Easy Zapier AI Automations - ft founder Wade Foster

Zapier's AI automations are so good, people are creating whole software companies on top of them. And it's so easy to do. Well, the founder is going to show you how easy. Coming up. Wade Foster is the founder of Zapier, the AI automation company. Yeah, let's get it. The next new thing. Why don't we start with this? I feel like everyone's going after HVAC and roofers these days in tech, you know? You have people who use Zapier to create their whole businesses. Give me an example of somebody.

Well, it's funny you say roofers. We have one of our, like, solutions partners experts. He started as a roofer, so he was running small-time business, local roofing business. You know, hail would come in, people would call him up and be like, I need a new roof. And he'd go out and like, get them a new roof. And so that's what he did for a living. And, you know, as per roofers go, it turns out he's like a little more techie, a little more nerdy than your average roofer. And he had set up a bunch of like technology to help him manage his business. So he had, you know, he was running ads on Facebook and Google to like target local stuff. He, you know, had a CRM to collect his leads. He would send out, you know, invoices so people could pay via credit card versus like writing a check, you know, or handing cash over, like, you know, stuff like that that, you know, is, is pretty modern for what you might expect a roofer to do. And, you know, one of these days he was like, you know what, I don't know that I want to be out on a roof all day every day for the rest of my career, but maybe I could help my fellow roofers out with all this back office stuff. And so he set up a, a roofing automation agency where he works with roofers and basically gives them the playbook for like, here's how you can manage your back office like way more efficiently so you can take on more clients and you can spend more time out on the roof fixing more roofs, get more billable hours.

How does Zapier fit in? What are some of the zaps that he creates for them? And essentially what he's doing is he's selling zaps, right?

Yeah, more or less. So, you know, if you think about how a local roofing, you know, business might work is first they got to get leads. Like, you know, when you, when you need your roof to get fixed, like, well, what do you do? You probably go to Google and be like, who fixes roofs in, you know, where you're in Austin, Texas these days? Yeah, yeah. Who fixes roofs in Austin, Texas? And then, you know, a list comes up and you're like trying to find these things. Uh, so a big part of a roofing business is like, well, I gotta, I gotta show up where people are looking for me. And so they might run ads on like Facebook or Google that are like geo-targeted and then drive them to a page or use like their lead form ads. And then there, that's where Zapier comes in. So we'll take the, the lead as it comes through Google or as it comes through Facebook, or if you have your own landing pages and have forms on your landing pages, and then they'll start to send them through an automated system. And so you can start to send out follow-up emails, follow-up texts with scheduling links, um, with payment forms, all this stuff that If you weren't doing automation, what that roofer would have to do is at the end of the day, they're hot, they're sweaty, they're like ready to go home and eat and have a shower. Instead of doing that, they got to sit down at the computer and go, okay, like, you know, how do I— do I need to call these leads? What do I got to do with these? Like a very manual, very bespoke process. That's not actually where they make their money. They make their money fixing roofs, not doing this stuff. But if you put automation in, you can create a much better customer experience, a much more responsive experience. And Zapier helps this, you know, all these roofers do that effectively.

I've seen whole agencies built on nothing but zaps. They take on a client, they create a zap, and the zap now is getting smarter and smarter. In fact, to call it a single zap is just oversimplifying it. Like, what are the smart things that it's doing now because of AI that weren't possible maybe a year ago?

The biggest new capabilities you get with AI are two things. One, you can add AI into workflows and what that gives you is the ability to work with unstructured data. Now, unstructured data allows you to do some very specific stuff. One, you know, in the old school world, you might have an email template that was using a mail merge. Well, mail merges are like sort of personalized, but not really personalized. I sort of pretend like I know you, but with AI you can actually go do deep research on somebody. So I can say, hey, tell me about Andrew and Mixergy and everything he's trying to do. And then based on everything you go learn, Now I want you to go write a specific email to Andrew using these key points and translated it to him in a way that he cares about. So instead of using those like old school vanilla mail merge, I'm able to actually generate a very custom email that is very specific to everything I know about you. That's something you couldn't have done before. So that's a great example of it. Another great example is you might have, um, a business where you get a lot of customer feedback, like maybe you've got a bunch of support tickets coming in or maybe you've got a customer feedback form. Well, in the past, you might want to go look through all that feedback and try and understand, you know, what are the common complaints I have? How do I go generate an FAQ? How do you all do all this stuff? Well, that required a human to sit down and like read all of them, categorize them in a particular way, and it was hard to do in a workflow. Like you just couldn't do it because the data is very unstructured, it's very messy. Again, this is where AI thrives. So you can send a big old block of text through a workflow to an AI and say, hey, what I want you to do is put it into a theme. Here's like 5 themes that could come in and I want you to categorize it. Then if it's categorized a particular way, I actually want you to go route it to this specific person on the team who specializes in these issues. They're going to be the rep that follows up with it versus having to do some round robin system or something like that. These types of systems allow you, AI allows you to put brains in your business in places that was really hard to put brains in the past. It was very manual, very expensive, and mostly, especially for small business, you're just like, I'm just not gonna do it. Like, I just can't do it. It's just not possible. And so that's where AI is like so exciting.

