How I Run A 0-Employee Marketing Agency With AI Tools

Hey everyone! I just had an incredibly mind-blowing experience. I just had a solo entrepreneur who's running a six-figure business by themselves with AI walk me through exactly what they did: the tools they use, their workflow, their exact prompts—and they're sharing it all with you! That is today's show. You're going to want to stick around; we've got an amazing guest, Barbara from Startup Cookie, who's going to walk us through everything. If you're looking for inspiration for starting an AI business, this is the perfect show for you. Let's get started!

[Music]

Show. I guess to just kick us off, like, where did you get started? Like, if you're somebody out there and you're like, "Hey, I think I want to run a solo business with AI," like, how do you even get started doing that? And like, where do you start from, like, a tooling and process perspective?

When I started this agency, we uh, just got ChatGPT; it just launched. And I was working for a YC startup as a head of content. I'd been kind of struggling for a few, few years just kind of managing an entire team of people just in order to sustain, like, honestly, a pretty mid content schedule—just like your average once-a-week blog post, social media post. You know, it's like creating all of that different resources. I wasn't doing any of the content creation; I was just managing people, communicating with people, and it cost a lot of money, it took a lot of time, and it wasn't the most fun work. It was just managing a lot of people. And when I saw what AI could do, even in the early stages, if you prompted correctly, I was like, "Wait, what if I can just do this myself without hiring anyone?" Started off pretty small, but already with our first client, I realized that this is completely doable. And now, when you just like look at the last three months and the improvements and things that OpenAI launched and everything that's kind of progressing uh, in the AI world, you're realizing that you can effectively scale your agency exponentially just by using these tools.

I love that you started the company because you had the realization that managing people—that's really a horrible, horrible thing to do.

It is, because it takes a lot of time. Uh, now I go into ChatGPT, and when it doesn't do what I say, I just like turn my caps lock on and just absolutely… myb… exactly. You don't, you don't have, uh, you don't have all of the messiness that comes to managing humans. The only thing that might be uh, worse is your holiday parties might be a bit odd with just you and a bunch of Agents.

They're great! It's just me here in the hot tub, like, in the mountain. It's fantastic! Mark Andreessen was on Next Freedman's podcast, and he talked a lot actually about the fact that he's like really excited to see when we have the first kind of companies either where the CEO is just managing a bunch of Agents, or the uh, Agent is managing a bunch of agents, and the human is supporting those agents. Like your, your version is like, "Hey, I'm going to create a company and just have all of these agents to do these use cases." And actually, one of the interesting things is Sequoia had a report out recently, and it showed the differences—the stark differences—in AI usage if it's built into Services versus AI usage if it's a consumer app. It's actually been much more successful in Services businesses.

What was the very first use case, content-like thing you did that worked really well? Like, what was the very first content agent you built that you were like, "This is actually better than a human?" Because I feel most people's experience of content in AI is the opposite, where it's like, "This is like much worse than the human."

