then I'm going to put in the topic of that article and then it says use the following information to create the blog post. Here's a summary and then I put my summary variable in there. Here's my quotable takeaways and I'll put a list of those in there and then I also then provide it. Here's the subject matters, tone and style. And I include that variable here's past blog posts. They've written, put that in there. And then I essentially lay out the task, review the summary and keywords, analyze the SMS SMEs past writings and generate a point of view on the tarp topic using supporting evidence and insights, and then draft the copy. I also make sure that it calls out and said, please include quotes from the author throughout to reference their. They're a piece of content And then ultimately have it spit out something of, in this, generate the blog post and then provide it in a format that I can use. So Claude will go through, do all of that work, and on the other end of it, I have the draft of a blog post ready to go. And now I could end it here. I could simply just save this doc on my drive and be done with it. But the other thing that I really liked doing, and I forget who mentioned this to me, but I really thought this was brilliant is, you can have one of these generative AI tools, right? The article. but what's cool and handy is to have a second, a different generative AI tool, actually review it as if it's an editor. so you get essentially two different training set, training data sets to review, to draft, and then to review the article. The other thing that I've done with the second one is, I've set it up. So this editor is also an SEO expert. So at this point, after the article is written, I have. The automation go in and grab the list of semantically related keywords for this topic. and so now I have that keyword data available to me within here. And then I'm going to pass all of that information over to a second. open AI assistant. and that second assistant is oops, wrong button. Okay. So I call this one, my SEO content editor. And in this case, I've already preloaded it with a prompt of you're an SEO expert, content optimization. And, what I've also done. is because you can do that with these assistants is I've preloaded some resources into this assistant. So I've got a Google SEO starter guide for optimizing for Google, avoid search engine first, whatever it is, I forget the name of the article. In other words, I have just given it an education in, SEO best practices. And I've baked that right into the assistant. So when this thing fires and this thing runs, what it's going to do, it's going to run through this prompt, but it's also going to draw from all of those resources and essentially give it a solid expert level background on how to optimize content to perform well on Google. So when I call this assistant here through the automation, I'm going to provide it the keywords and I'm going to provide it a draft of the copy article copy. That was generated by the Claude, operation. And what it's going to come back with is a version, another version of that article, but optimized with new keyword, with the semantically related keywords. It's also going to come back with new features to add to the article. say, for example, a frequently asked questions section, or, here's the recommended page title and meta description for each of those are for that article. and so by the end of it, I'm going to have a fully optimized piece of content. With additional features to bake into it. And now I can take that information and I can save that full drafted out optimized blog posts on my Google drive. So that when it's, and now that's the thing that can be reviewed by my content editor.

Speaker 3:

So first of all, this is absolutely brilliant. I want a quick summary of this step and we're short of time. So maybe we'll stop here. Maybe we just want to show the last few steps quickly, but the, what this really does is Created another step that is an SEO expert. And the way you create the SEO expert, you give it a lot of SEO best practices. So you give it whatever articles or books or whatever they are that you want to reference for this thing and say, okay, here's a blog post that I've written here. The keywords I'm trying to optimize for use all that knowledge of best practices. In order to evaluate and update my initial draft in order to make it a better version. And you can do this for literally anything you can imagine, right? This could have been any other step, but this just allows you to, when you hand it off to a human evaluator already after it's been optimized once or twice through these different filters. The other thing that I want to touch here is in theory, this could have all been done in one step. But these tools, a, this allows you to use different tools for different things. So in this particular example, you're writing with Claude, which is probably the best writing tool out there right now. And then you're evaluating which are GPT. So that enables you to do that. But also, even if you're using these tools, the same tool, it's always better to break it into different parts. individual steps because then you're going to get a better outcome for each of the steps versus if you try to combine it all together. And the last question was a question from somebody in the audience who's watching us do this. So those of you who's not watching us, every time that Keith mentions parameters in the prompts that he's sending, they show up as these little colorful Boxes, because what they are, they're literally parameters from the previous steps that we've done in make. So whenever you want to enter a parameter, you do a forward slash, you get a drop down menu and it shows you. All the different things that happened in the previous steps, and you can pick the parameter you want and basically place it as part of what you're sending over to the chat. So every parameter that happened in any previous step is now available to you to build the next step and send the information over.

