30-Minute AI Automations Anyone Can Set Up & Sell Right Now

Here are some 30inut AI automations that anybody can set up and sell right now. I did this in a mixture of naden and make. com. And the first system is a

Google map scraper. To make a long story short, when I click test this workflow, what this is going to do is it's going to grab this search term right over here. In my case, Calgary plus dentist. It's then going to feed that into a Google Maps scraper. This Google Maps scraper is going to return us a giant list of all of the websites that rank for that term, Calgary dentist. We are then going to do some data processing, a little bit of code to extract the URLs, some filtering. We're going to remove the duplicates, and then we're going to end up looping over the items. What's happening right now is it's scraping specific URLs, extracting the email addresses of those URLs before finally looping back and adding them to the sheet. If I go over here to emails, you'll see that we've now scraped a variety of emails. And this was a very small example of the potential of a system like this. We only ran through 24 items. Imagine running through 2,400.

The second system is a search intent scraper. What this does is this goes onto LinkedIn and finds job listings that are for a particular search term. In our case, the term sales development representative. It then fires off these search terms to a third party scraper called Appify. What Apify does is it goes through each of these job posts and it scrapes them. So, it scrapes the company name, it scrapes the location, it scrapes the job details and description, it scrapes the duties and responsibilities. Once we've done all that scraping, we then go into our search intent scraper database. And this is where we actually put in the companies and then finally the email addresses of the scraped inquiries. The reason why this is so valuable is because instead of just scraping any email address, what we're doing now is we're scraping email addresses from companies that are extraordinarily high intent. These are companies that have money in their hands and are willing to pay to have a need solved. So instead of pitching them on getting hired for their job, what you do is you pitch them for a related service that solves the same need, but it does so for less money. It does so quicker and it does so with less attachments. The way the system works is first we run that scraper I was talking about. Then we extract all of the data. And then finally, for every element that we extract, what we do is we check a Google sheet, that database I mentioned earlier a moment ago, to see if a record exists. If it doesn't exist, we actually proceed and we add it. And then finally, we'll also pass this through an AI filter whose job is to essentially filter out any job descriptions or postings that are irrelevant to us. This allows us to add a flexible portion to the system. So, it doesn't just do it based off keywords. Now, for the important part, how do we get the email? What we do is we make an API call to a service called any mail finder which is a thirdparty service that allows us to discover emails thanks to something called nominative email enrichment where they permute the first name, last name, and then the email domain multiple times in multiple different ways until they find one that works. Now, the way an email finder works is after you make that API call, you can attach what's called a web hook URL. What we've done is we've actually forwarded this over to a second scenario who catches that web hook. After it catches that web hook, what we do is we research the decision maker using a module called Perplexity. Perplexity is a simple service that allows us to combine the flexibility of artificial intelligence with more or less the power and scope of something like Google to pull real-time search results from the internet that are related to that particular prospect. After that, what we do is we take data about the person. We feed that into artificial intelligence and have it generate us an icebreaker. And then finally, we pump it into instantly and then our campaign. If I scroll all the way over here on the right hand side, you see what we've done is we've started by feeding in a simple company, in this case decagon, that's hiring for a role, in this case sales development representative. We then scrape all of the data, including the description, including the text, including the job function, and so on and so forth. And then we actually find a co-founder or CEO at that role, grab their name, get their job title, get a LinkedIn URL, and then finally generate a high-quality icebreaker that makes it seem as if we did a ton of research on the job and we wanted to apply. You add this to any email campaign, and because it's personalized, your opening and reply rates are going to be substantially higher. The third system is a YouTube

