Switching From Zapier to Make, and A Potpourri of Automation
I wax poetic on a number of automation-based topics, like switching from Zapier to Make, how ChatGPT can help creators (and exposes a gaping hole in the education system), and rebranding the YouTube channel to focus on automation tools. In PRO, I’m thinking of switching off of Castos, and sales numbers from my latest launch.
- Join How I Built It PRO
- Make vs. Zapier: Why I Moved
- ChatGPT is Exposing Our Broken Education System
- The Automated Solopreneur | YouTube
Joe Casabona: Hey everybody. Today is going to be a solo episode. And it’s going to be a bit of a potpourri kind of episode. There is a thread of automation going through the whole episode. But there are a few things I’ve wanted to address and so I’m going to address them here.
We’ll talk about my switch from Zapier to Make, we’ll talk about a new brand I created, and I think probably the most interesting thing, I’ll be giving my thoughts on ChatGPT and AI in general and how I’ve been using it.
So I think this is gonna be a fun episode. It’ll be shorter than normal, but not as short as the How I Built Bits. And that is another thing I want to mention here. How I Built Bits is back. You can go to howibuilt.it/bits. They do drop in this feed as well every Friday. So it’s usually just a tool or some sort of tip, maybe a book I came across that I have found really helpful that I think you will find helpful as a creator as well. So again, that’s over at howibuilt.it/bits.
Today’s episode is brought to you by the Solo Creator Club, Groundhogg, and LearnDash. So definitely check them out. All the show notes, I suspect I’ll be linking to a lot of stuff, all the show notes will be over at howibuilt.it/306. But for now, let’s get into the intro and then the episode.
Intro: Hey everybody, and welcome to How I Built It, the podcast where you get free coaching calls from successful creators. Each week you get actionable advice on how you can build a better content business to increase revenue and establish yourself as an authority in your field. I’m your host Joe Casabona. Now let’s get to it.
Joe Casabona: Alright. So first up on the agenda, I’ll try to add chapter markers as I think of them. So first up on the agenda is Make vs Zapier. So I decided you might have heard this, I wasn’t really super shy about it or anything like that. But I switched from Zapier to Make.
This was an experiment I tried back in January and by mid-January, I was pretty much sold. I fully moved from Zapier. The main reason is the considerable cost difference. And I’ll just say here that you shouldn’t do things just because they’re cheaper, but also as a business owner who does their due diligence, you should consider vastly cheaper options. You don’t just want to waste money, right?
I think something I’ve said for a long time and something other business owners will say is, Well, I’m willing to spend money to make money or Well, I’m willing to spend money if I never have to think about it. And that’s absolutely true. I have my lawn mowed by someone every week and I happily pay like $35 a week for them to do about 15 minutes of work so I never have to think about it. That’s money well spent.
But if I come across a tool like Make that is, I don’t know, 90… I think it was 90% cheaper to go to Make versus Zapier and Make does everything I needed to do, that would be stupid of me not to do. Because even the few hours I spent learning Make and then moving my automations from Zapier zaps to Make scenarios, it’s worth it. Because again, 90% cheaper, right? It went from like 75 bucks a month for me to 10 bucks a month for me, which means after six months, that time that I spent is worth it. It’s a long term investment.
But that’s not the only reason. That was just like a soapbox because somebody’s got on my case about it. Like, “Oh, I’m willing to spend the money if I don’t have to think about it.” I’m like, Yeah, me too. That’s why I’m investing in automation. I mean, there’s a reason that Bill Gates cuts his own hair—because he feels that it’s financially smarter to do that.
The last thing I’ll say here is that truly wealthy people are not the people who frivolously spend and waste money. And based on what I’ve learned about Zapier versus Make, to stay on Zapier would have been a waste of money. So there you go.
But there are a few other things I like about Make versus Zapier. First of all the route building and general design of scenarios is better. I think the interface is much more intuitive. It’s easier to move things around.
Like with Zapier, unless they’ve changed this in the two months since I’ve left, with Zapier, once you have that flow in place, if you want to move stuff, you can’t just drag and drop it, you have to delete the action, and then place it later. But with Make, you can move the actions around, you can move the triggers around, you can disconnect them, you can create routes. I think it’s a lot easier to build scenarios and visualize how they will work and understand them a lot better with Make. I think it’s much easier.