Yeah, I hear you. Even when you think about the mail merge, the fact that, that you can have a text message or an email fired off that says, Andrew, in your part of Austin, the freeze is so bad that you're gonna have trees falling down on your roof. And that little bit of understanding is like, ouch, I do remember that. That literally happened 2 years ago. I need to protect, I need something to protect us. Okay, I get it. Now let's talk about what else is out there and then we'll go into what we could do with Zapier. Because I'm on LinkedIn lately. I don't love it, but I'm, I'm learning to like it. Every freaking guy on LinkedIn ends up getting a bunch of likes or hearts or whatever it is that they measure success with on that platform by saying ChatGPT or OpenAI just crushes Zapier. Let's take a look at what they announced with their agents and then let's talk about how it differs. And then I'd like to actually see if we can build something together with you on Zapier. But let's start by looking at what's on OpenAI.

OpenAI launched their agent builder like 2 weeks ago. It's a pretty cool product. I am actually pretty excited about what's possible here. And you know, I think it is pretty different than Zapier. While it looks like a workflow builder under the hood, What it really allows you to do is build better chat agents. So you build a chat agent. So what is a chat agent and how is that different from like an automation or something on Zapier? Well, a chat agent is triggered by a message to ChatGPT. So you literally are sitting at your keyboard and saying, hey, I want a blah, blah, blah, blah, blah, blah, blah. And then instead of going to the general purpose ChatGPT you know, uh, LLM that's like answering, responding, it'll send it to this agent that has a specific set of instructions. And that specific set of instructions will help give a better answer to the person sitting there at the chat. So that's a pretty different experience. Whereas on Zapier, what you're trying to do is you can wake up your agent in any different way. You can have a Typeform come in, you can have a new email come in, you can have a calendar event, you can have a new customer on Stripe, you can have all these other things that would wake your agent up, and then you can have logic that encompasses any of the 8,000 different tools we work with. Whereas this is really about giving very specific prompts to ChatGPT to make it answer you better. If you do that, you can see like start. Well, what is start? Start means talk to ChatGPT. It means literally type a message. There's no other way to make this start. Then inside your agent, you can start to give instructions for it. So this would be like an AI step inside of Zapier where you'd say, hey, you know, I want you to, you know, let's see, let's call it like sentiment analyzer, right? You know, tell me if the message is positive or negative, right? So now you've got just like a very simple, like, agent here. That's job it is, is to assess the message coming in. They're just like trying to figure out if you're a happy person or a sad person. Something like that.

If we were, if we were to create like a brief generator on my upcoming meetings, it would be me starting a chat. That would be the start.

Mm-hmm.

In the chat, I would put a screenshot of my upcoming meeting, or I would ask it, what's— help me prepare for my upcoming meeting. Then it would—

yeah, you would give the chat a bunch of context. Yeah, go ahead. Mm-hmm.

And then it would be able to pull in my calendar, cuz I think it can. And then it would do some research and then it would come back and say, Andrew, based on what you like, for your prep for a meeting. Here is what I found about this person that you just chatted me that you want information on.

Totally. So you could say like, yeah, well, let's call this the Brief Analyzer agent, right? So you would say, uh, you know, write a concise brief based on the info you get from the chat, uh, and You know, use bullet points, less than 5, you know, blah, blah, blah, blah, blah, blah, right? So on and so forth, exactly the way you'd want it. But here's the kicker. This is where actually Agent Builder and Zapier get really interesting. So there's a thing called MCP. Now MCP might sound like this kind of techie concept. It stands for Model Context Protocol. But what's really powerful with Agent Builder is you can now call tools. Now, again, tools might sound kind of techie, but really all this is, is connecting to apps. Think of all the apps you use, and if you wanted this agent to have access to your information, you probably want to go use MCP to do it. And here is where you can see OpenAI has a handful of apps that you can connect. So your Gmail, your calendar, your Outlook, your Outlook calendar, your— Google Drive, et cetera, kind of some of the standard stuff. But then they've got third-party servers and there's not that many, but right here you've got Zapier.

Yeah.

And so Zapier, you can go hook in and now with Agent Builder, the thing that you're kind of, that you really want is I want access to all of my apps, not just, you know, the, you know, 8 here that ChatGPT offers out of the box. I want everything. And so now you can use our MCP server to give your agent more, ways to respond. So ultimately, that's how, you know, Agent Builder and Zapier are kind of like peanut butter and jelly. In fact, I would wager if you're not using Agent Builder with Zapier, you're, you're probably using like a much— it's basically just a vanilla chat, chatbot builder is what this is.

Got it.

Right.

So if, for example, I wanted to look up a customer who's using— who is in my CRM, which might be Close, I can't do that out of the box, but here I could say create an agent in ChatGPT's agent tool that also prepares me for a meeting, but looks up anyone else in this company that I've talked with and look it up in my Close account, not on the internet.

Got it.

And that's where Zapier comes in and is helpful. And 100%, but I don't even need, um, I don't even need their agent builder to do this. I can do this just directly in Zapier. And in Zapier, the nice thing is I don't have to go to the chat to trigger it. I can do things like press a button on my Chrome browser that triggers it. I could send a text to trigger it. I could do anything. It could just be time of day. It could be when this, when this meeting's about to come up, that kind of a thing. Okay. So basically to all the people who've said that they've killed you, congratulations on getting all the, all the likes and the hearts and the attention. We're clearly not there. And if anything, it's actually sending people over to Zapier, but it's, it's a nice way to introduce this new tool and tell your followers about it. Now let's see the comparable experience. Like if you and I were going to build this type of brief in Zapier, what would that look like?

