Prompt Engineering
Hey. It's Bootstrap The Web. It is Friday, June 7, and we're back at it. Today is the last day of school for my girls. And, yeah, summer is here.
Brian Casel:Let's go, Jordan.
Jordan Gal:Yesterday was the last day of school for my girls, and today is already complete chaos. My oldest had four friends sleep over, the middle had one friend sleep over, then more friends came over at, 8AM. There's air hockey happening. The boys came to visit at, like, 9AM. Wife went out to get bagels.
Jordan Gal:I mean, here here we are. So it's it's fun. It's good chaos. But summer is summer is here.
Brian Casel:That sounds fun, man.
Jordan Gal:Yeah. It's fun and this this town has a great thing they do the last day of school right after school which ends early, everyone goes to the beach. So the entire town is at the beach. It was lucky we got it was like 75 degrees and sunny yesterday and that's it's just like a fun celebration thing and we're lucky enough to be right on the lake. Yeah.
Brian Casel:So it
Jordan Gal:was like a beach day. I took half the day off. Everyone's having a few drinks. It was it was beautiful.
Brian Casel:That's awesome. I so so how far are you from the lake?
Jordan Gal:We are about five blocks.
Brian Casel:Oh, yeah. You're you're real close.
Jordan Gal:Yeah. Really yeah. It's a trip. It's like we live in Illinois but it is a beach town. It is right Yeah.
Brian Casel:For sure. Yeah. I I remember living in Chicago not far from the from the lake. And so here in Connecticut, we live like a ten minute drive to the Long Island Sound
Jordan Gal:Yeah. Beach. Beautiful beaches.
Brian Casel:Absolutely love it. Like, you know, one of these weekends we're gonna start going. We we like to go out there like every weekend, do breakfast on the beach. And you grew up in Long Island like like I did. I I don't know about you.
Brian Casel:I feel like I can't live anywhere that is just totally landlocked. And just like you think about like so much of our country is, but I've I've always grown up near a coast and having like easy access to a beach.
Jordan Gal:Mhmm. I mean, if you look at the population map, a lot of it is centered around the coasts, you know. That's true. But but I'm with you.
Brian Casel:I,
Jordan Gal:Portland was an anomaly. We we went out there thinking, hey, it's kinda by the beach, but it's it's a good hour and a half drive
Brian Casel:to beach.
Jordan Gal:And the beach is so unpredictable. It could be 75 and sunny in the city, and then you drive out there and it's 52 degrees and raining or it could be 90 and sunny. It's very very unpredictable. Mhmm. That was the departure.
Jordan Gal:But I we're very happy to be back by by water.
Brian Casel:I and I love Lake Michigan and and the Chicago area. I feel like it's actually kinda similar to where I live now in Connecticut where it's like you get the benefit of It's like a legit beach. I mean, Lake Michigan is like practically an ocean. Yeah. It's an ocean.
Brian Casel:You know, like But very calm, you know, very calm waters and everything. But the cool thing about it is that depending on where you are, it's not super crowded and it's and it's pretty clean like beaches and clean water. And and the same idea here in Connecticut. I, you know, I grew up in Long Island, New York, fifteen minutes from the Atlantic Ocean.
Jordan Gal:Yep.
Brian Casel:But it's crazy traffic getting down there and then it's just like insanely crowded on the beach. You're you're you've got beach towels like two feet from the next person. And
Jordan Gal:It's good when you're 17, bad when you're 40.
Brian Casel:Yeah. But but here, like up in Connecticut, it's just like totally wide open. Nobody's around, super clean, super calm. Love it. We we spend so much time down there.
Jordan Gal:Yeah. Yeah. Anyway. Alright. Now, on the work front.
Jordan Gal:Got a lot going on. We're about to launch. It's about to happen. It's real.
Brian Casel:Oh. Alright. So what what does launch mean? What does this look like?
Jordan Gal:Yes. Okay. Fair fair question. And Patrick, you know, I'm gonna disappoint you. Not gonna give the URL.
Jordan Gal:We we are set to publish on either Monday or Tuesday. And the delay we thought we're gonna publish this The delay was was two things. One, the demo video that we're trying to put together. Mhmm. It that just always takes longer than you think.
Jordan Gal:Yes. And we we wanna do a good job because that's really the only interaction with the product that we're gonna put out there. We're not gonna just put out a phone number just yet. At some point in the near future, we'll either put a phone number or a button that you can just click and just talk to our agent. We're not quite there yet.
Brian Casel:So like your your AI agent?
Jordan Gal:Yes. Yeah. It's it's a weird thing and and Rock Rock has a lot of scar tissue from the checkout product in terms of technical paranoia.
Brian Casel:Mhmm.
Jordan Gal:You know, at at Rally and at Cart Hook on the checkout, we needed technical paranoia. How are people gonna jam in coupon codes? How are they gonna use fake credit cards? We just had to think in a paranoid, you know, perspective. But this is this is also tricky because if you put an AI agent out there whether it's up on the site or behind a free trial that doesn't require a credit card, you are taking a a real risk because hits to the API means something very different.
Jordan Gal:You know, it's it's it's money per minute. And so if someone wants to be a bad actor, you you have to protect against them just blowing up your agent and then the next morning you wake up to a $5,000 bill from OpenAI.
Brian Casel:Right. Yes. So And Yeah. And in that case, in your case of like using it as like a demo to show on your site, you know, with no credit card upfront, no sign up upfront, you're just gonna get a a ton of tire kickers and you're paying for those.
Jordan Gal:Yes. That's right. And and to a degree, tire kickers are
Brian Casel:That's fine.
Jordan Gal:Good for now. Yes. So there's a balance there. So the video that we're putting together, you know, the the way we're doing it is we want we want it to be a video even though it's an audio recording, but we wanna show on the screen what's happening. So there are times when you're just seeing like text on the screen and you're seeing the word being spoken as highlighted.
Jordan Gal:And then at other times we wanna show the calendar view and how a calendar is read and then appointments are created. Then And we wanna show like an SMS confirmation. So there's like there's some stuff to do there. And the second reason, I feel like such an amateur on this front, privacy policy in terms of service. At some point, I was like, oh, we can't use the same one as Rally.