And I actually think that comes down to being able to prompt intelligently versus actually the, the, the AI capabilities. Hot take incoming here: I've worked with a lot of freelance writers while I was working for startups full-time, and unfortunately, most startups just don't have the budget to pay the actually exceptional writers that I would still fully pay today. Most of them were just around $200, $300 per article, and my experience was: giving someone a brief, extensive detail, context to write a piece—that piece would come back to me, and I would essentially have to rewrite 60, 70% of it. And that was just kind of the process, and we called that efficient because we weren't willing to pay for each piece like that. Like, if you're trying to sustain a certain schedule, it's difficult to set up like a $100K a year for just like your blog to be active, but it was a lot of work on my end, and it just, it didn't feel creative in any way; it didn't feel innovative; it was just kind of what, you know, the best that I could kind of get out of that quality of writer. And then, as soon as I tried ChatGPT, I was like, "Not only is this better than the usual draft I get delivered, I can work with it, and I don't have to wait two, three weeks for it to be delivered to me," so I can just kind of unfortunately cut out that part of waiting and communicating and putting all of this work ahead but not getting a result that I'm remotely happy with. And like you mentioned, it's all about the prompt. So the first time it clicked to me is when I started using our webinar recordings transcripts. I started using that for blog posts, so I was like, "Let me see what kind of blog post we get if I have this transcript, and if I, you know, explain our brand guidelines, any like writing styles, what, what happens when I do that?" And it was exponentially better uh, because you had a genuine piece of content and insights and knowledge that you first gathered and then used to create a piece instead of just going into ChatGPT and prompting it, "Write an article on this topic." Like we all kind of know that that just doesn't work anymore. So that was the first time that it clicked to me: it's like, "Okay, if I have something to work with, I can just repurpose this across different channels—social media, blog, email. We can try new growth channels like this pretty easily," so it's like, it's kind of endless if you have that good starting piece. And honestly, that's still what I do today. We never start with just like prompting AI just by itself to do anything, even a simplest social media post. We always have something to start with, whether it's a transcript from a webinar, a podcast episode—kind of like this—just download the transcript and use that. I actually started my agency with a co-founder, so now he's here only to interview Founders and CEOs because if they don't have a podcast, if they don't have a webinar series, he just gets on a call with them and just talks about different things that they're excited about: what are they building, what are their views on, you know, AI is popular right now, but like anything, anything they don't want to talk about—personal views, hot takes, anything they want to communicate but just can't do it themselves—and then we basically manage their personal accounts as well, but we always start with that transcript, so we have someone's actual insights and actual knowledge, and we also have, like, you know, the tone of voice, the writing style, the phrasing to work with, so that's what you kind of need in order for the actual result to be in any way good. And then, of course, you have to kind of fiddle with it and play with it to get it to the quality that you want. You know, each founder gets one interview a month; it's an hour; that's totally fine. And then other companies have webinars and such that we use. So that was the first time that it like clicked to me that I was like, "Oh, this is actually not only providing great results, it's fun to do for both us and the companies and the founders." The founders love it; they're like, "Oh my God, this was like a therapy session for us," like a monthly one. They get to explore different topics that sometimes they don't get to explore in, like, product meetings, because sometimes you just need to talk through different concepts instead of just like kind of telling your team what to do and what the next steps are; you just need someone to kind of listen to you and, you know, kind of get that, get that concept and get that product messaging out and test it and just see how it performs. It's been working really great so far, and as AI is getting better, it's just getting easier and easier. So I think that step is like, if you were going to suggest how people could follow that, it's really: get context, and the context really matters. And one of the things Kip and I were just Slacking on is: actually having someone interview people is a pretty good way to get additional context; it's not available elsewhere because you get all the meeting transcripts. Yeah, and especially if you work with uh, a company for quite a while—our average client has stayed with us for a year and a half already—so we have a lot of content already, and we have teams kind of reaching out being like, especially for busy Founders, you can't go and ask your Founders like, "Hey, what's your take on this social media thing that's going around right now, and we want to like create messaging around it." So they often send us a message and they're like, "What do you think he would say to this, and what would be his phrasing?" And then basically, I just put in, you know, 10, 20 transcripts that we have from him, and I just asked ChatGPT, "Like, did he mention this? Were we, did we talk about this topic at all?" You know, just like, "Let me know." And yeah, then we just work with the team as well, so it's, it's very interesting; it's like kind of creating a persona of someone and having that available in your ChatGPT. Yeah, we, we do that both in, like, Claude and ChatGPT, where you can just have a project, have all that context, and you can kind of just interact with that project to get that clarity right that you're looking for. And so, if step one is getting the context, and that's either publicly available transcripts or doing those conversations and recording them like you talked about, then step two is doing stuff with it and prompting and engaging with that. And we were hoping maybe you could show us some prompts, like, walk us through some of how you're actually doing this, so that somebody who's at home, they're a marketer, they're running an agency, like, "Hey, what do I do?"

Do you want everything that Barbara is talking about in this show? We've taken Barbara's insights from this episode and we've actually created this incredible full-stack AI marketing toolkit just for all of you! It's packed with things that you can copy and paste right away; like all of the AI prompts we talked about are loaded right down here in this guide. It is packed with copy-and-paste-ready AI prompts—prompts that are going to solve your biggest marketing headaches. We've included use cases, customization tips, how you can do quality control, so you can just like copy and paste everything into a one-killer AI workflow. You're going to want to get it right now; it's at the link in the description below, or you can scan the QR code. And uh, now let's get right back to today's show.