repurposing scraper. What this does is when I send an email address that contains the URL to a YouTube video. So if I grab this URL up here, let's just grab it from here up. Then I send it over to in this case myself. If I then test this workflow, what this is going to do is it's going to launch another third party scraper from Appify to basically go out pull the transcript of that YouTube video. It's then going to feed that into artificial intelligence open AAI with a prompt that essentially asks it to grab all of the highquality and informative sections of that giant transcript and then generate simple, straightforward Instagram, LinkedIn or Twitter posts. We then grab that copy, split it out before finally appending it to a Google sheet. The Google sheet ends up looking something like this. So we have the post up here and we have a variety of different subsections of the transcript that are then massaged into something that might work on Facebook, Twitter, LinkedIn or Instagram. With this system, you can turn any massive YouTube podcast or longer form video into a series of highquality snippets that make it easy for content teams to repurpose footage. The last system is a

deep multi-line icebreaker. So, if I click test this workflow, what's happening is it's going over into a Google sheet and then it's pulling a search URL from this URL column. What this search URL is this is a database of leads hosted on a platform called Apollo. io that gives us most of the information about a lead that we might be interested in with one notable exception, which is the email address. So, what the system does is it actually goes and then calls a third party scraper, again built in Appify. Hopefully you guys are seeing a trend to go out and then grab the email addresses of the people on Apollo. It then performs a bunch of data filtering and it then for every person that it pulls feeds in their website, extracts the HTML, does some more data processing and formatting and then for every website searches all of the additional websites linked on that page. Unsurprisingly, there is a lot of very valuable data that is hidden in the websites that the prospects on this list are associated with. For instance, my own website, leftclick. ai, tells you a bunch of things about my service that aren't immediately or plainly evident on my LinkedIn profile or the details that Apollo gives me. And so, what we do is we scrape these pages to give us more context about who the lead is, what they value, and ultimately how best to pitch them. Once we're done with that, we feed all of the results of these HTTP requests, basically plain text website scrapes, into an HTML extractor. This HTML extractor's job is to take as input all of the links on the page and then pull them out. From there, we're going to end up with a big array of links who we process and then loop over. And then for every individual link, we actually go through and then we perform additional HTTP requests to grab all of the links on their page. We feed all of those subscriptes through into artificial intelligence to summarize the individual website pages before finally aggregating them and then using them to generate a very deep nuanced what I like to call multi-line icebreaker generator. Now, a deep multi-line icebreaker is essentially much higher quality than the one-off ice breakers that most people are currently doing in cold email. Instead of previously where we just say, "Hey, Peter, love your dog. Thought I'd connect. " At the end of it, you end up with a very highquality icebreaker that occurs not just at the intro line like most people do in cold email, but on multiple lines that also references specifically some very important things to the customer. usually things that are phrased in their own words on their website which you know if you pair it back to them they tend to like and think that you did a lot more research about. So in this case this website made by this guy Brad called Mission House put out a local guide for arts and coffee and then we're saying we're also a fan of finding the best espresso in town. We wanted to run something by them. Okay. We creep their site quite a bit. Building real community ties is something that's very important to them. They keep on mentioning partnerships with local nonprofits on their website. The whole point of this is you just make it so dang unlikely for them to think that you did not actually stalk the hell out of them in their website that when you finally do send them an email, they'll almost always at least give you the light of day because of it. That's it

for 30inut AI automations that anybody can set up and start selling today. If you guys want all of the blueprints and templates for this stuff, just check the link in the description. I focus on high ROI systems that actually go out and do something valuable for customers. So, you'll notice that a lot of these tend to involve some sort of scraping application. That's just because outreach and any sort of sales or marketing function just tends to be more valuable to a company than let's say some minor process optimization. But that's not to say that you guys can't also build, you know, backend or fulfillment systems. I just tend to focus on the things that, you know, drive the most disproportionate revenues. You guys like this sort of stuff, you'll definitely like Maker School, my 0ero to1 accountability program where I help you get your very first customer in AI and automation. So, if you guys have the technical skills and you guys maybe want some more business skills, absolutely run through that program and let me know your thoughts. Aside from that, thanks so much for watching. Like, subscribe, do all that fun YouTube stuff that gets me to the top of the ALGO.