← The Digital Marketing Podcast
The Digital Marketing Podcast
AI Copywriting and Claude - A Copywriter’s Guide to Getting the Best from AI
00:36:44
In this episode of The Digital Marketing Podcast, Daniel Rowles sits down with copywriting and AI expert Kerry Harrison to explore one of the most exciting—and often misunderstood—areas of artificial intelligence: AI-powered copywriting. Together,...
Loading summary
Transcript41 lines
- [00:00]
Daniel Rolls
Welcome back to the Digital Marketing Podcast brought to you by targetinternet.com My name is Daniel Rolls and in this episode we have an expert guide to copywriting using AI and a hands on guide to Claude. So if you're anything like me, you've been using ChatGPT, maybe Google Gemini for a while, you've been doing some copywriting. You think you're pretty good at writing good prompts for copywriting and getting good quality copy out of these tools. You may not have played with Claude and you may think there's a little bit more you can explore. And this is the interview that is going to really help you with this as well. So I have got an interview with Kerry Harrison. Kerry is an expert in using Claude. She's worked out the real differences between Claude and the other AIs and how you get the most out of them. And she's also originally by trader copywriter. So writing is her craft. And I thought it was really interesting to see someone as a copywriter, not feeling threatened by AIs but actually really embracing them and working out how you get the most out of them. And what Carrie's going to take us through is a step by step guide to approaching copywriting for any given scenario. But also while we're doing that, we look at how you use Claude, the difference between it and the other AIs and what you can get out from it. I really learned some great practical tips in this one. So over to the interview. Okay, so I am here with Kerry. I've just kind of explained to people that I'm not familiar with Claude. It's been off my radar for a while and ChatGPT is the default for a lot of people. So why do you recommend Claude? And what kind of separates it, do you think, from ChatGPT and Gemini? And like.
- [01:46]
Kerry Harrison
Yeah, it's a good question. It's so interesting because ChatGPT is the default for so many people in most of my training that I run literally every. If anyone's tried any tool, it's ChatGPT and I totally get it. It was the first that came out November 2022, so ChatGPT was the first there. And so people have just sort of grown with it, which. And it's a brilliant tool. It's not that I don't use it. I'm just a really big fan of Claude as well. I think it's a really great, you know, not that dissimilar to ChatGPT. It's not quite as innovative. I feel like ChatGPT is always like the first to, to be, to be ahead. They're a really innovative company. But I'm a copywriter by trade, so I write a lot and Claude is really good for copywriting. I just think it's got a really nice default hoe, so I tend to use it for that. In terms of how it separates and this is something I talk about in my training is that it's one of the things I really like is they're very. So it's run by a company called Anthropic. So Anthropic is the big company and Claude is their product and they have trained their model to align with a constitutional AI document. So this document talks about things like opposition to inhumane treatment, it talks about freedom, it talks about safety. And so essentially the model's been trained to kind of align with those values, which I think is really interesting. And if you go onto the Anthropic website, the first thing you'll see is this, their interest in safety. They're sort of slower to move, so you haven't got, you know, all the fancy bells and whistles that you get with ChatGPT. But they take their time to release things. They really want to make sure that they're doing things properly. They talk a lot about the long term implications, they talk a lot about doing the right thing for humanity. So I really like that kind of ethical side and that approach that they take. So that's one reason to use it. In terms of writing. There's a little tool in it that I use for writing which is helpful for anyone who's doing any kind of writing, whether it's for social media or blog writing or whatever it might be. There's something called use style, which is just accessible from the main prompt window. And if you press that you first of all, you can decide whether how you want Claude to respond to you. So it might be that you want. So you can do a normal one, which is just the default, or you can choose something like precise, where it'll give you something that's very. A much more concise answer or you can go explanatory. So if you're learning something, then you click on the explanatory response and it will give you something that's a bit more like a teacher, so reply in that kind of way. But what you can also do with that is you can train it on your own style so you can upload a document, it will scan it and have a look at the way that you write and then it will name that style, it'll absorb that style, and then that's also then becomes one of the dropdowns as well. So if you want to train it on something to sound a bit like you, you can just then go to that dropdown and it reply, it's not perfect. It's not ever going to sound exactly like you, but it just gets out of the default tone. And I re. I just think that's really important with writing, considering more and more people are now using these tools for their writing. It's just like, how do we not sound like ChatGPT, basically? So I like the fact that I can train it on different styles. So I've trained one for my sort of newsletter song where I'm very much me and I just sound exactly like I am. And then I've got one where I'm a bit more professional, so I've trained on different ones so I can just literally click and go, I want you to reply like this today. So, yeah, things like that I just think are really helpful.
