Hello and welcome to SEO is not that hard. I'm your host, ed Dawson, the founder of keywordspeopleusecom, the place to find and organise the questions people ask online. I'm an SEO developer, affiliate marketer and entrepreneur. I've been building and monetising websites for over 20 years and I've bought and sold a few along the way. I'm here to share with you the SEO knowledge, hints and tips I've built up over the years. With you, the SEO knowledge, hints and tips I've built up over the years.

Hello and welcome. Back to SEO is not that hard. It's me, ed Dawson, here hosting as usual, and today I'm going to be talking about workflow automation tools and AI. So this isn't just about workflow automation tools. So, if you're not aware what a workflow automation tool is, it's things like you may have heard of zap or makecom, which are tools that let you sort of connect various different systems together and make a workflow that automates a process that you might be doing manually. An example of a workflow automation might be creating a workflow within one of these tools which you set to trigger a specific time every day, say 7 o'clock in the morning, and what it will do is then go to your Google Calendar see if you've got any calendar notifications up to date, anything that's in your calendar, and then it will email you a list of all your calendar items today and what you've got to do so you can help plan your day, or you can be able to set it up so that if there was nothing in your calendar, you might get an email that says, hey, you've got nothing in your calendar today. You've got a whole day to do what you want, or even just not send an email at all if there's nothing in there. So that's a very basic workflow automation.

Now, I've never really used these workflows much in the past. Maybe I've been missing a trick previously, but before the kind of things I was wanting to automate needed thinking, needed something a little bit more than just doing something really basic like that, um. But obviously recently, with the advent of ai, you can now actually put ai in these workflows and do things that are much, much more complex. So here's an example of something that I'm working on at the moment. So I mean one thing that I I'm terrible at, basically, is taking the best advantage of some of the sort of assets that I've got available, such as the email list. I've got an email email list for people that listen to the podcast or have come across my own personal site. We've got the email list for keywords people use and you know the thousands of people on these email lists, thousands of people that have signed up to sort of hear content that we produce.

And yeah, I do produce the podcast regularly. That's one thing I'm quite good at if you've followed long enough is actually getting out three podcasts a week. I'm good at that, I do it, I enjoy it. What I don't enjoy and what I'm sort of become very lazy and rubbish at, is creating emails to promote the podcast episodes or to promote any kind of new content we create. It becomes just a baller and I've done it occasionally, usually when there's like a really big thing to talk about, but and it really boosts engagement with the podcast and boosts listener numbers. Every time I do it. But I just never really find the time or the motivation to do it.

So I thought this is something that's right for automation. So I started using this tool, this automation tool called n8nio, n8n um. It's not the most well known um. I came across it just by talking to chat gpt about. You know what alternatives to zapier um zapier is the most well, but there are also some drawbacks with that that I wasn't quite into. So I thought, well, what the alternatives are. Came across LA10 and I started playing with that and I'm working on this workflow that basically will trigger every time a new podcast is released onto the podcast feed.

So this is the key thing with all automation is you have to have a trigger. So it could be a rss feed trigger. It could be a webhook trigger where someone clicks we click a link on a website or an email. Or it could be a times trigger, so it happens at certain times every day. Or it could be a manual trigger where you go into the tool and then click, hit enter to trigger it manually. Or it could trigger from a new um line being added to a Google sheet or a new element being put in a database. There's loads of ways of triggering, but essentially they trigger based on an event. So the event in this case is a new podcast goes on the podcast feed, which happens automatically.

Buzzsprout, who I host with, sort out the feed for me. So all I have to do is upload my podcasts, schedule them on Buzzsprout and then forget about it, and then, when the goes out, it goes on the feed and then triggers this workflow in NA10. And what this workflow does is it gets that podcast URL, it goes to the Buzzsprout API and gets a few details about the podcast, such as where the audio file is available. It then takes that and goes to AWS Transcribe Amazon Web Services Transcribe Service and uploads the audio file to S3, the storage bucket on Amazon, and then kicks off a job with AWS Transcribe, which then transcribes the podcast into text. It then passes it to OpenAI on the 01 preview model and it says to it basically this is my podcast. Please summarize the episode in terms of what it's about, what the core topics are, but obviously don't tell people what all the takeaways are, because we still want people to come and listen to the podcast, because there's more to it than listening to a podcast and getting a summary. But create a summary that will hopefully engage people to come and want to listen to the podcast.