So here we've got the Zapier Agent Builder. Okay. Now this is a little different. So instead of, you know, having the like nodes and drag and drop, which you can do with Zapier's Workflow Builder, with the Zapier Agent, you're just describing what do you want the agent to do in plain language? The nice thing is I know a lot of folks struggle with thinking through all the detailed instructions that agents really benefit from. One of the things you can do with the agent is just describe it like you would be talking to a friend. You wouldn't give a friend all the nitty-gritty details. You might just say, make me a meeting brief agent. That gives me some details before my meetings. This is a pretty bad prompt. This is not what agents generally prefer to get. They like detailed instructions. This is not detailed instructions at all, but we're going to start with anyway and see what happens.

For people who are listening, you just press start.

Yeah. Now you've got this Copilot that's over here thinking and trying to figure out Okay, what exactly are we trying to do here? And it's like, hey, I'm happy to help you with this. To build this effectively, I'm going to need a little more details. So, you know, what calendar system do you use? So I use Google Calendar. Let's use this. And then can you send the meeting brief like let's do 4 hours.

Yeah.

Before the meeting. So that way I know I've got the brief. Ahead of time. What do I want included? So let's see, include details about attendees. I actually only want it to do— only give me a brief for external attendees. I don't care to get a brief for people at Zapier. So only give me a brief for external attendees. I'll just say ignore internal attendees. Then let's see, previous meeting notes or context. You know what might be helpful? Can you, let's see, use any prior email correspondence I've had with the attendee. Let's see if it can do that for me.

This, by the way, is the Copilot's on the left and what it's doing is it's saying, look, before I create this on the right, I have some questions for you that I want you to think through. And when you're referring to all these questions, that's where it's coming in.

You're right. You've got it. So send me the meeting brief in email. So that's what I want it to do. But you could send it in Slack. You could send it, you know, whatever other places. Where should the agent pull information from? CRM, previous emails, company database, LinkedIn. Oh, interesting. I didn't answer that. So let's see. Use, you know, internet research. About the person, make sure to include a LinkedIn profile. We'll just do that for now. Let's see what happens. Okay, so we're gonna give it some more instructions because it said like, hey, I need more details to make this agent a little bit better. And you can see I'm not like, I'm kind of sloppy about this.

I see that.

I'm not even, there's a lot of typos. There's, you know, I'm not exactly, being super professional about how I go about this. And you can see it's over here, it's starting to build it and you can start to see your agent start to kick in over here on the right. And when you read through what it's starting to do, you're like, oh, that's better. You know, when a Google Calendar event starts in 4 hours, generate a comprehensive meeting brief for external attendees. So extract meeting details including time, title, location, all attendees, identify external attendees by filtering out internal company email addresses. For each external attendee, you know, search through prior email correspondence. So like it's fleshing this out in a way that an agent is going to be like, oh, that's good instructions. Like this is the kind of stuff that you would put in an actual standing op, like, you know, operating procedure. Like if you were trying to hire an employee, right, you would much rather give them instructions like this versus what I gave the Copilot. I gave the Copilot bad instructions. It's like, this is not not all that good, but over here we're starting to get something that you're like, okay, like someone could follow this. So this is the cool thing about using— this is the other place where AI is really exciting is it's not just helpful as a tool inside your workflows, it's also really helpful for building workflows because building workflows is kind of hard. Like not everyone thinks in systems, thinks in structure. And so what we've tried to do with Copilot is make it so that You know, when you're, you're just like, have a vague idea of what you want. I just, I kind of want a meeting brief thing. Like you can just tell it that and then it will coach you through, uh, how to go build all that stuff.

I, and one of the things I told you before we got started that I really like about the software is it's not just giving instructions that make sense. It's also written in a way that's highly scannable. Like you look through it and this feels like I, like a blog post almost, but with just the facts. And so it starts off with step number 1, extract meeting details including time, title, location, and all attendees. Step number 2, identify external attendees by filtering out internal company email addresses. Step number 3, for, for each external attendee, then there's a bullet point, bullet point, bullet point. Then it goes on to step number 4 and so on. And this is so easy to read that now I can go back in and edit it if I want to change it. So I might say for me, external means all email addresses that end in one of these 3 domains. Big, uh, oh, sorry. Internal is all email addresses that end in one of these domains. Okay, I got it. I see it. Then we hit per agent, we can go in and edit it in the instructions.

Boom.

Then we hit preview.

Yeah, you got it. And so, you know, you can see up here, Google Calendar, it's a new event. So this, it's set up the trigger for us.

Good call. You can see, uh, it's, I didn't realize that this is like, it's saying, this is what I know is going to kick this off every time I see a new event. Now you can go in and change it and say, minutes before the new event I want you to do it.

Yeah. And actually, you know, I can see it here. I do think it's made a mistake. So this thing is not perfect. You're going to have to pay attention to this. You know, in this case, I actually think I want it to be Google Calendar. We want it to be when an event starts and we actually want it to be— let's do my own calendar and I actually want it to be 4 hours. So made a mistake, right?

So this is what you asked it for, right? Right.