Jordan Gal:There's a whole bunch of different issues. It's not about payments. It's about calling and recording and two parties and all this other stuff. So I I, you know, I hit up that lawyer and that's not an overnight thing.
Brian Casel:Yeah.
Jordan Gal:It took it took a week to get that done. I just got the email from the lawyer today.
Brian Casel:I don't know if I should be like broadcasting this but I've I've taken the bootstrapper approach to terms terms of service and privacy policy which is like you find whatever template out there and you swap in your company name. And I've used like in many cases like the same one across multiple products of mine. Just swap out the company. One Make some tweaks for for some terms that you need Right. Whatever.
Brian Casel:But like
Jordan Gal:I think that's how almost everyone should do it. I think that's generally the right approach and I say that to the lawyer upfront. I go, I just want you to know my perspective on this is that no one will ever read it. It will never come into play. This has only negative impact on the business, you know, so I I kind of I make sure the lawyer knows my point if you want it because I know what's gonna happen and it did happen.
Jordan Gal:What's going to happen, especially around phone, is that as soon as you touch legal, they will come back to you with feedback that will be a negative impact on the product and
Brian Casel:service. Mhmm.
Jordan Gal:And then you have to make a decision on the balance between how strict to be on legal and risk and how much you're willing for that to impact the product. You know, because that that that sucks. It sucks. At at first they told us you can't have recordings. You need to delete them right away.
Jordan Gal:And we were like, no. Absolutely not. You mean
Brian Casel:like your your actual customers?
Jordan Gal:Yes.
Brian Casel:Or Yeah. If you
Jordan Gal:ask a lawyer, should a service like ours keep recordings of calls? Every lawyer will say absolutely not. Huge Yeah. Or don't do it. Absolutely.
Brian Casel:Huge risk.
Jordan Gal:And then you start to poke and prod and show examples and then all of a sudden, oh, we've come up with a safe way to do it that allows us to keep the recordings.
Brian Casel:Mhmm.
Jordan Gal:So I I like knew it was gonna be this funny little battle between someone that I'm paying but they're helping.
Brian Casel:Yeah. Yeah. I mean it is their job to like find the areas of risk and yeah push back on them, you know.
Jordan Gal:Yep. Yep.
Brian Casel:Yeah. Very cool.
Pippin Williamson:How about you?
Brian Casel:I was gonna say.
Jordan Gal:What do you got going on this week?
Brian Casel:You know, this week like today feels pretty good because I finished probably three significant projects that were on my plate. These are like I think of them as like big blocks of work that take up significant amounts of time, multiple days And these are shipped. And I've moved moved on and I'm moving on to the next thing. Like right now, today, I'm I'm like in between those big projects and about to start the next project. So two of those projects are in Clarity Flow.
Brian Casel:One of them is a client project. And it just like there's just that mental transition state that I I it's sort of a love hate relationship. It lasts about a half a day to a day where it's like, okay, that's done. It's like a huge check mark on my I like to think of like a Kanban board. That's a big card that I've just moved into the done column.
Brian Casel:Okay. But then, like as soon as I do that, I need a little bit of time. Like I I took off work a little bit earlier this week and I'm, you know, hanging with the girls and and doing some hobbies and stuff and I'm starting to and it's like I know exactly what I'm gonna be working on next but there's still this like mental state where it's like, is that the right thing to work on next? But what if I work on this next or or that next? Okay.
Brian Casel:And and it's and it's a little bit of a decision around like, well, wait a minute, like, don't don't get into something because whatever you start, you know, is gonna take it could it could take several weeks. So but anyway, like the the two things on Clarity Flow, one is product related. So we are starting we're we're we're now breaking ground on a very big new feature in Clarity Flow. Something that customers been asking for like like requesting forever and I've been mostly saying no to the feature and I'm now I'm cracking. I'm like, no.
Brian Casel:We we should just do it. Let's do it. Okay. And so my role in that in that project is I've gone back and forth on different ways to execute big features in Clarity Flow. One is I just write up the specs in in linear, know, in detailed specs that I'll that I'll give to my developer.
Brian Casel:But then after she's done, I will build most of the UI component. Like clean up the UI components. She'll she'll put in the functionality but then I'll make it look polished and ready to ship. This time, I did all that work up front or most of it up front. Like the views, the components, the the There's a lot of new interface stuff that we're gonna need for this new feature.
Brian Casel:And I put a lot of that in place and I wrote multiple issues in in linear. Super detailed. Get it I'm basically queuing her up for like at least five or six weeks of of her full time focus on this feature. So I spent about three four days on on that stretch of work. And so now it's now it's in her.
Brian Casel:Now, the ball's in her court. She'll be working on that for the next month or so. And the other one is sort of a marketing The the rest of the projects in Clarity Flow that I'm that I'm working on are marketing related. And this is another one where it's like, I don't know about you. I find that like, there's a bunch of projects that need to get done.
Brian Casel:Most of them are gonna be my projects that I completely do myself. But a couple of them are things that I'm gonna hand off to my team. Like that like that feature. She's gonna be working on that. This other project is we're we're migrating our help docs from our sub domain on help scout into our main domain to make them like part of our actual marketing site.
Brian Casel:We can get into that. But that required me first to design and build the section of our marketing site that's going to house our support docs. So it's a little bit of, like, design and code work in our static CMS. We've got a searchable, like, knowledge base that is now built into our marketing site. So I I set that up.
Brian Casel:I designed and shipped that functionality. And now, Kat on my team is gonna be tasked with actually migrating all the docs and editing them and doing some things.
Jordan Gal:Can I ask what you're after there in terms of benefit? Is it is it SEO? Is it
Brian Casel:It's SEO. It's two things. It's it's SEO and it's we're the I'm I'm starting a big effort on Clarity Flow to make the whole marketing site just much more product focused and we're gonna be removing a lot of the on the unhelpful content, if you will. Okay. Okay.
Brian Casel:Interesting. Just making just just getting the focus so so much more squarely on like, this is the product. It's this type of software product that you that And here's what you can do with it. And I think that a person who Our help docs, which a lot of them have videos and very detailed like how what you can do with the product and how you can do it with the product. Those really should and they often do serve a dual purpose.