- [05:03]
Daniel Rolls
And that default writing style you've said is probably better than the kind of standard chatgpt for writing as well. Do you think?
- [05:09]
Kerry Harrison
Yeah, it's interesting because I've gone through this real journey with Claude, so there's been two model releases, literally in all my courses, I was like, if you're copywriter and you're writing BTC copy, always go to Claude. It's just really, really good. And pretty much everyone at all PR agencies, copywriters, normal agencies, they would just be like, oh, yeah, now I've seen Claude, this is amazing. And then they did an upgrade to 3.7, so they've just upgraded to 4. And when they went into 3.7, I started playing with it and I was really disappointed. I think it was the first time where I explored a new model and it had not been better than it was before, just for copywriting, for everything else I know code had said like, oh my gosh, the new upgrade is amazing. And then for me, as a copyright, I thought, oh, no, it's just. No, it's just not as good as it was. So I was actually dropping down to the former model and then I reverted back to ChatGPT and I was talking to fellow copywriters who were doing the same because they were like, oh, we're really disappointed with the Claude one as well. Have you found the same? I'm like, yeah. So I felt a bit sad because I just really like Claude for all the reasons we talked about. And then I was like, oh, no. But then they've just upgraded to four. So they've upgraded their models again and then it's gone back in and I've kind of got. Yeah, I'm like, I'm back into Claudic and I really like Claudic, so I was really glad that it did that.
- [06:23]
Daniel Rolls
I remember we had this scheduled in and you kind of messed me when. Do you mind if we push this back a little bit? Because I'm a little bit concerned about the new model. And it's really interesting because the different versions of ChatGPT can be the same and use different models and it will give you a different, slightly different tone of voice because the way the model has been trained, so it's hard to pick out that if you're writing, you need to know the model and the response you get and don't expect it to be the same every time. I think, yeah, that's really important.
- [06:44]
Kerry Harrison
I think. I think that's true. And that was the first time where I'd actually was disappointed because I think with Chat GPT, I often found ChatGPT was a little bit stiff. And actually, I think their new upgrades, as they've gone along, that's actually got better for B2C copywriting. So, you know, there's probably. It's. There was a point where I thought, actually, now Chapter TP is actually better than Claude, and now we're kind of somewhere in between. I just. I just quite like Claude's kind of approach and this kind of slower approach to releasing their tools. They just seem to be taking the time and thinking things through. I really like that. I think another thing with Claude that I quite like, whereas I feel like ChatGPT, and I know there's been quite a lot of talk about this lately, that it's quite sycophantic, you know, it'll tell you that even your, like, really quite mediocre ideas are genius and things like this. It was. It loves to flatter you.
- [07:28]
Daniel Rolls
Right.
- [07:28]
Kerry Harrison
I feel like Claude's not quite like that. It's a bit. It doesn't sort of flatter you because sometimes it's like, it looks like occasionally you'll be like, yeah, I know, but it is a pretty good. Right. And then occasion's just like, do you know what? ChatGPT just tell me straight. Because I don't want you to just keep me nice to me all the time. I feel like Claude's a bit more realistic and I quite like that.
- [07:47]
Daniel Rolls
A critical friend. Which is good.
- [07:48]
Kerry Harrison
Yeah.
- [07:49]
Daniel Rolls
So they've upgraded the model recently. So. Yeah, what do you think about it? And I think there's like a default and a reasoning model, isn't it? There's different versions.