But, you know, making the change was like actually not that complicated. Like I just clicked a couple of buttons there. And then as I read through it, most of the rest of this stuff looks pretty good. Let's go see what it did on the Gmail tool here. So it's basically going to go look inside of Gmail and then it's going to guess. I actually want it to guess, like, just go figure out, you know, if I've talked to Andrew before, basically, and tell me, you know, if there's anything in those emails that I need to know before this meeting, just include it. So I'm happy with this. You know, what else is interesting? You know, this is probably the one place where I might make some changes. You know, meeting overview, external attendees, prior correspondence, LinkedIn profile. You know, I might say like, well, here's, here's like the style of a brief that I like. And so I might give it an example of like, you know, can you make it look kind of like this and structured this way, etc.? Maybe somebody on my team wrote like a really nice brief, right? Once. And I'd be like, follow this format for me. But by and large, like, I'm pretty happy with it. And so you can go ahead and click, you know, the agent preview, and it will go do, you know, a test for us here. And so it's going to go take a look at an event in my calendar, and we'll see if I don't accidentally leak PII here. So, oh, it actually pulled in the Mixergy one, so that's great. So, yeah, it's going to say I'm going to, you know, see what's going on here with Andrew. Everyone knows your email address now, Andrew.

I'm good with it. They all know yours too.

So it takes a minute to kind of test all this stuff.

And now it's just, oh, this is the part that's gonna make me nervous 'cause it's gonna pull up all our past email interactions.

Yeah. So we'll see. You might, you might have to blur out what, what pops up.

I won't blur. I don't, I can't imagine there's anything that's private. Yeah.

It's probably just like, hey, how are you?

I think a bunch of it is just me showing off about how I have one of the, actually the first account on Zapier. And as a result, I still have all these features in my free account. That I refuse to let go of because it's the classic account. Even though we pay for a real account for our company, I still hold on to that.

Yeah. Yeah. That is a little known fact is you were the first external user of Zapier. So for 12 years, no, 13 years ago now.

Let's also say customer. I paid on your way to—

Customer. You did pay. You did pay. It's a wild story. All right.

It's going. Did it complete it? Okay, it found it.

It did find it. So it found and looks like it found a bunch of emails, et cetera. So I, it's still thinking though. So you can see up here.

Oh, I see.

We probably need to make this more obvious that it's, it's thinking still. That, that is the one challenge with agents versus workflows. Workflows are fast. They're fast. They're reliable. They're consistent. Agents, the LLM's thinking, you know, it's, it's like trying to work its way through this. It's trying to follow the instructions. The more tools you give it, the harder it thinks, the more mistakes it's going to make. These are things that as you start to get used to building agents, you start to learn a little bit more about how to use them. I find with agents, it's easier to get started than with workflows, but you run into more, I call them potholes. It's not major problems, but they're things that it's not so good. Whereas with workflows, They're a little harder to get started, but they work. They're like, they're rock solid, very consistent, very reliable.

Because workflows are just, you tell it what the variables are, you tell it what to do, you step-by-step guide them.

All right, while it's doing that, it's not having to think, it's just going and doing the thing. Yeah.

While it's doing that, let me ask you a couple of questions about the business. How many customers do you have now?

Uh, we're like 350,000 customers or so.

Wow. And revenue?

Russia. Nice try.

Hundreds of millions of dollars based on that, we can say.

Sure.

Yeah, we'll go with that. You didn't take on much funding, right?

We did a seed round that was $1.2 million in 2012.

Did you touch any or you hardly touched any of it?

We treated it like the last money we were going to spend. We did we did burn money for, you know, about 12 months. Like, we were burning money. The most money we lost in a month was about $20,000, which at the time was like terrifying. But now I hear the stories of some of these companies that are like literally burning billions, like a billion dollars a month. And I'm just like, oh my gosh, that's insane.

No, this is nothing. I mean, even smaller companies now are burning a lot, though. Actually, I was just talking to Gary Tan of Y Combinator. He says the revenues are growing phenomenally for their companies.

Yeah, I mean, there's, there's a lot that are just doing really, really well. Um, so I, yeah, it's, it's impressive like how fast these, um, you know, companies are growing these days.

How much are you gonna continue to depend on outside LLMs for your thinking, for the AI internally that you're using?

Yeah, I think, you know, we will probably always depend on, um, external LLMs for large parts of this. I think these large language models, these frontier models are, they're pushing the envelope, they're at the cutting edge. So it's really useful for getting, you know, a rock solid model that can do most things well. We'll see if we start to like sprinkle in, you know, our own like custom smaller models that are like really hyper-targeted at specific tasks that maybe the large language models are just not quite as specialized at. So that's, that's an area we're considering.

But you're not doing that now. I kind of assumed that you were, that you were taking on the bit, the smaller stuff for yourselves. Okay.

All right. Here we are on our agent. So you can see it's gone through and created a brief based on this upcoming meeting I have with Zapier on Mixergy. And this is the email that it wants to send. And so you can see it generated this, this email. Of course, it's in HTML, so it's a little tough to read. But you can see it's generated one. If we're going to just go ahead and approve it, and so this will send me an email. If you give me a second, I can change screens and we can actually see it. We can actually go read what gets sent.

While you're doing that, if I were doing it myself, I would probably say I don't want any HTML. I just want you to do nothing but plain text. Yeah. You could.

Let's go see what it does though.

Fair.

Window. So this is the email it sent me. Meeting brief. Zapier on MixerG. You know, here's the details of it. And then here's stuff about Andrew. So, you know, backgrounds and achievements, notable interviews, education, current focus, expertise, recent activity, you know, prior email correspondence. Whoa!

Wait, that's interesting. It actually knows that I'm doing this series of AI software founder interviews. Okay.

There you go. Yep. Key context from recent communications. So you can see. You know, the outreach, the scheduling process, interview focus that you want to spend time on. Wow. Topics that Andrew may cover, you know, Andrew's interview style, action items, etc.