Brian Casel:They help our existing customers and they help sell new customers and look at what you can do with the product. You know, I think that there are a lot of customers especially in Clarity Flow who they spend a lot of time to dig around our docs and our videos and learn about like, what can I actually do with this and how does that actually work and does it actually work the way that I think it should work? And they're digging into that stuff before they even start a trial. So so why? Or at least on the first day of their trial.
Brian Casel:They're they're checking that stuff out. So I think that we I like one of one of my marketing realizations now that I'm starting to learn is at least and it depends on the space of your product. But in in my case, it's I think we we tend to think that like people come to our SaaS marketing site and they don't need much in order to start a sign up. Like like sign up for a trial. You just need to sell them on a headline and a benefit and a pain point and like Mhmm.
Brian Casel:Okay. If they identify with that, that'll be enough for them to
Jordan Gal:Because there's nothing to lose. It's not a big deal. Just create an account or
Brian Casel:Yeah.
Jordan Gal:I was gonna ask you what
Brian Casel:you I think that I think that that's wrong in a lot of cases. Not all cases but like at least in because I I find that the customer wants to spend a lot of time digging into the details before they are sold on the idea of like, okay. It's worth my time to actually proceed with a trial.
Jordan Gal:This is the thing I've been looking for. Yeah. I was gonna ask you if you had a way to describe the way the site is currently compared to what you're describing it as going toward, which is very product focused and pulling these things even from a different domain, pulling it all the way out front to let people do the research that they want. Yeah. Yeah.
Brian Casel:Some of it like like a lot of a lot of this is not implemented yet. So, you know, it's not gonna be a major change visually. The style, the design is all gonna be the same. But the organization of the content and the organization of the copy and the focus of each individual page is gonna be different. I think overall, we're gonna have fewer pages.
Brian Casel:We're gonna be killing and redirecting a lot of pages. We are going to yeah. I mean, that's I think yeah. Like like the I think the help doc bringing the help docs into the main site is going to essentially replace the need to to have multiple product feature pages. So like we right now we have a home page and and then that links off to like like maybe five or six pages dedicated to specific parts of the product.
Brian Casel:These are like product marketing pages. These are not help pages. There's marketing. They're like versions of our of our homepage. Yeah.
Brian Casel:And then in in addition to that, we've got a lot of like comparison pages. We've got we've got like reviews pages. We've got all these and then we've got the blog. But the reality is most of most of that stuff is unnecessary and bloat and pages that nobody ever even wants to click to or link to. But the help pages, the detailed tutorials with videos, people do spend a lot of time on these pages and they find them on Google too.
Jordan Gal:Mhmm.
Brian Casel:It's not Like logistically, it's like why why duplicate work but it's also like I don't know. I think people people actually want more details than we give them credit for.
Jordan Gal:Right. The difference between a marketing page that talks about a specific feature or category features and the way we make that pretty and we don't dive into too many details and we'll write a sentence on how something that you can accomplish with the product. The difference between that and a help doc that digs in into the real real details, that's a pretty interesting thing to note. Like if, you know, we've talked over the last year like what the hell works in marketing? How are people buying?
Jordan Gal:What is happening out there? And it feels so chaotic. That's kind of an interesting tidbit to look at and say, alright. If that works better, then that tells us something about how people make their decisions.
Brian Casel:Yeah. I think a lot of people make most of their decisions on your homepage and no other pages. And then and then But if they do spend up time on other other pages, they're probably looking for like deep dive details. They they don't want like a second homepage or a second like
Jordan Gal:Right. Or four homepages for each feature category.
Brian Casel:Yeah. And that's kind of what we have now is is just like a lot of versions of our homepage, you know. Okay. And you know, another thought that comes to mind here is like, think about like developer tools, developer products. Yes.
Brian Casel:It's true that like developers are a different animal and and and they consume products and you sell to them a little bit differently than other types of customers and types of products. But I do think that there's something to be learned from developer products. Look at so like I think that the the big that like the best best practice if you are selling a tool to developers is you have to have best in class just world class documentation. Look at the I I think of like the Tailwind CSS site, their docs as like the gold standard.
Jordan Gal:Yeah.
Brian Casel:You know?
Jordan Gal:That's that's a lot though. Like that audience is unique because and they think uniquely, they they read uniquely, they their peer circles are different, Their decision process. I think that's kinda like the most extreme version of you must give me a lot of detail.
Brian Casel:Yes. But what I'm saying is their docs, their website is so easy to navigate, so easy to search and find the answer to. And the content itself, the the text, the the images, it's all so easy to consume and easy to to to go down these rabbit holes. That's what developers do. I think that other customers do that too.
Jordan Gal:Not In in their own way.
Brian Casel:In their own way. I'm not I'm not talking about like technic like they're not gonna read code tutorials like like someone on a on a Tailwind CSS doc site would. But they do want that because oftentimes they're switching from some other tool. They need a good reason why it's worth the effort to switch from another tool. It has to functionally work a little bit differently and better in some ways.
Brian Casel:So they're gonna dig around in the docs or whatever videos they can find to say like, oh, that that has the little function that I've been looking for. Maybe it's worth the switch, you know.
Jordan Gal:Very cool. I'm excited to see how how it works and I'm excited to just the fact that our website is so new that we don't have anything. I'm gonna try not to make mistakes that we need to go back on.
Brian Casel:Mhmm.
Jordan Gal:We're definitely launching with a landing page and not much more, but it's not bad. And the design, I think, is coming out great, and that's really exciting. I have this maybe I don't know if I talked about it last week, but I've been thinking about it. New competitors are launching. I think I talked about that a 16 z article that came out about voice agents, and you look at it and it's like, it's a bit thin in our category.
Jordan Gal:And I'm I'm assuming it's gonna get filled in. So I just keep an eye out. I follow a few Twitter accounts that talk about AI. I I'm subscribed to this newsletter about AI companies. It's when I tell you every day, it's seven days a week.