Okay, so I created this a while ago just to have an overview for myself. So the "before" is basically everyone that I had to hire when I was working as a head of content full-time. I made a calculation how much that would be per year based on different salaries right now—full-time, freelancer. Obviously, you don't need, you know, five writers full-time working for you. It's more money at the end of the year than you expect; it's always one of those things like, "Oh, we always have reviews; we always have like another uh, request for the writer," and then it all adds up. And then when you introduce like SEO copywriters, video editors, audio editors, they're all very expensive, and all of their kind of like contract periods are at least six months, so you're kind of, you have to commit, and that's a bit, it's a bit difficult when you're just kind of trying to test different channels and test what content works for you. If you have like a proven channel, then it's worth obviously investing in it, but when you're still testing, like as a startup—I've only been working for startups—so I'm just my mindset is very like scrappy; I'm like, "How can we test this as fast as possible in good quality without like spending a bunch of budget on it?" So this is basically the whole list of people that, that we needed, and you know, copyrighted, marketing designer, all of these like different roles that you either need full-time or you need to get freelancers, but then you need someone like me who is head of content, but instead of creating content, I'm just managing all of these people, and it's not very efficient. Uh, so basically, now I just have that team in AI. I put my entire tool stack here, but none of them are unheard of. People usually don't know about Granola; Granola is very excellent for for meeting transcripts, and you get to chat with the meeting transcript afterwards, so instead of uploading that transcript into ChatGPT and getting it to tell you things, you can immediately be like, "Wait, what was talked about? What did he mention there?" And you can just do it right there, and it, it works really, really well. And then, yeah, Riverside, Midjourney, Descript, Super-Whisper, OpenAI, Claude—that basically replaces all of these roles, even some kind of more technical ones, like a data analyst. Like obviously for marketing, that's not—you'll, you'll be fine; you can get away with just like your social media analytics, like go to Buffer—but for a lot of roles, like, I remember we had like a data analyst on the team, and it was just like this guy who knew how to work Tableau; like that was his only thing; like it was just like working full-time for us just looking at Tableau, and then you're like, "Hey, can you give me these numbers?" And then he does. So it's, but yeah, there's like a full role just for that, and you need them full-time, so now you just have AI stuff for that. One of our clients actually built uh, data uh, analytics and visualization tool that lets you like upload your data set and just like you have in ChatGPT, you have a chat for it, and you just ask your data set anything that you need to know: you're like, "Okay, tell me these exact numbers for this quarter, and how does that compare to like the last year or whatever?" And I'm like, "Wow, this is amazing!" Like non-technical people couldn't do this before; I couldn't do this before, and it, it can cost you less than $1K per year. Like, that's my cost of running an agency; that's crazy!

It's a sensitive topic. What, what, what you really have here is a stack to go from idea to like final piece of content. Like, you still don't have any email service provider or like the kind of, or any cost you're paying to distribute the content, ads, or anything like that, but this is a, you know, 400x cheaper uh, way to do, "Hey, I have an idea, and I need to get that idea to a finished piece of content," which is pretty wild, right?

Yeah, yeah. And sometimes you need to get through all of this in order to test a new channel, like email. So that was kind of the issue—one of the, the biggest friction that I felt when I was working with teams before AI is that just to test something, you know, you get that energy, you get an idea, and you're like, "Oh my god, let's see how that performs; let's test it out," and then when you actually delegate that, it's like two months after that you're actually testing it. It's, yeah, it's, it's not ideal. And you also, you know, spend money to test an idea that's potentially going to fully flop, so yeah, it's, it's a bit of an investment, and I feel like it prevented us testing different channels in a lot of companies that I work with just because of uh, lack of budget or lack of resources in terms of like people. But yeah, I have a full, like, just our workflow with AI, just what we were talking about a few minutes ago. Go.