I like that. Andrew's interview style, known for thorough preparation and fact-checking, focuses on actionable insights for entrepreneurs. Experience with 2,000 founder interviews, likely to ask about specific metrics, strategies, and lessons, which is exactly what I did here.

It nails you, right?

It really nailed me perfectly.

So you can see like we built this in what, 5 minutes?

Yeah.

And this is what you get with 5 minutes of effort. Now I could look at this and also go like, well, you know what, I don't, I don't like this part or I don't, or I wish it did more, you know, maybe I wish it had more context on, I don't know, like maybe your education. I really care about you, what you did at New York University or something like that. And so I could go back and edit the prompt and be like, you know, pay a special attention to these things and less about this, or make it shorter or make it longer. So you could give it more guidance, but you know, even just out of the box with like a super basic thing.

Yeah.

You know, this is, this is to me, I think what is so exciting about AI is you get pretty good stuff pretty dang fast.

What, what's interesting is it didn't get any of the past email interactions that we had because I used a different email address to book it. And, uh, it would've been interesting to see what came up over the years, but I'm, I'm glad of this. All right, we'll go on to, to the next thing. Which is the agent that qualifies leads. Do you want to look at one of those?

Yeah, let's do that. Do you want to team me up or you want me to ask it or just dive, dive in?

You know what? What I guess what I want to know before we start diving into what this is, is who cares? Like essentially what we're looking at is some— it's, it's looking at a Typeform entry and then it's qualifying whether the person is a good customer or not. Why is it so important that this is what you're showing me?

So every business has to acquire customers. Like, this is just one of the core competencies of every business from day one is you have to figure out how to get customers. And if you're any good at marketing at all, you're going to acquire a bunch of leads. And not everybody that sort of comes into your funnel is going to be an actually good fit for the products you sell. Okay, so what this agent here does is it pretends that we are a fictional automation agency that specializes in selling automation consulting services to mid-sized regional insurance providers. That's who we're really good at. Like, maybe you're from the insurance world and you just know exactly like the processes inside and out, you know, the tech stacks, you know everything. And so you are really good at this kind of business. And so you have, you know, you're, you're putting advertising out in the world, you're telling all the regional insurance providers like, hey, I can help you do this stuff. But, you know, occasionally you've got like a mom-and-pop person coming in, maybe you've got like a mega, you know, mega company that comes in, maybe you've got someone that's not insurance, maybe they're real estate, or maybe they're, you know, some other financial services, like close but not exactly what you do. And they're just reaching out because they're like, well, You know, insurance, but maybe, you know, maybe you could figure out how to do automation for MySpace, etc. And you have to figure out which ones do I want to go spend my time on and which ones do I not want to spend my time on and how do I want to follow up with them? So you can make an agent that, you know, you can give it all the rules. And so this is a case where I've already built one. So we've, in this case, we've already gone through the Copilot experience and it's helped, you know, fill out all the sort of standing operating procedures here. So we've got Typeform, which is using is where we collect the lead. But once we get the lead, we're going to pull out the lead's name, the email, the company, the role, the website. Then we're going to go do internet research on this. So it's going to go look out on the internet and find everything we can about this person who is a potential lead for us. Then based on all that information we get, we want to go compare it to our ICP, an ideal customer profile. And so here I pasted in what we think that ideal customer profile is, you know, the US-based mid-sized regional insurance provider Here's some things they're struggling with. Here's maybe an approximate company size, the industry they're in, maybe their revenue benchmarks, that kind of thing. Then once we've got that, we want to go score it, you know, based on all this internet research. Are they a great fit for us? Are they a possible fit or are they a poor fit for us? And no matter what, I want to store them in the CRM. So even if they're a bad fit, I want to go put them in a Zapier table, which we're going to use as like a basic CRM for ourselves. Um, but beyond that, I've got some conditional logic. So if it's a great fit, I want them to just go ahead and draft an email inside of Gmail saying, I want to follow up with this person and go use all the information you found and then go take like relevant case studies, examples of similar customers, like, you know, give clear next steps for a discovery call, be professional but friendly so that the agent knows how I want it to draft this email. So that's the first thing we want to do. And then go ahead and update the Zapier table to say I've— that you've done this. Then you got to go figure out what do you want to do with the other one? So if it's a possible fit, what I want you to go do is I want you to actually go send me a direct message in Slack. So go ping me and let me know that, hey, you got a possible lead here and I need your help. Like the agent's not sure, maybe it should, maybe it shouldn't. And so in Slack, you're going to send over a summary of what you found. You know, reasons why you're uncertain. It's like, hey, I wasn't sure, yes or no. And then, uh, you know, Slack will give me one of those buttons that's like yes or no. And so I can just quickly skim, you know, maybe I'm, maybe I'm doing a podcast real quick with Andrew and I'm looking over, I got a lead in, I just happen to spot it real quick and I'm like, ah, you know, uh, yes, go ahead and give me that one, right? It's out of the corner of your eye, you're just, you know, you, you just want to, want to keep, keep things moving. And so then if you say yes, okay, great, do the same thing, go draft a personalized email the same way as we did for the great fit leads, update the table. And then if you say no, no response needed, just let the, just let the table know that, hey, it's a poor fit. And then of course, last, poor fits, you know, go ahead and do that. So again, you're just describing how you want this workflow to work. You know, this covers like, you know, pretty basic lead, lead flow system that you might use in any small business.