Jordan Gal:A $115,000,000 raised, $44,000,000 raised between these companies, $280,000,000. It's just relentless.
Brian Casel:I'm on the the Ben's Bites newsletter. Are you on that?
Jordan Gal:Yes. Yes. That's one of them. Yep. Yeah.
Jordan Gal:So it's it's pretty intense, and I'm kinda preparing myself for that level of competition. And recently, one launched. And what I found myself doing is like, I was gonna be disappointed either way. Like, when I when I okay. I see it.
Jordan Gal:I read about the competitor. I'm like, alright. That's kind of pretty firmly in our space. And I go to it and I'm expecting like one of two things. It's either not impressive, in which case my reaction is based on that.
Jordan Gal:It's like, oh, whatever. Another you know, like nothing to worry about kind of thing. Impressive. And then you get that weird dark feeling of, oh, shit. So I've I'm almost I'm just waiting to be I'm waiting to come across a competitor that's really impressive and to get that sinking feeling.
Jordan Gal:It hasn't happened yet.
Brian Casel:What what do you think makes it impressive to you? Is it like just the the overall, like, design, look, and feel? Or or do you see some indication of like, oh, they have a lot of customers?
Jordan Gal:Yeah. Okay. That I mean, that that's definitely one of them. But so so many agents are so new that, you know, they just don't have a lot of customers. Yeah.
Jordan Gal:And so I think that's a good question. The thing that would give me that sinking feeling and has in the past in other contexts and other companies and whatever else is not so much money raised that's a little bit of a factor just because you have to deal with the money. So someone raises $50,000,000, you kinda roll your eyes like, oh, now we get now we get it. We're gonna deal with that. They're gonna advertise.
Jordan Gal:They're gonna be all over the place. And so that's kind of that can be frustrating in that way regardless of how good or bad the product is. Mhmm. You just have to deal with it. That that's what we had with Bolt, which was a terrible product.
Jordan Gal:But to raise $900,000,000, you're like, they're gonna be in every deal. Their salespeople are gonna be emailing people. You just have to deal with it. So that that's one factor, but that's not the most important factor. I think the thing that gives me the biggest sinking feeling is positioning.
Jordan Gal:If they are describing things properly
Brian Casel:Mhmm.
Jordan Gal:And highlighting their features in the right way, that worries me because then I'm like, oh, they got it right.
Brian Casel:They it's like they get it. Yes.
Jordan Gal:So if it's beautifully designed, that's one thing. If the product is impressive, then the customer list, maybe the money raised, but the thing that worries you the most is, shit. They got it right.
Brian Casel:Mhmm.
Jordan Gal:So that that is the thing that I'm hanging on to right now where no one has taken the angle that we are taking on the product itself and and the positioning of that product and how technical or not technical, how easy or not easy, the pricing, the set of factors that plot out their exact position to attract that type of customer, no one's there right now.
Brian Casel:Mhmm.
Jordan Gal:So that's that's me that's me being happy about that and just waiting for the shoe to drop. Like, uh-oh. It's it's gonna happen eventually. Yeah. So Rock made a good point the other day.
Jordan Gal:I expressed this to a few people and Rock was like, Jordan, that's gonna be us.
Brian Casel:Like people are gonna look at you
Jordan Gal:and like,
Brian Casel:oh, shit.
Jordan Gal:And I'm
Brian Casel:like Yeah.
Jordan Gal:Yes. I I forgot that. Yep. That's exactly what we're going for actually.
Brian Casel:That's true.
Jordan Gal:But for some reason, you kind of view it That is
Brian Casel:a really really good point. Yes. You know, the other thing that I that I think about or like for me, I probably the reason why I don't spend a lot of time thinking about or looking at the competitors very much is I just assume that there are competitors in anything that I do. But you know, going back to why you chose this market. You you chose a market that is huge.
Brian Casel:Like, it's massive. And so I I'm always of the mindset of like, the like, I chose this because it's big enough. It's it's big enough for for me plus other competitors to Yeah. To be fine. Know?
Jordan Gal:I think I've I know
Brian Casel:it's different game in the VC game. Like I'm
Jordan Gal:cool it a little bit. I'm like, yeah, cool story but you really really wanna be out in front as number one because you just win so much of the market from that. Yeah. So as long as you're not established, you're not comfortable. And then maybe once you're established, you're still uncomfortable in a different way.
Jordan Gal:But the opportunity to become number one and then get the partnerships and the integrations done and, you know, just that leadership position makes everything so much easier. So that's kind of what I'm after and I definitely drink the cooling after raising money. You're like, yeah. That's how you do well in this version of the game. So normally, I would say yes.
Jordan Gal:There are definitely a thousand customers out there. It doesn't matter what competition is out there and therefore I can build a business. In this case, I'm a little this is this is where raising money changes that mindset.
Brian Casel:Yeah. And also your decision to to do an AI product like this, like so much of the game is being early. Right? And Yes. And and and part of that game is like being first, being the first one that people talk about.
Jordan Gal:Yeah. Or at least the first one in in that specific position in the market. There are more established call center AI products that are already series b and beyond and they're that's a different thing. So it's just this spot that I I want. Yeah.
Brian Casel:Mhmm. A question came up on Twitter. This is also a thing that I was talking on on Jessica Malnick's podcast the other day, which that was a show all about AI. Okay. I don't know why.
Brian Casel:Tweet
Jordan Gal:about that. That sounds cool.
Brian Casel:Yeah. I don't know why I was on a panel talking about AI because I feel like so far from an expert. But but I I think it's interesting. I was just talking about I like I I What I think is interesting to observe at least is like how the the places where I am heavily using AI day to day and the places where I want to be using AI but I'm I don't think it's good enough yet. Okay.
Brian Casel:And one of these things is I I was just describing how we have a project going on where we're migrating a bunch of our help docs out of one system and into another system. And so that involves, I don't know, 75 plus different pages of content in one system, each with multiple fields. So there's a lot of like highlight everything here, copy it, paste it into this other CMS system over here. But while while you're at it, let's let's make some edits and adjustments to the content. It's like percent 10% like thought analysis work and 90% just data entry, copy and paste.