That said, you do need a little bit more know-how than Zapier. Zapier has tighter integrations with Dropbox and Google. For example, if you want to use your personal Gmail account, you need to spin up an API key for certain actions instead of just authenticating.
This is actually a lot more secure because you’re not giving complete access to an app. You’re actually explicitly choosing the services that you want an app to have access to. So that’s nice. The security aspect is nice. But like if you’re just looking to go in and connect your Gmail account, you do need a little bit more know-how.
Along with the know-how you do, you need to be more mindful of how your scenarios are run. Make charges per what they call operation. So you can’t just let your automations run wild. With Zapier, you could set something for 15 minutes. And because they’re charging you per zap, you can basically let a zap run every 15 minutes if you want.
With Make, I tried applying that same sort of thing, like run my automations every 15 minutes, and I ended up hitting my 10,000 operation limit within two weeks. So that’s really short. But luckily, I was able to dial them back a reasonable amount. And now I think last month I hit a little more than 50% by the end of the month. And I’m on that same track. I think I’ve hit like 30% halfway through this month. So you do need to think about that.
The way to manage the operations is to not have them run as often. So the default is 15 minutes. I have some run every two hours, I have some run every two days. If I have an automation for this podcast, based on the publication of an episode, I don’t need that to run every 15 minutes, every two hours or even every day. I know a new episode comes out around 2 a.m. Eastern Time on Mondays and 2 a.m. Eastern Time on Fridays. So I can explicitly tell Make to only run at let’s say 3 a.m. Eastern time on those two days.
So this is fine. They run perfectly fine often enough so they don’t bottleneck my workflows. The hardest part for me was coming to terms with knowing they aren’t constantly running. But again, Make as much more affordable. I would have to pay for around 90,000 operations to hit the same monthly costs as Zapier.
And if I doubled my monthly operations, which is all I would need to do having the scenarios I run as often as I did, I would still be saving 55 bucks a month. So the cost savings is still considerable. But if you’re smart about your operations and how often your automations run, you don’t need to worry necessarily.
Then finally, thanks to reevaluating my automations I was able to create more efficient actions and move some actions to the native app. For example, Vimeo has direct integration with Dropbox. They didn’t have that when I looked into it, how many years ago that was. I actually don’t need Zapier to upload a video from Dropbox to Vimeo anymore. So that was nice.
I was able to cut away some automations, take things and things native, move things just to Airtable. I’ll probably do a full episode on this as well. But in Airtable… or I’m sorry, I was doing some stuff with Google Sheets and then having Zapier send emails based on changes in Google Sheets.
I moved those Google Sheets to Airtable and now Airtable sends the emails, which is a much better function because there’s not that middleman that could break down. It’s all happening in Airtable now. So I made my automations and my communications and my tracking things much more efficient in this process as well.
So, on top of savings, I actually made my business operations better. So if you are doing automations if you have less than five zaps, it still makes more sense to be on Zapier. But if you have more than five zaps or more than five automations, I would strongly consider Make.
The last thing I’ll say around this topic is that Make is formerly Integroma. Just a great name, like a great get for the folks who own Make like to have make.com, pretty cool. But googling tutorials is a little bit of a pain in the neck. So I will usually just google how to blah blah, blah Integroma. And that usually shows up. But I don’t know how long it’s gonna take.
I’m sure like if you include make.com… their documentation is pretty good and I think they’re improving it. But that’s just one thing to keep in mind. You do need a little bit more know-how, maybe. I don’t know. I feel like I’m a little bit too close to it. But there are a few things that maybe if you’re coming in fresh and you don’t know either, Make is going to be fine. But I think Make is a really nice tool to look into.
So that is all I have to say about Make versus Zapier. I do have a blog post with some screenshots and words to accompany my rambling. So I’ll include that in the show notes. To get all the show notes it will be over at howibuilt.it/306 or in your podcast player.
Why don’t we take a break now to hear from our sponsors. And then I’ll get into the rest of the stuff. By the way, I didn’t say at the top of the show, which maybe I’ll ADR that in the beginning. But what I didn’t say in real-time in the top of the show is in How I Built It Pro I’m going to talk about how raising my price of the Podcast Liftoff Playbook went as far as the sales went, what I’m considering for branding and positioning, and a few other plans for the future regarding that, and possibly this podcast.