I could see myself setting this up now. To if someone is a perfect fit or if someone is the ideal customer, ping me with a text, call me, send me a message, send someone else a text, and that way I could reach out to them immediately. Like I spent Sunday morning just deciding that I would sell this Prius that we've had in the shed ever since I came from San Francisco to Texas. I said, we're not driving it here, we got to sell it. I filled out a couple of forms on websites. And there are a couple that were so quick to call me that I said, okay, let's book a meeting. I'll come in and I'll drop the car off. And I eventually went with the person who made it easiest and responded the best. And I think that in a situation like that, if I'm their ideal customer, for them to reach out to me while I'm hot and while I'm doing this research, incredibly powerful. Speed to lead. Okay, I get this. I get this value. And you know what? I never thought to do this for myself. I use forms. I like Tally. I like Gravity Forms. I use them all the time to collect information and I just Immediately send it to whatever we need to get, to get done. I never thought to create this interim step that says, wait, now analyze it and then go and do it. And by the way, you guys also have forms, I think, on your site. As I was clicking around today to prepare for the interview, I saw that there are forms. Yes.

So we have, uh, Zapier. Zapier Interfaces allows you to build native forms. Zapier Tables, you have sort of like a, a, a native spreadsheet table database-like system. So there's a lot of stuff you can just do native. In Zapier beyond like, you know, if you don't have like a forms provider or a tables provider, all this other stuff. And, you know, it's a, it's a pretty good setup. Probably saves you some money too, because it's all bundled in with one Zapier subscription.

So coming away from the screen share for a minute, let's talk about business ideas here, because Wade Foster, I get pinged a lot by people who say they can create this for me, they could create that for me, they could solve this problem, that problem. And as I talk to them, I realize a lot of them are building their agencies on nothing but a collection of Zaps. Give me a couple of ideas of businesses that are running today, and then some that could run with nothing but automation built on Zapier.

Oh, what is a business that could run entirely on, uh, automations?

Meaning sell, sell nothing but automations. Like go into a business, like you gave me a great one with the roofer, right? Roofers, they've got customers coming in. Totally get it. I could imagine that there are 50 other local businesses like that. Maybe one for landscape.

100%.

One for gate fix, gate repairs. Okay. What else?

I've seen one for the trades. Like there's one that just sort of totally specializes in trades workers. So roofers, plumbers, electricians, you name it.

Taking all their leads and using Zaps, automating it and customizing it for them. So if they're the type of people who want nothing but calls, the Zap could then call 'em up and— right? A Zappy— a Zap can call up and send it. Totally. Good. Definitely do text messaging and so on. What else?

Another great one, real estate agents. Real estate agents are fantastic because they often operate kind of as like quasi small businesses. And so they, they buy fast, they, they run independently, they can make decisions, they can move for themselves, etc. So real estate's another great one to go work to do this.

And then what's an automation that they would need? Have you seen these already?

So a lot of them, there's a lot of paperwork involved in real estate transactions. So they have leads as well too. So they've got leads coming in from Zillow, Zillow sending them leads, Redfin sending them leads. So they got that whole lead flow that's happening. Then they've got scheduling is a big part of it, you know, come out to the open house or come do the like private showing. So there's a whole scheduling flow that needs to happen there. Then you've got the paperwork process. So, you know, I'm sending out this paperwork, waiting for a signature, sending it to this person. So like there's a whole bunch of systems that happen once someone decides, hey, I am interested in like, you know, putting in an offer and then the offer gets accepted and then there's what's they got to do an inspection. They got to go through all these things. And, you know, all of them are like fairly standardized, fairly routine. And so there's a bunch of automation there where a real estate agent can benefit quite a bit.

I imagine digital marketing in general for online-only businesses is an easy one, right?

Digital marketing agencies, they're like, this is the place where I've seen most automation agencies spin up because there is so much just low-hanging fruit that can help any business be more, more successful. Mostly these lead management flows that we're showing off, like these are exceptionally impactful and they generate money. Like speed to lead, you, it improves your conversion rate massively. And when you improve your conversion rates, It means you can now be more efficient in how you deploy your advertising dollars because now you're getting a higher customer lifetime value, higher ACVs. So now you can afford to pay more for those leads than you were in the past. When you're able to pay more for those leads, you're boxing out competitors. And so these types of automations, it's not just about being faster or more efficient and like saving you time. It is actually like real money hitting your, uh, your bottom line when you do this stuff really well. And so you like, a lot of these folks understand this, uh, the, the marketing agencies deploying these, these workflows.

You know, we've done, you mentioned that, uh, I've got a company that's part of the GatewayX Venture Studio. Um, and Jesse will post on his social media a lot and he'll post things that, that generate leads. The thing is he's got a company called Growth Assistant. They don't want to— they don't want to work with companies that have fewer than 10 people. Because if you have fewer than 10 people, you're probably not going to need to hire a growth assistant. You're definitely not going to want to hire 3 of them, or almost definitely. They just don't want those leads clouding or cluttering up their system. On the other hand, I tend to deal with smaller operators, and if you're 10 or under, you're perfect for me. So when someone fills out a form to get something, a lead magnet, there's a quick analysis that happens. If it's 10 or more people, go to Growth Assistant. If it's 9 or fewer people, come to OurBusiness. And it's such an interesting setup. What we hadn't done though is something that I'm learning from you is if someone has, say, 100, we could automatically text the top salesperson immediately and say, look, this is a good person. You should at least— you should go. In fact, we could probably even have analysis done on them. If it's someone who has— if it's a major company, Jesse might want it to go directly to him for growth assistance and see the co-founder and just immediately text that person and say, hey, I saw you on the site, what are you interested in? Right?