So you start with obtaining authentic insights. Yeah. Once you have that unique insight, whether it's from a webinar, podcast episode, your founder—and I often tell other Founders, I'm like, "If you don't have the money to be paying an agency uh, for my own content, I often just turn on Super-Whisper and I record myself talking; I don't need someone to interview me"—so that's how I create my own content. So it's like you don't necessarily need to have someone interviewing you. If you're like a Founder that's just starting out, you don't have anything, nobody's inviting you on podcasts and stuff like that, you can also do this yourself. So just talk about what happened during the week, talk about what you learned this month, how the team is doing, how's the product doing, do you have any challenges, how did you overcome them, and then you just use that transcript. So it doesn't have to be an interview. I will also link later all of my prompts in a sheet so that you can link it under the episode. I feel like people love kind of going in and just copy-pasting, and they can just use that; it's uh, always public. But yeah, our first prompts are usually just: "Extract all of the insightful topics that we covered in this conversation," because it's an hour; I often, you know, sometimes I sit through it, and if it's like an interesting founder, I'm like, "Okay, let me listen to this like a podcast," but the reality is you just don't really have time to do that each time, so you just need to ask ChatGPT to tell you about what topics were actually discussed, like, LMP them, which ones were interesting, which ones were like fully covered and flushed out, and you just, it just gives you a list, and then it gives you—can ask it for um, time stamps—and then you just go to that part of the conversation. I still often manually uh, just listen in a little bit because no matter how much you work with AI, sometimes it just misses, I don't know, that part of the conversation where you were like, "Oh, actually that was a great zinger; that was like, that was great; I see a lot of personality there." I still haven't gotten it to give me each and every one of those uh, kind of talking points, uh, so you have to work with it a little bit. You have to be present. If you're just trying to prompt AI and, you know, not trying to like kind of be involved and actually think about a content piece, it's probably not the best strategy. And then once we have a list of these insights, I just go one by one, and I tell her to summarize it; I tell her to look at the entire transcript and basically fill in any gaps at context uh, make sure that it's only taking information from the transcript—this is important because sometimes it starts pulling things online that are just kind of relevant but weren't really said, which is difficult when a Founder is talking about a product; you kind of need to be accurate, and you need to use their own phrasing uh, because they have like different features, they have their own branding—and then I basically just instructed to create a social media post from it. The interesting takeaways—is there any kind of like prompting or anything you're doing to extract—I know you can like add the time stamps, and you can say like, "What are some of the most interesting takeaways?" But for example, one of the things that I played around with is figuring out like what types of content perform well on different platforms and then templatized them and then asking it to look for talking points that match one of those templates. I'm curious, like, did you do, did you do—how did you like—how did you have it understand what are interesting takeaways?

It kind of depends on what they want to talk about online in general and what their kind of persona is. We kind of help them in terms of branding a little bit to just like have some of the, the topics that we regularly come back to, but it's all about prompting AI and not expecting it to deliver a full list. If you just ask it one question—one thing that has really helped me is I very rarely type into ChatGPT; I only use Super-Whisper, so I use just my voice; I talk to it, and the results, for whatever reason, are infinitely better because I add more context the way that I wouldn't when I'm writing. I kind of tend to make it shorter, make it more concise; you're thinking about the sentences that you're writing, but when you're just talking, you add more context than necessary, and ChatGPT performs much better when you give it as much context as possible. So I can kind of go in and be like, "Okay, so this founder wanted us to uh, talk a little bit more about the product; their product is XYZ; we want to find something interesting for this particular target group; extract any insights that they shared in this particular transcript of that," and then I see that, and then I kind of just read through it and see what kind of looks good. An unfortunate part of—well, not unfortunate, but a part of prompting and creating content with AI is having good judgment and having a sense of what a quality piece of content is, and that's a little bit more difficult to cultivate and explain and put into a prompt, so you have to be—it's like focus mode; you like, just because you're prompting AI, it doesn't mean that you're not focusing on what is actually going to produce uh, an interesting—whether it's a tweet or an email or a blog post—so you have to be present, and you have to kind of look at that list and think critically: "Does this sound interesting? Does this sound like something that can be turned into a bigger piece? If not, let's move on to the next one," and you know, sometimes from these transcripts I get like one or two insights; that's just unfortunately what happened that month, and then other times it's like, "Oh my God, they're really like in the flow; they shared a lot; there's a lot of knowledge here to be uh, kind of taken and turned into different social media posts," so you know, sometimes we just end up with a little list of social media posts, but other times we're like, "Oh my God, this can be a much bigger resource; this can be a full email like newsletter series that we can just turn." So it's like, we sometimes we get more, and sometimes we get less, but you just have to kind of work with it and be a bit strategic and also harsh. You know, sometimes I'm like, "Okay, that's not really interesting; you know, it's been said before; let's move on; let's not use it just because it was discussed in the transcript." So I prompt a lot; it's not one long prompt; it's several smaller ones, so I'm basically just having a conversation with ChatGPT, but I highly recommend people, especially when they're starting out, to try to talk to ChatGPT instead of write, especially if they're creating a bigger piece, like blog post; works much better.

Yeah, you're, you're basically saying—I, I don't know if you're saying the same thing—but I, I talk to it about what I want to do and then have it create the prompt. I don't know if you want to show some of your prompts, cuz I think it's really hard to like, to understand what that means without seeing it. I think if you're, if you're listening along, might be easier if you could actually show some of them.