So if you want to get ad-free extended episodes of this show, as well as support the creator you’re listening to right now, you can go to howibuilt.it/pro and sign up for just five bucks a month or 50 bucks a year. Again, you’ll get ad-free extended episodes, you’ll also get some members-only videos. And as the membership increases, there will also be like a newsletter and things like that. But that’s really kind of based on what the members want. So if you want your voice to be heard, again, that’s howibuilt.it/pro. Then I’ll be talking about how my last sale went. So a little behind-the-scenes stuff there.
Okay, but for now, let’s hear from our sponsors.
Sponsor: This episode is brought to you by LearnDash. Look, I’ve been making courses for a long time. I’ve taught at the college level and I’ve created curriculums for several different organizations, including Udemy, Sessions College, and LinkedIn Learning. When I create my own courses, there’s no better option than LearnDash.
LearnDash combines cutting-edge eLearning tools with WordPress. They’re trusted to power learning programs for major universities, small to mid-sized companies, startups and creators worldwide. What makes LearnDash so great is it was created by and is run by people who deeply understand online learning, and adds features that are truly helpful for independent course creators. I love the user experience.
And now you can import Vimeo and YouTube playlists and have a course created automatically in seconds. I trust LearnDash to run my courses and membership. And you should too. Learn more at howibuilt.it/learndash.
Sponsor: This episode is brought to you by Groundhogg. Groundhogg is an open source CRM and marketing automation suite for serious agencies, small businesses, content creators, eCommerce experts, and WordPress professionals. Groundhogg allows you to create funnels, automate email, and SMS communications and manage your contacts from the comfort of your WordPress dashboard.
Unlike other SaaS CRM platforms, Groundhogg does not charge you a success tax. Groundhogg charges a flat rate fee regardless of the size of your list. Groundhogg will never charge you more as your list grows. It also integrates with all of the top WordPress, ecommerce LMS, and membership plugins to create a unified customer experience.
Start now with a 14-day demo for $1. Go to howibuilt.it/groundhogg. That’s howibuilt.it/groundhogg or use the code HOWIBUILTIT for 20% off your first year of any plan. Thanks so much to Groundhogg for sponsoring this episode of How I Built It.
Sponsor: If you listen to this show, you know it’s an amazing time to be a creator. It’s never been easier to get paid for your expertise. But being a high performing creator is a different ballgame. High performing creators generate consistent monthly recurring profits.
They trust the process and don’t overlook the essential fundamentals of business. They are dedicated to becoming masters of their craft and creating more customer value. And high performing creators are business owners as much as they are artists.
If you want to become a high performing creator that earns a living from selling your expertise, then I recommend you join the Solo CEO Club today. Surround yourself with other high performing creators. Expand your influence, increase your income, and cultivate a deep impact on your customers through meaningful interactions.
Become a member of the Solo CEO Club today by visiting jointhescc.com. Again, that’s jointhescc.com. And you can get 33% off your first month with the coupon code CASABONA. The Solo CEO Club, where creators become high performing experts.
Joe Casabona: Okay, so next up on the agenda is talking about AI, ChatGPT, all these things that are involved. So these are my general thoughts on ChatGPT and generative AI in general. Take them with a grain of salt. I’ve been using them a little bit for mostly idea generation.
So one example I’ll give you is I was asked to come up with a podcast concept for a topic I’m completely unfamiliar with. And this is not launched yet and it’s for a client so I don’t want to get into too many details. Let’s just say it’s underwater basket weaving.
So I was asked to come up with a podcast concept for underwater basket weaving. I don’t really know anything about underwater basket… I guess it could just be basket weaving. I don’t know anything about that either or woodworking, like any of these things that you have to do with your hands. Let’s say it’s woodworking.
So I first asked ChatGPT like, Tell me a little bit about woodworking, what are woodworkers called besides woodworkers? Is there another word? And then I asked it to come up… You know, I am creating a podcast where I interview competitive woodworkers on their craft. Can you give me a list of 10 names for that podcast? And then I said, Okay, come up with two descriptions for that podcast. And then I said, Okay, come up with 25 episode ideas around competitive woodworking.
And it did a really good job. It did a pretty admirable job. I, you know, finesse it, I did a little bit more research to make sure it wasn’t just completely out there. But I was pretty happy with the results. So I’ve been using ChatGPT for stuff like that: doing some research and fact-checking and looking up kind of fun facts like that.