Brian Casel:But it's also like between multiple browser tabs and multiple tools and multiple page refreshes and click this button multiple times. Mhmm. And so that's the kind of like sort of like low level
Jordan Gal:Like tedious.
Brian Casel:Tedious work that like my my first thought is like, okay, someone's gonna need to do all this work. My first thought is like, maybe I'll just hire a VA, know, to to take care of that. Like, you know, because the only other person on my team who who is involved in this is Kat and she's our customer success person. Just, know, higher level. She she works with customers.
Brian Casel:She's strategic. She does some marketing work. So I I don't really want to task her with that type of work. I feel like it's below her a little bit. It's not a really good use of her time.
Brian Casel:I'm not gonna be doing that work. So my first thought was like, let me hire a VA for like a temporary like one week project. Give you some instructions, just copy and paste and that'll be that. Then I was like, but it does it does require a little bit of strategic work that Kat really should do. Some like editing, some rewriting, some re organizing, and and some thought work into this.
Brian Casel:So I want her involved in the project. I was like, there should be a a case for AI here. Like I should I should be able to use a tool to to do like a workflow across multiple pages, multiple tools, multiple page refreshes, copy and paste, all of that. But Mhmm. There that tool does not exist yet or that capability does not exist yet.
Brian Casel:You know?
Jordan Gal:Kinda. I've I've seen two products over the last few weeks that you can train based on what you're doing on the screen.
Brian Casel:Mhmm.
Jordan Gal:So it's basically like, watch what I'm about to do. Click here, pull down tabs, select this, hit enter, wait for it to refresh, type something out, copy, paste, go to this screen, change tabs, and it it can be trained on your actions on your computer as opposed to something separate outside of your machine that it goes to a server and it learns something and it gives you feedback. So I think all those things are close.
Brian Casel:I think they are close. But here's another trend that I'm noticing all the time now with all these AI tools. Okay. They are over promising and under Sure. Under delivering.
Brian Casel:Like big time.
Jordan Gal:It's it's a big in that way. It's
Brian Casel:I see it every day with developer tools. With I mean, every single day. Like but also what you're talking about. I I've seen those as well, like, it on this on on clicking around. And and I see that and I'm just skeptical because it's like, that's that's pretty cool, but I'm just thinking about the the amount of time that I'm gonna spend troubleshooting that.
Brian Casel:Like, why didn't it do it correctly and this or that? And I I just don't think it's there yet. Like, if I think about the developer tools or even ChatGPT itself, so many of them are marketing themselves as like chat with your code base. Mhmm. GitHub Copilot or Cursor or any of these has access to your entire project, all the files in your code base.
Brian Casel:It should it should know. If you ask a question, if if I'm working in this one controller over here and I ask it a question, it should be able to access my routes file and these other models and these and and these other files in my code base to know, okay, those definitions and those exist over there. Let's help me inform my answer to Brian's question here. No. It does it does not work.
Brian Casel:Like, it and they advertise it like that. They're like, chat with your code base. Like, it it's plugged into your whole code base. Like, no. It's it's it actually does clearly, it's not aware of whole parts of my application that exist in these other files, but it it did not take those into account when it gave me an answer.
Jordan Gal:You told me it knew but it didn't.
Brian Casel:It it just clearly does not. I and ChatGPT has the feature where you can get you can attach files to it. Like, you can attach a spreadsheet, attach a PDF, and give it a prompt and say like, read these files and then tell me what you find with an answer to this question. So the other day, I gave it, I think like four file attachments. You can put multiple file attachments.
Brian Casel:I put like four along with a question. Like reference these four different documents and tell me the answer to this. And just based on their response, like, clearly, it read like the the first document and it just ignored the other three. You know?
Jordan Gal:It's a slacker like everyone else.
Brian Casel:Yeah. Like, okay. Like, I I get that I'm asking the computer to do a pretty incredible thing, but but you are marketing it to me like it's supposed to be able to do this and no. It's not doing that.
Jordan Gal:So I think this I would I would blame this on the the marketing arms race.
Brian Casel:Yes. Exactly.
Jordan Gal:You you had no choice but to overpromise or your product in comparison looked ridiculously behind. Yep. And and I I don't know the name of the adoption curve where it's like the big spike of initial excitement and then the novelty wears off and then there's the trough of sorrow, the wiggles of hope, a little bit more success and then all of a sudden like, you know, the promise is fulfilled. So I think we're definitely there where the promises were way, you know, overdoing it. And now there's some novelty wearing off.
Jordan Gal:But I I'm pretty sure it's it's gonna keep climbing.
Brian Casel:So Oh, there's no doubt that like it's the the curve of advancement is out of control so fast and that that's what makes this whole thing so exciting. Like, think about where we are today and where we're gonna be a year from now. Think about where ChatGPT was a year ago. It's incredible. Mhmm.
Brian Casel:You
Jordan Gal:know? Yeah. And I'm I'm I'm learning more about this. When I heard the term prompt engineering, I really I really didn't know what to picture my mind around what that was. And as our team learns more about this that, you know, I'm I'm basically asking to be educated by the engineering team so that I have a better understanding.
Jordan Gal:I can describe it more properly. I think about how to market it. I could, you know, not sound like an idiot on podcasts and and so on. This podcast in particular, I'm perfectly fine sounding like an idiot. So I'm gonna talk about one one area that I learned about this week that gave me a good a better understanding around how to improve the quality of responses when you're trying to accomplish something.
Jordan Gal:So I learned about the diff the difference between system prompts and user prompts.
Brian Casel:Right.
Jordan Gal:And Yep. And that was very helpful for me to to just understand that it's it's not about, like, the words that you're asking. It's it's also providing the larger context to the model and saying, this is what you need to know. This is what you need to use as your foundation of information. This is what you need to ignore.
Jordan Gal:This is what I want it to be like. This is my goal. Right? Those are all the system prompts. And then the user prompt is, look into my docs and give me this.
Jordan Gal:Mhmm. So so those two things combined, what what we've been talking about internally is differentiation and and building up value over time. And I didn't really quite understand how prompt engineering fell into that, But our ability to improve over time is one of these things where, okay, maybe you can build a product just like ours in a short amount of time. You can't shortcut the amount of pain and learning involved in how to set up the system prompts to make success in the individual user prompts much more likely. Yeah.