Speaker 2:

Yeah. And the, just to hit the last couple of points on this, then is after that draft is done, what I'm going to do is pull the past social shares for the author and send that into Claude. And it's actually going to generate for me two to three LinkedIn shares to promote the article. I'm going to save that information to a Google doc. And then at the final step of this, so essentially the output. What I'm going to do is assign my editor to go through, review the content, review the social shares, get it all set up and polished up, and then upload it into wherever it needs to go, whether it's LinkedIn or the content management system. That's the one thing I will absolutely, I want to make sure that I leave you with. Never, ever let these tools just publish automatically. You have to have a human in the loop. You have to have someone have eyes on it before it goes published, because there are things that will come out of this. You'd be like, where did you get that from? but that's that kind of stuff happens. So you need to have that extra set of eyes on it.

Speaker 3:

Keith, this was absolutely brilliant. I think this process is literally mind blowing. And again, this is very well structured and it ticks. literally all the boxes that I talked about in the beginning that are problematic with just, Oh, I'm going to have chat GPT write a blog post for me because it misses all these really amazing capabilities. And I want to touch on two big other points that are critical. One of them you already touched. You can put as many human based steps in the middle and the way to move forward in a human step. So let's say you wanted another evaluation step in the middle is. You're in your case, posting the tasks to click up, but this is going to be in Monday, Asana, JIRA, like whatever task management tool you're using. And you can say that once you move it to the next status of tasks, so this is for review, it goes from for review to reviewed, that's going to continue the automation, from there or start a new automation, however you want to build this. So you can do that as well. And that's how you can get humans in the loop in that process. And the other thing is. This whole process takes minutes. So this whole thing that would have taken a company of people, either because of handshake time, okay. I got an email and I didn't check it. And I checked it the next day. All the time he takes would have taken days to do like this whole process that Keith had just showed us takes minutes to run and then. You just save people in your company, few days of work, and it still goes to a human reviewer that can then edit and make whatever changes, but he's already starting at 80 percent of the work is done in some cases, a hundred percent of the work, but in let's go for the worst case scenario, 80 percent of the work is done. You add your two cents, you make some minor changes and you're ready to publish and you saved a few days. Of work, both in means of effort as well, definitely means of timeline. As I mentioned, absolutely amazing. Keith, if people want to follow you, if they want to connect with you, if you want to use your services, If they want to know more about what you're doing, what are the best ways to do that?

Speaker 2:

Yeah. I'm on LinkedIn. I'm also the, our website is just l2 digital. com. so we're ramping up and putting up a bunch of resources, similar, like kind of talk through and show how to do all of these types of automations. Got a bunch of specialized use cases for those. So those would be the two best spots, LinkedIn or through the website, would definitely be the easiest and most efficient ways.

Speaker 3:

Awesome. Everybody, by the way, both on LinkedIn and on the chat on zoom are going like, Oh my God, I'm blown away. This is the breast step by step breakdown I've ever seen. there's a bunch of those on both chats. So as I said, that's how I felt after seeing your presentation on stage. And I'm very happy that I got a chance to host you here and share this with my audience. Thank you. Thank you. Thank you.

Speaker 2:

No, I appreciate it. And just for the fun of it, when you started talking about how long this thing takes to do, I put, go, the process is already done. I've got the task.

Speaker 3:

That's awesome. Great. thanks everybody who joined us, live. As I mentioned, we do this every Thursday at noon Eastern. We also have the. AI Friday hangouts, which we do every Friday at one. And this is just like an open mic kind of thing. Anybody who wants can join. And we have conversations about what happened this week in AI and problems people are having, and we try to help each other solve them. So more of a community get together and it's a lot of fun. So if you want to do those again, there's a link in the show notes where you can come and join us to these events. And again, thank everybody for joining us live, whether on LinkedIn or on zoom, we had a few dozens of people join us and I appreciate all of you. And I know you have other stuff that you can do in the middle of your day on Thursday. So thank you for being with us. And thank you again, Keith, for doing this and for sharing your brilliance with all of us.

Speaker 2:

Thank you. And thank you for having me.

People on this episode

Head Shot

Isar Meitis

Host