I’ll talk about this more in the Pro show. But I’m trying to come up with a new name for the Podcast Liftoff Playbook. And so I gave it a little synopsis on the playbook and what it does and what I’m thinking and it came up with seven names. I’m actually going to go with one of those names. I might tweak it a little bit but I’m gonna go with one of those names. So I was really impressed by that sort of stuff.
As far as, you know, what creators can use it for, I think idea generation is key. So, you know, even maybe first drafts or what I’ve seen examples of, which is pretty cool, is like you give it some text, and then you say, write it, write it with a different tone, or write it with a different voice, write it from the perspective of.
And I think those things are really cool because you want your message to resonate with a particular group of people. And if you don’t have that same exact perspective, or you don’t have the same life experiences, ChatGPT, using its vast word association database, can help you come up with different perspectives or see what you’re trying to say in a different light. And I think that’s really cool.
The other thing that it looks pretty promising for, though I’ve had mixed results, in my own examples for what I’ve tried. So summarizing text is another thing that ChatGPT or these other generative conversational AI tools can do.
So you feed it maybe like you’re driving and you’re just kind of like freeform brain dumping into a note, right? I’ve done this from time to time. We all like speak a bunch of stuff and then I try to finesse it later. You can dump that into ChatGPT or another generative AI tool and say, “Summarize this. What are the big takeaways?” or “Turn this into a blog post.”
And then it’ll look at what you’ve written and structure it. And maybe probably won’t be the way that you write it but you’ll at least get the general ideas and it’ll be a good starting point for something that you word vomited. Because word vomit is not always the best blog. Most people don’t speak the same way they write. So taking what you spoke and turning that into a blog post verbatim is not going to work. But with chat GPT, it could work pretty well.
I attempted during a recent live stream to use it to summarize transcripts of episodes. I thought that this would be just like such a great use case because I am usually trying to summarize my episodes from memory. Or if it’s just me, I’ll just take the cold open and copy that, usually from the descriptor transcript. But if ChatGPT or another generative AI tool can summarize the transcript that would be great.
The problems I’ve run into are that my transcripts for these episodes are too long. So I’d have to break it up into chunks, and then it’s summarizing chunks, but it may not catch the whole thread. And maybe it wouldn’t do that anyway.
So maybe there are tools out there that I haven’t looked at yet. One of the things I want to do on my YouTube channel over the next few weeks is explore how automation… I’m sorry, not automation, how AI tools can help podcasters. So that’s something that’s in the works.
The other thing that I’ve been doing, because I’ve been doing a lot of user research, which I’ll talk about in the Pro show, but I have been recording the Zoom calls, and then throwing them into open AI, Whisper AI tool, so that it comes up with like a pretty high fidelity transcript, and then I can search through that.
And these are like 15 Minute Calls. So maybe I can put those into ChatGPT and see if they’ll summarize them. But for now I’m taking my own notes. And so I’ll just have that in my craft document as reference in case like I remember they said something about building authority. Like what were they saying there? I can at least search the transcripts. So those are the main things I am using ChatGPT for.
The last thing I’ll say on this is kind of like social commentary maybe. I was at a talk a couple of weeks ago about generative AI and someone asked about what it meant for students and homework assignments. I’m paraphrasing here but the speaker said something that I can’t stop thinking about, which is if ChatGPT can regurgitate information as well as a student and the teacher has no idea, what is the real problem?
I wrote a blog post on this and shout out to my friend, Nick Benson. He is an educator. He has his PhD, he teaches at the college level. And he has told me some just horrific things about the state of students coming out of high school these days.
Like he said, if there are paragraphs in a paper that’s turned in by a student, he knows that it was probably written by AI because students aren’t using paragraphs. This is terrifying. This is part of the problem with the educational system. And I talked about this in my blog post.
I’ll say like, who cares if ChatGPT can write a paper about the Battle of Gettysburg at a fifth-grade level. That’s not a skill. Writing is a skill and you need to teach that skill. ChatGPT cannot teach us how to be good writers. It could write stuff for us but that doesn’t make us a good writer. Because at best, these tools will be assistive for us. Assistive technology, not replace it.
Like there are people who say like, oh, yeah, I wrote my book with AI. You didn’t write your book then. Other people from all over the internet wrote your book. ChatGPT and these other generative AI tools don’t have your life experience and they don’t have your perspective. They have what other people and maybe what you have already written on a topic.
Like ChatGPT could have spit out Atomic Habits or Buy Back Your Time. They could write a book about productivity. They can write a bunch of words about productivity. Anyway.