Jordan Gal:So if someone says, actually, I changed my mind next Thursday isn't good. Can we do the following Thursday instead? So that is a user prompt that goes into the system. The system prompts that we build into our model then make it much more likely that the system will understand what the following Thursday actually means instead of giving a a bad response.
Brian Casel:Yeah. I like that. That that makes a lot of I
Jordan Gal:think a lot when I hear people say it's not good. I always have in the back of my mind that that's not that it's user error but there's a lot that goes into making it successful. So a lot of these larger companies that are hiring prompt engineers, you're like, oh, a what? You're gonna hire someone who types a slightly better phrased question? Like, I don't I didn't understand it.
Brian Casel:Yeah. I was you know, you're right that I feel like I'm very far behind the curve on the whole idea of prompt engineer. I know what you're talking about with system prompts versus like user prompts or whatever the front end prompts are. But like you know, like even in my in my chat GPT account, like I I put in some baseline. They have a feature in there where you can say like, I generally work in Ruby on Rails.
Brian Casel:Right. And so like when you're given when I'm asking about code, just assume that it's a Rails project.
Jordan Gal:Yeah. Is that what's called memory?
Brian Casel:I I'm not really sure. Maybe. Okay. Might might be
Jordan Gal:a slight feature, but but that's what
Brian Casel:in in your what you're describing is is like building an AI product. So I'm sure like using the API, can feed it like system level prompts and then Mhmm. One of the So I was on this podcast the other day, Jessica Malnik's podcast and I was on with with Matt Pritchett who who runs a tool called Quilby which is really interesting. I haven't really used it but but I know that they've been launching it over the past year or so. And it's it's one of these like AI writer tools And like my hope for it was like or at least in general with AI was to be able to use AI to help me produce more personal content that I might put out on my personal Twitter or my newsletter or my blog.
Brian Casel:But I've never even come close to feeling comfortable like actually publishing something under my personal name that was like AI generated. Okay. You And I've tried multiple times. Like like one time I was on a plane on a on a flight and I had an idea for a blog post. So I just put down like maybe like 10 bullet points of what I wanna include in this thing.
Brian Casel:Then I fed that to chat GPT. Was like, can you make this a blog post? And here's copy and paste like three of my previous blog posts. Like, make it sound like me. You know?
Brian Casel:And it just did not. Yeah. You know. Yeah. Not yet.
Brian Casel:And that's probably just too basic. That's that's not like a prompt engineering thing. But the thing that I was hoping for, I don't know if tools like this can do it, but I want a a much more limited AI chat GPT or or some kind of Like a a far far limited thing. Like per Intentionally To what? So even though I told it like, hey, these are the bullet points that I wanna These are the points I wanna make and here's a sample of my writing.
Brian Casel:I I don't want you to come up with any new topics. Don't come up with any new points. Just use my points. Just write them so that it's like a readable blog post. It still went out and like added more content to my article.
Brian Casel:Or it's still extended sentences like an extra sentence or two with something else that like, no, I just don't I don't want that. And and and it also still just doesn't sound like me. Yes. These are readable sentences, but they are not sentences that sound like my voice because it's from my personal blog. Right?
Brian Casel:Even though I tried to train it on on that. So what I want is a much more limited thing where it's like, it literally does not have access to the rest of the Internet. It only has access to my blog, my newsletter, archives, maybe like archives of this podcast transcripts, and like, that's it. And that's all it knows. I realize it's gonna be very dumb.
Brian Casel:Like it's not gonna be able to generate
Jordan Gal:It's not dumb. It's specific.
Brian Casel:It's it like, I don't want it in some ways just for this person just for this use case of like write my personal blog, I still want the personal blog to be my ideas, my bullet points. I so I don't want it to generate content for
Nathan Barry:me. Right.
Jordan Gal:Right. Don't don't get too creative on me.
Brian Casel:Don't just don't be creative. Just But I I would like it to take care of the legwork of writing a clean, easy to read blog post. Yeah. Like, I don't wanna do the polish work. I just wanna get my ideas out of my head and Yes.
Jordan Gal:And published. Make it as a draft and then let me just review and click one button.
Brian Casel:Let me give you like a super super raw rough brain dump of bullet points and and then like publish it. Something that I could be proud of that actually sounds like my voice. And Yeah. Because it's only trained on me. Like, I maybe there's some way to do that.
Brian Casel:I just haven't had time to, like, find out how to do it.
Jordan Gal:I don't think it's far at all. I the, you know, the what's the term? Oh, just agents. That that that is the term I hear for this type of thing. Mhmm.
Jordan Gal:And, you know, people can't help themselves. They they go sci fi on it and they'll say my agents will be talking to your agents and they're gonna be creating agents. Right. Come on. But in reality
Brian Casel:take over the world.
Jordan Gal:Yeah. In reality, it's just these very purpose specific set of agents and and that I don't I really don't think that's far. I think there's a personal assistant type agent that's coming. Mhmm. There's still, you know, silly things that we do that are a giant waste of time.
Jordan Gal:Like, the ability to just open your mail and just scan it.
Brian Casel:Oh, yeah.
Jordan Gal:Just just just help me, man. You know, that that that's really what we want.
Brian Casel:Oh my god. Do all the shit in my life that I don't wanna do. Like I had one
Jordan Gal:of those moments yesterday. God damn it. You know, it's like I go my three months without opening my mail.
Brian Casel:Me too. Sorry.
Jordan Gal:Sorry, everyone. And then and then I bite the bullet and I just open all of it at once. And when I tell you the first piece of mail, the first time look at this. Look at this. This this yeah.
Jordan Gal:I'm showing my stack.
Brian Casel:That that looks like my counter behind me.
Jordan Gal:Got a damn stack. Yeah. The first one I opened maybe I should have known not to open the IRS one
Brian Casel:first. Oh, yeah. That that gives me so much stress. Like like, there's a there's an envelope that's from the IRS. It's sitting on the counter, and I I don't touch it for, like, weeks.