Totally. Yeah. I mean, you know, it's, it's like if, I don't know, Nike shows up or, you know, Disney shows up, it's like, I, I, I will stop anything I'm doing right now to go attend to the need because the opportunity is so, so large. Um, versus, you know, someone, I don't know, uh, Bob's Donuts. They might be great, but you, you may not have as, as much of a business opportunity selling to Bob's Donuts.

I get this. Let's talk about where this is all going. Like, I feel like you are sitting on one of the hot, um, AI companies. A lot of times it feels like when there's an AI company coming out, yeah, it's nice, but OpenAI is gonna take over. Yeah, it's nice, but until ChatGPT can do the whole thing, they've got a business and then it's gonna go away. You feel, to me, it feels like you are locked in, dude. Like every software company has got to have a Zapier connection or else they're disconnected from the rest of them, right? They're on an island on their own. Is ChatGPT going to go and connect with all of these tools and going to go through the headache that you had to do? It's possible, theoretically, not likely, right? You're just sitting on this AI company that's, that's durable. It's one of the few ones.

Yeah, I think like this category is so important. Like it, you know, every business can benefit from automation. Like every business. There is no business out there that would not benefit from deploying these things. AI is valuable by itself, but it becomes like critical and exceptionally high ROI when you connect it to the rest of your stack. When you hook it up to automation. It's even more valuable when, as a business owner, you can choose the tools that are best for you. And so what I see the best automators do is they know ChatGPT is really good at this type of queries. Claude is really good at these types of query. Gemini's really good at this type of stuff. And so they're using Zapier to say, hey, go route this request here and route this request over here, and this one needs to go there. We benefit from having an agnostic provider who says, "Hey, we're just going to give you all these capabilities. We're going to of course help you make it really easy to build this stuff. But if you want to, if you want to get really brainiac about it too, you can go customize this stuff to your heart's desire." That's where our mission is. We want to make the ease of use, that really simple setup, as simple as that meeting brief generator that we showed. But for someone who is like, that's not good enough, like that was— that meeting brief generator was fine, but like, I really need it to be this. You can come in and fiddle around with it and really get it working so that you're just like, it matches exactly the way my business works. And so that's where— that's where our mission is.

Do you have any personal ones that you do for yourself?

I'll tell you. So the— The one I think is— I get a lot of value out of is we use meeting recorders for a lot of our meetings internally. And so I have found that AI is an exceptionally good coach. It is infinitely patient. It is neutral. It just observes what it sees and it tells you what it thinks it has observed. And so for our exec team meetings, We, we have these recorded and so we'll take the transcript automatically. We'll send it to a prompt that is based on the Five Dysfunctions of a Team. So if you haven't read Five Dysfunctions of a Team, it's— it basically describes like good behaviors and bad behaviors of teams. And then based on this prompt, it will generate coaching for all the meeting participants. And so they'll all get a DM that says, here's how the meeting went for you. And it is so valuable because again, it has that just very unbiased, very neutral observer. You know, it doesn't care about, oh, Wade Foster's the boss and so I need to butter him up a little bit. Or, you know, this— I don't really like this person, so I really want to like, you know, grind their gears a little bit more than the next person. Or like, this person I like a lot, so I'm just going to be, you know, I'm just going to take it easy. It doesn't— it doesn't think— it doesn't care about any of that. It's just— it's just like, I saw that here you interrupted this person and that wasn't great. Or I saw that you didn't speak enough and you could have had a really good point. You should have voiced your point of view. And so it just gives you those things. It's neutral and it comes in a DM. And so I'm just like, great, thanks. That was a helpful tip. And so it's one of those things that I find is a very— it's the type of thing that's pretty small in the grand scheme of things, but it's so fundamental to like how I show up as a teammate and it just makes me better.

I'm now— I like Grain. I love Grain because it gives me videos that I can clip afterwards and and then it lets me search past conversations. I went in to see if they have integrations. Yes, they do. They have an integration with Zapier. So what I could do is have my conversations go to Zapier and then come back and evaluate how I did. And then maybe if it's a team meeting, how my whole team did. I like that a lot. Totally.

You could do it for this interview too, right? So you could have this running for this interview and you could say, you know, my best, when I'm at my best as an interviewer, I do these things. These are the 5 things that I think make me an exceptional interviewer. Here's me at my worst. These are my bad habits. Maybe I don't know, you don't interrupt people, but maybe it was like I interrupted folks or I laughed over them or I don't know. What are the habits you have and say like, hey, coach me on it. Tell me how I did. And so after every interview you could get actual coaching and it's probably good coaching because you probably have folks on your team that you ask for feedback from, but You know, you're Andrew, you're, you're the guy, right?

So they're probably like, oh, you did great, boss. You don't wanna insult me 'cause then I might not perform at my best.

You want, mm-hmm.

You know what I could do? I wrote a book on interviewing called Stop Asking Questions. I've got the PDF. I could take the PDF. I could say, okay, based on this book, measure me. And then the other thing I could do is I could then take a few interviews from other people who I respect and say, to go to, that's where I would go to ChatGPT and say, I want you to break down why you think these are good interviews. And I want you to give me like points and then examples for each one. And then at the end of it, say, I want you to write a prompt for me that will, that I can use to evaluate my interviews against all this. I love that.