So here’s what I said. If my kid leverages tools like ChatGPT to do their homework and save themselves time, they’ve gained a much more useful skill than memorizing “the Battle of Gettysburg was a major turning point in the American Civil War lasting from July 1st to July 3rd 1863, with the Union Army defeating the Confederate army led by General Robert E. Lee.” And yes, that sentence was generated by AI. Perfectly fine, right?
Again, memorizing stuff like that… I have a general interest in history now. I didn’t care about this in fifth grade or 12th grade. In 12th grade, I should have been learning accounting and other life skills. I should have been learning how to publicly speak, I should have been learning more than just memorizing. You know, shout out to Mr. Turner, I guess, because I like history. But you know, Hammurabi’s code, I haven’t really used that since the test. I think about keep it simple. Stupid, right? But that’s the thing, right?
If you’re gonna teach me something that you’re gonna have me regurgitate, then you need to assign critical thinking to it as well. And this is my point of the piece I wrote. Generative AI is not going away. It’s going to help us get information faster. And then students will have to apply some critical thinking to it. So that took an unexpected turn but those are my general thoughts on generative AI.
Now the last thing that I’m going to talk about here is the direction of my YouTube channel. And that’s mostly because I finally have a focus for it. If you’ve been following me for a while, you’ll know that it’s just kind of like a hodgepodge of videos that I thought were interesting. And that’s not really a good way to grow a YouTube channel.
But I posted something on LinkedIn recently, and my friend Jeff Large told me that… it was about automation. And he basically said that he thinks I am better positioned to help people with automation than I am with podcasting.
Now, I’m not all the way there. I think there’s a way that I can have it both ways. But the Joe Casabona YouTube channel lacked focus until that moment, so I decided to spin up a new brand called The Automated Solopreneur. You can find more information at Solo Autopr… Ah, Solo Automator. There it is. Great domain. I can’t even remember it. Soloautomator.com. But again, my YouTube channel is going to focus on automation tools.
So lately I’ve just been doing like one video a week where I walk through one of my automations while I get a feel for like what does well and what doesn’t. It’s kind of a new day for the YouTube channel. So what I plan on doing there, I’ve already updated the branding, all of my live streams are going to have an automation slant now as opposed to a WordPress slant.
What I need to do is update the videos that you see on the channel page, right, you can curate that experience. And right now I only have one playlist called Automation, whereas I’ll probably have three moving forward called like automation tools, thinking like an Automator is probably one of them. That’s a really good one. Thinking like an Automator. And then demos, like automation demos, where I walk through some of my own automations.
And then there’ll be the live streams where I build automations in real time or I take suggestions from people watching. So I’m pretty excited about that. That was just a quick aside, but I think that this is going to be a really good direction for the YouTube channel because I have my Podcast Liftoff YouTube channel that I’m going to publish.
I plan on doing like six videos on that this year, but I want them to be high quality videos. And up until now, I’ve been sick, like I got the flu and then two weeks later I got strep throat. And I’ve had to ship two LinkedIn learning courses in that time. And now that’s going to slow down a lot and I’m going to have more time to focus on this kind of fun content.
So I just wanted to give a quick update on that. I’m pretty excited about the direction of the YouTube channel. I love automation. So if you have any questions about automation, you know, feel free to send them in howibuilt.it/feedback. I’m probably not going to spin up a new podcast, I’ll probably use this as the automation arm or the podcasting arm of my automation brand. And like that fits into the name How I Built It and maybe How I Built Automations. So that I’ll probably discuss more in the Pro show.
But for now that’s it for this episode of How I Built It. I hope you enjoyed the potpourri style. Again, if you have a podcast player that supports chapters, I have built some chapters in so that you can skip around if you’d like. I have even chaptered the sponsors since they’re all in one break now. I guess if you’re at this point, though, you either already know that or you just listen to the whole episode and you’re like, Well, I missed out.
Anyway, thanks for listening to this episode of How I Built It. Thanks to our sponsors, the Solo Creator, Groundhogg, and LearnDash. Definitely check them out. For all the show notes, as well as to join my mailing list where you’ll get newsletters with these roundups and things like that, you can head over to howibuilt.it/306.
If you’re gonna stick around for the Pro show, I’m going to talk about how my new sale went as well as the direction for this show and some infrastructural changes maybe. But that is for the Pro shows. Thanks so much for listening. And until next time, get out there and build something.