Then it goes to MailChimp and it creates a new email campaign with that content, with a subject that the AI also creates, and then it emails that email to me, sends it to me directly, so it will drop into my inbox with an accept or reject link in it. If I just then click the accept link, it will fire out the campaign via MailChimp back through the workflow. It will fire out the campaign by MailChimp back through the workflow and, even if I don't particularly like the email that it's put together, for me, it has actually created the campaign all the way through in MailChimp for me. So it's then just a case of going to MailChimp, quickly, logging in and just editing the content of the email and then hitting send in MailChimp if I want to sort of tweak it slightly. So even then it's done percent of the work that I wouldn't generally do myself, which is logging into MailChimp, creating a new campaign for the stuff that's just boring, okay, whereas it'll take it all the way for me, and in many cases I've been testing it with running through different podcast episodes and seeing what kind of output it's come up with, and I've tweaked the prompt to the point now where I'm actually really happy.

I would send out probably nine times out of 10, I would send out exactly what it says to the email list, because it's done a good job, it's done a good summary and, yes, I'd be happy to put my name to it, and especially because it is AI. Yeah, and I know I've been sort of less bullish on AI in the past on the podcast, but that's when AI was based purely off just asking a simple question. In this case, the output of the AI is heavily dependent on the input, which is the podcast. So that's me talking for a good few minutes in most cases, sometimes even longer, and it's based all the output, only on the things I've said, only on my opinions, only on my thoughts, only on my strategies, only on the things I've put in it. It doesn't add in its own things, but it takes a task that I find boring, time consuming to the point I don't do it, task that I find boring time-consuming to the point I don't do it. And it now is automated to it so that this can happen. And if you're on my email list, you'll start to see these emails coming out, maybe even before this podcast is released, because I'm recording this about a week in advance, so you may actually have already seen some of these before you hear this episode.

Now, this is just the start with what is possible with these workflows when you start putting ai in there in the first place, as long as you've got a good input. Like I said, my input is the podcast and I like to think that you know the the content I put out is at least human and not ai. You know I am a human. It's human content. It's come from my human intuition and my human experience. Okay, so the next step could be using it to create linkedin posts along the same lines to promote the podcast or to promote other content that we produced and put on websites. But then use it to create that linkedin promotion and do the posting for us, so that you can set that workflow up, that when a new piece of content is produced on the website, then do the linkedin post or then do the twitter post. There's all integrations within these things to be able to automate that.

The great thing with these automation tools is, although they've got lots of built-in integrations for lots of very popular other web tools out there, you also can use them to connect to any service or tool that has an API. So you can connect, for example, to the key, which people use API, if you've got the right County with API access that he could connect or API and you can start pulling questions from our api into the workflow and then use ai to modify it to make decisions based on those questions that you find and we're going to be. I'm going to be experimenting with, like using the keywords. People use api with these workflow. You can also use it to hook in data from other co tools as well, ones with different capabilities, such as using hrefs or samrush. You could use their apis to pull in and then you know sort of mix and match data between different services.

There's a whole host of things you can do. Anything that's got an api you can connect to with these workflows. So so the kind of the boundaries are limitless essentially, and especially when you start to use the ai reasoning in there as well, that means you can then do much more complex actions that used to be have to be done manually by a person. You can now do a lot of that work using the api and to make at least the basic core decisions or or flag new things to you in a way that you couldn't do previously. So I'm really excited about these.

I'm going to be doing more with them and you'll probably hear me talk more about them in the future, and when I can find specific SEO use cases that will be really useful for you. I will be letting you know. Anyway, until next time. That's it from me today, so I'll see you next time. Take care, before I go. I just wanted to let you know that if you'd like a personal demo of our tools at Keywords People Use that you can book a free, no obligation one-on-one video call with me where I show you how we can help you level up your content by finding and answering the questions your audience actually have. You can also ask me any SEO questions you have. You just need to go to keywordspeopleusecom slash demo where you can pick a time and date that suits you for us to catch up Once again. That's keywordspeopleusecom slash demo and you can also find that link in the show notes of today's episode. Hope to chat with you soon.

Thanks for being a listener. I really appreciate it. Please subscribe and share. It really helps. Seo is Not that Hard. Is brought to you by keywordspeopleusecom, the place to find and organise the questions people ask online. See why thousands of people use us every day. Try it today for free at keywordspeopleusecom to get an instant hit of more seo tips. Then find the link to download a free copy of my 101 quick seo tips in the show notes of today's episode. If you want to get in touch, have any questions, I'd love to hear from you. I'm at channel 5 on twitter. You can email me at podcast at keywords people usecom. Bye for now and see you in the next episode of SEO is not that hard.