Brian Casel:Yeah. I'm just like, I don't wanna deal
Jordan Gal:with The amount due immediately, 8,900. God damn it. And I know it's wrong. I know it's wrong. I have to go to my account, I to stress out for two days and they come back to me and say, we paid that in 2023.
Jordan Gal:Don't worry about it. Anyway.
Brian Casel:I got a letter from the IRS the other day to state like, we've received your request that you made eight months ago. And but you missed a detail and you have to resubmit something. I'm like, I don't even know what it was eight months ago. What are
Jordan Gal:you talking about?
Brian Casel:Like, they they sent me a a mail a thing in the mail to
Jordan Gal:to tell
Brian Casel:me this. I'm like, what?
Jordan Gal:Okay. Well, we we we digress. Here's here's what I wanna talk about. More AI. But first, I gotta give a shout out to a new person I follow on Twitter.
Jordan Gal:My man, Cody Schneider. This dude is on god level amounts of zen. I don't know what is happening in this this person's brain. He is an idea machine. Follow this man.
Jordan Gal:There's so many good ideas. I keep I keep pasting them over into into our Slack. Eventually, everyone's like, what is up with this guy? There's so many freaking ideas. So Cody Schneider runs a product called Swell AI.
Jordan Gal:And I think this I
Brian Casel:think I just heard him on a podcast somewhere.
Jordan Gal:Yeah. He he's been on a few podcasts too. Yeah. This thing is where I think small software companies like us, like we have to go up this learning curve because there are there is now a way to take one or two people's marketing efforts and produce an amount of work that that 10 people would be required for. And that feels like an absurd thing to ignore.
Jordan Gal:Absurd. If we limit what one or two people can do on marketing and not use these like amplification products. So what Swell AI does for example is we could take this call, this podcast, we could take the video of it because we're on video and we plug this thing into Swell AI and it will amplify. It will create 40 different video clips with the subtitles ready and formatted properly for TikTok, Instagram, Reels, whatever else. It'll schedule 50 tweets and you can go in and and, you know, accept or decline whichever ones you want or don't want or schedule them.
Jordan Gal:And this is what I what I told Sam who is, you know, my basically my go to market everything on our side. We we we we have to learn this. We have to be able even if the quality is not as high, it will not be. Forget if. It will not be as high of quality as if we did everything ourselves the old school way, but the quantity having a quality all its own mindset, I think is required.
Jordan Gal:So I'm looking at my boy Cody who comes up with these amazing ideas. I'm looking at his software product and I'm looking at David from Jenny AI, that blog post that I'm kinda looking at as like this North Star. It's the combination that that's what that's what we're gonna do.
Brian Casel:I think I I like I like where you're headed with this and I've I've wanted to do this for so long to like have a pipeline of content that that is just like I create one thing and then send it out as tweets and LinkedIn posts and newsletters and Yeah. Whether it's people, whether it's AI. But I feel like the thing that The the key thing to make that work is you have to have really good source content for the first piece. Right? Like like if we if we actually cared about this podcast and made this like a business enterprise like content thing like Right.
Brian Casel:I feel like we would have like a lot of source like we could take each week's episode and and it it that could we're not doing this. But like we that that could turn into like like halfway decent streams of tweets and LinkedIn posts and newsletters based on what we actually talked about here on the podcast. So I feel like if a company's gonna gonna use something like this like a Swell AI, like, you still need to have probably the founder, I think, or someone high level
Jordan Gal:Someone good.
Brian Casel:Like, doing a high quality podcast or or YouTube channel as like the primary source. And then everything else is
Jordan Gal:What I'm repurposing. What I'm hoping I I agree with you a 100%. What I'm hoping is that that like chicken and egg issue is solved with the motivation to create the initial good content. Being there because look. If I were to start a podcast for the new product and then went out and did all the work required for a podcast Mhmm.
Jordan Gal:And then did episodes and then all we did with it was publish a podcast episode, tweet about it once or twice, and send out an email about it once or twice. It's almost like not enough motivation. I just don't believe that's gonna make that much of an impact. So it's not motivating to do the initial work. I'm hoping that the amplification opportunities provide more motivation to create better source.
Brian Casel:I mean, I I also sort of agree with that now that like it even even amplifying it and even just content in general is not gonna do a whole lot in terms of like gaining new exposure. You know, and I I think that a lot a lot of these tools like this like because I I I have used these for years. But even before AI, like there there's there's always been the idea of like scheduling social media posts. Like tons of tools that have been around for decades doing that. Right?
Jordan Gal:Mhmm.
Brian Casel:For the most part, they those scheduled repurposed social posts do not do well. It The the ones that are actually personally from a person with a unique point of view, something controversial or something super interesting or something get that gets a reaction. That's that's what actually goes whatever viral like and you know, but the the the repurposed, the the formulaic headlines, the the click baity stuff, I think that that is getting less and less effective these days.
Jordan Gal:Yeah. I I agree. I'm not sure if I'm not sure if there's an issue there between personal and business though. Because I I don't wanna hear an individual person's like regurgitated, rescheduled, whatever.
Brian Casel:But from
Jordan Gal:a business that's offering me something that I'm gonna be interested in, I
Brian Casel:But I feel like in business even more so like Even more so. We we tune them out even more than people.
Jordan Gal:Sure. But I think what works there is just ubiquity. Just Branding. Yes. It's almost it's almost like a b to c product that you need to see 10 times before you're like, alright.
Jordan Gal:I guess I'll go check this thing out.
Brian Casel:But then it then the question is like, okay. I buy that for consumer products. I don't I don't know that I buy that for b to b products.
Jordan Gal:I don't know either, but we're gonna find out. Because that's that's how I that's my approach. That's how I think this product is best distributed. Yep. Yep.
Jordan Gal:A slightly indirect approach. Right. People on Instagram reels and TikTok are not there for business, but there are a lot of ads for business. It's a it's a normal expected thing. I think that environment plus ubiquity is what will give us an opportunity to to get the the actual offer in front of people.