And now stick it into that automation. And so every time that, every time you get off of a, of an interview, it fires off that transcript over to that prompt. Then that prompt sends you an email or sends you a Slack message and just says, here's, here's how it went, Andrew.

I will have to do that because today you got an A+. Because if I have to do it myself, I'm going to move on with my day and not be able to do that. I wonder, actually the other one that I use is I use Granola and yeah, look, you're in Granola too. Granola I like because it will not have to join the meeting. It'll sit on my desktop. It'll listen even on setups like this, which is not one that's like, it's, this is not a meeting app. It's a, it's an interview app. I'll go with that.

I love Granola and Granola, you can do it. You can sort of do these things with the Ask Granola, right? Where you can. You know, if you've recorded, you know, a bunch of interviews like this, you could say, look over the last 50 interviews and tell me, you know, what's, what's my style or what am I good at? What am I bad at? Like, so it can look at a huge chunk of 'em at once, which is nice too.

All right. Gimme, gimme a couple of other apps that you really like. So you like Granola because it lets you do all that. Gimme a couple of other AI-based apps that Wade likes.

Yeah. Um, I have started to use, actually just recently I started using Claude Code. So I'm not an engineer. I long ago, I used to write code, but I kept hearing people say, yes, it's called Claude code, but like you should use it for non-technical tasks. You should use it for non-technical tasks. And so I was like, okay, I'll go figure out how to do this. And so I'm like, you know, opening up the terminal for the first time in forever. I'm downloading Claude, like trying to figure out, like, you know, trying to remember these commands, these terminal shortcodes. But then once you get it open, it's kind of just like talking to Claude. Like, I don't need to know any fancy commands or anything like that. I can just talk to Claude and it just does stuff for me. So like, I had an old laptop and I was like, hey, it's getting kind of sluggish. It's like, you know, I want it to be more performant. Can you like, like, can you help me figure this out? And it was like, sure. Do you want me to like write a cleanup script for you that will like check all the stuff? And I was like, yes, please. And so, you know, wrote a little Python script called like check setup or whatever. I didn't even look at the code. Like, I didn't even know if it was good code or bad code, like just no clue. And it was like, would you like me to run this for you? I'm like, yep, sure, please go do that. And then it went and looked and was like, here's all these like, you know, old installers that you don't need. We can delete those. Here's a bunch of like movie downloads you don't need. We can delete those. Like, here's a bunch of things that you can just do. Would you like me to go do that? And so like this old laptop that was just like not really like functioning anymore, it's like, it's, it's kind of good now. Uh, so, you know, it's just like a, I was like, wow, this is, this is pretty cool. Yeah.

I heard you did a setup, a session with, uh, the 10x guys where you were teaching Zapier to them. They showed me Claude Code and it was just like ChatGPT, but with enough power to control your computer and the internet that you can tell it to, like the example that they used was they went They said, I want you to go into Alex Lieberman, the co-founder's LinkedIn account, find Andrew, write a message to him and send it out. And I go, this is actually sending it out from there. This is really impressive. All right, how about one last one?

Another one that I have really loved is Monolog. So Monolog is, um, a voice-to-text app. So, you know, kind of like Super Whisper or some of these others. Um, but Monolog in particular, I really like, 'cause they've done some really nice design touches where anytime you hit the keyboard shortcut to start recording, it actually looks at your screen so it can see that my cursor is in Slack or it's in email or it's in a Google Doc. And so based on that, it knows how to adjust my writing style to fit that. It's like, oh, you're writing in Slack. It's probably a little more informal versus you're writing an email to somebody. You want to do it proper versus you're in Google Doc. Oh, you're probably writing like a structured memo, like I'm gonna help you. And so I can just talk into it. And if I like make mistakes or do it a little bit like not quite the way I'd want it to sound in writing, the prompts will come in and like clean that stuff up for me. And so Monologue is like, mm, chef's kiff, just really well designed.

They really are artists over there at Evry that do it. I'm gonna give you one that's random that I, I was trying to think of what's one that Wade Foster probably doesn't even know. It's called Lori and it's for the phone, the iPhone and the Apple Watch. I love my Apple Watch more than my phone. What it will do is, you ever wish you can just say, hey ChatGPT, and just talk to your phone with, if you have earbuds in, like you have 'em on right now.

Yep.

So you have it in and you say the, the shortcut they have is cut the pineapple, but you can change it to whatever you like. It's stupid, but it, but it's stuck in my head. And then you're chatting with ChatGPT without going and turning your phone on and switching. So I walk around listening to audio all the time in my ears, mostly Mixergy Podcasts, because really I'm not an idiot. I gotta listen to the best, but I'm listening to it. And if the question comes up, I go, cut. Hey Siri, cut the pineapple. And then you get to have a natural conversation with ChatGPT. Really well done. It's the, it's the integration that I wish Apple had built in.

Love it. That's great. I'm gonna have to go check that out.

Yeah, brother. All right. Thank you. And thank you everybody for watching. Get outta here, everyone. Bye-bye. Do you think you can give away the, the 5, um, dysfunctions of a team setup?

Yep. You can? You can. I can. Yeah. I'll go track down the prompt we're using for that and we'll share a template with everybody.

And we'll give it to everybody as a template for Zapier. Love it. Thank you so much.