Yeah, what I love is you'd mentioned that you were going to share, share the link in the description uh, in the comments below to the spreadsheet so that people who want to use these prompts can go and, and use them directly. But maybe take us through a couple of your core, like, power prompts for co-creating content with AI. So let's, we're going to assume we've gone through the workflow as outlined; we've got great context from our subject matter expert, and now we're going to use these to bring that to life, right?

Awesome. So like I was saying, when you take uh, a unique piece of content and download a transcript for it or whatever you have—it can be written content as well; it doesn't have to be—well, transcript is written content; doesn't have to be from an event; you can also have like maybe a resource guide, like a huge one that you wrote, so you can use that as well—uh, and then this is basically the main, the starting prompt that I'm using: "The text below is a transcript from a conversation; your job is to do the following," and you basically are asking it to list the main ideas from the conversation that I can repurpose into an insightful blog post. Doesn't have to be a blog post; can be anything else. Focus on the most unique and insightful topics and insights shared; it should capture the real meat of the information, not a vague, useless summary. You can be a little mean in your prompt; that's okay.

You can be a little mean.

We'll call it direct. You want to be very direct with what you're looking for, right?

Exactly. And that's how you start. And then once you see that full list, just think about it in a very uh, critical and honest way: like, is—if you saw this on social media, if you saw this as a blog post, would you read it? Would you click on it? Would you interact with it? If not, might not be worth creating. I feel like people often uh, fall into this rabbit hole of like, "Oh, I can now make a lot of content very easily, so therefore I'm going to do that," but I think we can use AI to really zero in on the most unique and interesting and insightful types of content instead of just going for the, for the quantity, which I'm sure we've all been seeing on, gosh, especially LinkedIn; it's really, it's rough out there. I was looking at the LinkedIn comments in one of my recent posts, and I'm like, "These are all AI generated, 100%." And then once you find an idea that you like, tell it to focus on that; you have to go one by one. If you just tell it, "Take the whole list and make me a social media post from it," it gets very messy and will be—it's difficult to then figure out what part it hallucinated, yeah, which it does much less now; that was a bigger issue before, but it is a little difficult to kind of figure out where it was pulling the information from, but you essentially take one idea and tell it to craft an engaging and insightful social media post based on that topic; it should use the full transcript, so not just that part of the conversation, because often time when you're having a discussion about something, especially when it's uh, product related, you kind of talk about it through different points in the conversation; you might be coming back to it; you might like have a realization later on; you don't want to miss those, those things; you want to kind of connect everything, and that's why I love using ChatGPT for that because it has much better pattern recognition than me, so it can kind of connect those points in a conversation better than I could if I was just sitting there listening in on the conversation. Use the information from the entire transcript, not just one point; craft together a narrative about this particular topic; make sure that that it's following a format of a social media post; instructing it to be punchy still seems to be one of the main ones that perform great; works better than concise; works better than to the point, so I would recommend using these exact words that I used here, like, "Punchy, engaging," because they, they have worked really great consistently for me. And then I usually instruct it not to use metaphors, catchphrases, jargon, because it kind of makes a cringe. I even often write in caps lock, "Just don't be cringe; don't be cliché," and that works great, honestly. And then I just, I usually keep this list of words updated: "Don't use the word 'insure'; don't use the word uh, the word 'in the realm of'; don't use sentence uh, question sentence as a segue; it does that a lot; it's like, 'The goal?' question mark, and then it writes the rest." Like, okay, this is all terrible, and it's—we all know that it's AI, so if you just prompt that from the start, you can remove a few steps for yourself down the road. And another thing that I found really helpful with one of the recent updates uh, let me share that as well. So the projects thing—you can see we have uh, basically a project for each client and for each of their deliverables, so like blog post, social media; it's, it's, it's slightly different content, so I, I prefer to have different projects for it, but maybe later on the prompts are going to get kind of better, and it's going to get better at using the instructions and project files. Right now, it like misses about 50% of the time, which is uh, not great since that's kind of the main functionality of it, but when the projects came out, everyone was like, "Oh yeah, that's a, that's a neat feature," and I was like, "You guys don't understand; this just—I can scale my agency because of this even further; it's, it's fantastic!" So for example, this is also in one of my prompts, but I just want to share: so for example, for one of our clients, we write weekly blog posts for them, so in the project files I have literally a Google Doc that I downloaded uh, with writing style samples, to base voice and tone from, so I asked the founder, "What are some of his favorite writers? What are the blogs that he uh, reads on a regular uh, basis? Whose style does he like?" And then I just added all of that in here, and when we create uh, a piece that he's like, "That was great; love that; love that style that you established," I also just put it in here. And then general information about anything about the company, anything about the product, anything discussed, so that we basically have this huge document of everything that you could possibly need to know about the product, that instead of prompting it, just has it right here. So once we start writing something, it already has a lot of context on the product. And then in the instructions—this is arguably a more important part than the than the documents—you just instruct how you want it to behave every single time. I still find that I have to instruct it in the chat to make sure that it's following instructions of this project, which is a bit annoying because I'm like, "It's right there!" But you know, we might be a week away from that just being what it does all the time, so I don't want to complain too much, but it's—this is the prompt that I kind of found that it works the best for basically any kind of blog post, social media post; you just change it depending on the content piece: "Write in a direct, non-nonsense style; use clear, simple language; short sentences; focus on concrete details over abstract concepts; skip the startup buzzwords; it loves to use those a lot; I don't know why; cultural references; keep it brief," and I always love to tell her to stay honest: "Like, just let, let's be, let's be real here; don't uh, remove parts of the transcript that talk about like challenges or anything like personal; sometimes it tends to like not include that, which is interesting; share specific examples, data points, been relevant," and then this is probably the most important part of it: "Never use questions as transitions between topics; it does that a lot; avoid any sentence structure uh, structures that negate expectations," you know, "This isn't just about…" It's a very standard one that AI does. And then just list any words that you don't want it to use. This is a, this is a great one that works for me. Sometimes I have to instruct it further, you know, it's like, if you instruct it to use these instructions and then you kind of go through a series of iterations, you have kind of have to start repeating yourself essentially, but you know, you can do that in caps lock, and you can really just let all of that frustration out. So yeah, it, it, it works; it works good. Very excited about the projects tasks, too. I have a task for every single morning to get a list of the latest news in, for example, Tech—most of our clients are in Fintech and HealthTech—so I have an each one for that as well, just so I can stay up to date without scrolling Twitter endlessly uh, cuz before I did that, I was like, "Well, I have to be on X every day because it's my job to know; it's low-key ruining my mental health, but I have to do it." No, I don't—especially now that we have Gro, and you can also search within X, so yeah, that's kind of my, my favorite use cases right now apart from just the other prompts.