Brian Casel:You know, this I this sort of gets back to where I'm headed marketing wise with with Clarity Flow and everything. I just I just think that b to b, especially b to b SaaS is so much so so simpler is is a misleading word. I'm not saying simpler like it's easy. I'm actually saying simpler like it's harder to to market b to b SaaS. But but the way that the the way that customers buy b to b SaaS is it's a much simpler approach.
Brian Casel:They they tune out the bullshit. So we can't market SaaS. We can't market b to b SaaS like their consumer products, and we also can't market them like their content products. You know, and that and and I think that a lot of, like, SEO advice and agencies and consultants will convince you, you gotta do all the SEO content things just like a info product site or a content site or a news site would. But b to b, people are searching for product software.
Brian Casel:And like, you know, and and then they they might talk to their business colleagues and about like which software do you use for this or that. And then they recommend and other than that, it's okay. Maybe there's like a there's there's also like the like the sales play of like going into companies and like doing doing the sales cycle but Mhmm. I the idea of to me like the the idea of like winning through Instagram ads or TikTok or branding or viral. It's it's hard to buy it.
Jordan Gal:You know? I I hear you. But I think that is it goes along with with our situation. Awareness is super important. Right?
Jordan Gal:Because the search volume isn't there yet. People aren't actively looking to solve this pain. They're just starting to hear that it's that it's a pain that's solvable in this way. And so getting out directly in front of them, but but using those channels almost to point out the pain, to identify with the fact that, oh, yeah. Other people have this problem also.
Brian Casel:Yeah.
Jordan Gal:That that's generally what what I'm thinking. So it is it is it is user generated content based advertising. Mhmm. A whole bunch of word mashed into one. But you know what I'm saying.
Jordan Gal:The the ad doesn't feel like an ad. The ad feels like someone just like you who had this problem and is talking about it.
Brian Casel:You know, this is sort of ties into something I've been tuning into a lot of lately. Do you know do you follow Matthew Giovanisi? He runs a site called MoneyLab. He's had it for a while. Just really interesting like, I I don't know him but personally, but a very solid content creator, really solid SEO practitioner.
Brian Casel:He he runs a site called Swim University, which is a a long time like content site for like swimming pool Okay. Maintenance or whatever. So so they'd like won the SEO game in in that space through like content and affiliate products and digital products and things like that. And so so he, you know, he he create he has this other like kinda side business called MoneyLab where he talks about how he runs online businesses. He's been doing it for like for a while.
Brian Casel:So I really like his stuff. And he's he's got a podcast where it's just him talking solo, just kinda brain dumping these ideas. And so he's been sort of on the forefront of his whole business is based on on SEO, and it has been for over ten years. And and so I kinda really trust his opinions on SEO, and and he's been very, like, kinda bleak about, like, where it's headed now with the introduction of AI and how like look just look at Google. Like the front page like the top half of Google is not just sponsored spots anymore.
Brian Casel:It's now it's AI from from Google.
Jordan Gal:It's the whole thing is so weird.
Brian Casel:So it's like what happens in a world where Google as a thing goes away? Like, the company is not going anywhere, but I'm saying like Google like SEO as a channel. Think about how many of our businesses depend on that being a thing. And and so and I don't think this is happening this year or or even next year, but some sometime in the near future, like, there's going to be a future where when people have a question or when people are searching for something, they're they're not going to Google. They're just going to type into their iPhone or or whatever device or tool they're using, and they're gonna ask the question and and some sort of AI service is going to respond.
Brian Casel:And I mean, next week, Apple is about to announce their integration with OpenAI. Like, it's gonna be part of Siri. So like, there's going to be a world in the very near future where like, people are not Googling for things anymore. They're just asking. Mhmm.
Brian Casel:And getting responses from whatever they're holding in their hand. You know? And what like, my question is, like, what is that gonna mean for us? Businesses that depend so heavily on Google for visibility and exposure and and access to customers,
Jordan Gal:you know. I I don't know. I don't know. There there might be a lot of opportunity in that transition.
Brian Casel:Yeah. I think there's gonna be something that replaces it. I don't know what that's gonna be. Like, I think the the thing that that most people tend to start to think about is like, okay. Well, if we have to start relying less on Google, maybe we need to start to build up our personal brand on YouTube because people trust people.
Brian Casel:Mhmm. You know, a more human approach. A more I happen to think there's gonna be a more more of a referral based approach and that's why I'm investing heavily in like customer success because the best customers are referred from other customers, you know. Yeah. So that's and, you know, lower volume but higher quality subscribers.
Brian Casel:That's not the answer to replace Google as a channel but but I'm just saying like the at at some point, all these businesses are gonna have to it's gonna be a new world and it's coming sooner than we think I think.
Jordan Gal:Yeah. The the only comfort is that most people are much slower to adopt than we are. So that that will tail off over a longer relatively long period of
Brian Casel:time. Yes. But But just look at look at how on you the the current behavior from the biggest companies, Apple, Google, Microsoft, Amazon. Like, look, they are doing very unusual things. Like, Google is completely redesigning their Google search results page.
Brian Casel:That's the core of their whole business and they're completely messing with that with AI. Mhmm. Apple is about to announce a a huge partnership with with OpenAI probably. Like, they're this stuff is gonna go mainstream a lot quicker than we think it is. Like, once once it's yes.
Brian Casel:Last night, was watching the NBA finals. There's there's like multiple TV commercials from Google heavily with Jay Z endorsing it like promoting Google Gemini. It like dedicated TV commercials on the NBA finals showing consumers, hey, AI is here. You could use it now. You know?
Jordan Gal:Oh, boy.
Brian Casel:I don't
Jordan Gal:know. One one one year at a time.
Brian Casel:Yeah. Yeah, bro. Long times.
Jordan Gal:That's it. That's it. I I told my team that I almost completely screwed up the difference between system prompts and user prompts. So they're they are ready for this episode to be published. They they wanna hear if I got it right.
Brian Casel:I wanna hear that right now.
Jordan Gal:Wasn't sure when I started talking, but the pressure helped me remember.
Brian Casel:I like it. I like it, man. Yep. Cool. Alright, folks.
Jordan Gal:See you. Thanks for listening.
Brian Casel:Alright. Later.