Okay, that's amazing! First of all, thank you in advance for sharing the prompts with everyone. And so, I, I want to kind of recap what you have taught everybody: you've taught essentially a master class on how you go from having a big coordinated content team to a smaller, agile content operation. You're doing it as an agency, but you could certainly do it inside a company; anything you, you might want to do. And, and the first thing you did that I think was really important is that you have a very clear workflow; like, you know the steps of your workflow, and you have that documented, and you kind of know what tools and what process you have at each step there. And what you're also doing is you're really using the native functionality of those tools very, very deeply; like, you, you're using way more of ChatGPT than the average person, and that's where a lot of people are falling down right now is they're not getting deep enough in the tools that they are using. And uh, you are, you're doing the exact opposite; you're really deep in not just the features but even the prompting and the language you're using with the models to make sure that you're getting this, like, this really remarkable output. And I think the key insight here is like you're like, "I never start from a blank page; I always have context; context is everything; I need to either take existing context or go and have a conversation and get that to in order to have a great starting point." I guess as we close out the show, if you were giving advice to people who are like, who were looking to make this transition, who really want to automate how they create content, share stories online, anything we haven't covered, anything you're like, "You should go start here" to, to go and do that today.

I think it's very important what you just said: you never start with a blank page. And if you're, if you're someone who's just starting out with this—not just ChatGPT, but using it for work—you, you don't have to create each prompt by yourself. All of uh, our prompts that I use for agency management uh, which is also

Barbara, I really appreciate you joining us on Marketing Inst the Grain today. Thank you so much for sharing the behind-the-scenes of how you've done all this. And uh, thank you so much for joining us.

Thanks for having me. All right, see everybody next time. This data is wrong every freaking time. Have you heard of HubSpot? HubSpot is a CRM platform where everything is fully integrated. W I can see the client's whole history, call support tickets, emails, and here's a task from 3 days ago I totally missed. HubSpot. Grow better.