- [07:56]
Kerry Harrison
Yeah, that's right. So the new model you have now, if you're in the, if you, if you're free, if you're in the feed version and really do use the free version, if you've never tried, call before because it, it's a great place to start. If you're in the paid model, you also get the reasoning option as well. So you've got four Sonnet, which you get for free, but you just don't get it. You just have a limited use of it. And then when you're in Page, you can obviously use it for much longer, but you also get four opus, which is like the most advanced model that they've got, which is quite high powered. It's really good for thinking things through, critical thinking. And you tend to think with ChatGPT. With our reasoning models, they tend to be more suited to things like STEM and maths and coding and things like that. I feel like with the Claude one, it's also pretty good for content creation, things like strategy. So I do use it for, if I'm thinking more strategically and more recently I've been looking at my own business and my positioning and how I might move forward and actually Claude's been a really good thought partner for working through those kind of things as well with this larger model. Just, it's, it, it's just much more. Yeah, it's kind of critical thinking. It's reasoning, it's. It moves things through step by step. So I found that really powerful, a really powerful model.
- [09:15]
Daniel Rolls
And there's a lot of debate about AI content and ChatGPT creating stuff that's quite, you know, generic sometimes as well. How can you use Claw to make sure that, that copywriting is kind of authentic, compelling? It's going to be original as well.
- [09:26]
Kerry Harrison
Yeah, it's a good question. I think there is a danger with ChatGPT because it's the default model for a lot of people. And I think we're finding now that because so many people are using it for copywriting or content that actually people are getting pretty savvy and they know that it's generated for ChatGPT. I think you don't have to use it for that long term to recognize it. The certain phrases that it picks up, like every time I create any kind of blog or if I ask it to think about anything that's related to AI and writing or AI and content or AI marketing. It always starts the line something like in this fast paced digital world or something like that, like in the modern.
- [10:04]
Daniel Rolls
Era is the one I've seen a lot. Yeah.
- [10:07]
Kerry Harrison
And you'll see it a lot. And then I see it in blogs and emails and stuff like this that it's like you've, you've generated that with ChatGPT. But I was talking to someone the other day, she's a recruitment consultant and she was saying literally nine over like 90% of the covering letters she's getting is made with ChatGPT. And she can just tell straight away now and she's just kind of working out, you know, maybe I need to look at ones that aren't generated by ChatGPT because I've actually made the effort to do it, which is, which is interesting. And so I, I think with ChatGPT and I think it's the same with all the models really, we have to be coming out of the default tone as a default. You know, we have to make sure that we're not just sticking with what's there. I suppose with Claude, just because it's a bit more of an underdog, I feel like less people are using it. So you might be able to get away with just going with the default tone for a little bit longer before people go like, oh, she's doing it with Claude, which I don't think you would necessarily pick out. So, so there's that. But I think also just the fact that it's got that little abuse style thing where you can train it on different styles. But I think a lot of authentic, creating authentic content with AI comes down to also bringing in the human element. And that's regardless of whether you're using Claude or ChatGPT or Gemini, the same rules apply, really. You have to put in the work, as in, you have to use, you know, we've got amazing brains, we should keep using it. One of the key things that I worry about with AI is this idea that of descaling. You know, we'll just kind of go, oh, we'll get ChatGPT to do it, or I'll get Claude to do it. And we just, I really fear that we'll just stop doing our thinking, our critical thinking. So I have this methodology that I talk about in all of my presentations at conferences and stuff. It's called the AI Sandwich, which I know is not the most sophisticated name for a methodology, but it works really well. And it, people seem to remember it and Go. Oh, I loved your sandwich. So for me to get the best writing out of AI models and I guess it expands wider than writing is. It's a human AI, human process. It's a three part process. And it started with this idea because I wrote this creative methodology in January 2020. Where are we now? 2024. So I wrote it. So back into 2023, I was thinking, actually, I think the best way to get great writing out of something like ChatGPT or Chord is to use AI to generate a first draft and then for me as a human to go in and edit it and craft it with my own skills. And then what I realized towards the end of 2023 was actually the prompting is probably, is equally, if not more important than what we do with it afterwards. So that's where things really changed for me back at, back at 2023. So almost like a year into ChatGPT, it's like, hang on a minute, the prompting is so blooming important. So I thought, actually we need to do work before we even come to the tool. We need to have thought about one to come to tool with at the very least an objective. Because a lot of people now just go, I'll just go to ChatGPT. But they haven't really thought through what they want to create or why or how that links to their wider marketing strategy or their content strategy. You don't just kind of get, well, I'll just do it with that. So for me, I think we need to come with an objective, but also to think about other things. So how does it link to our strategy? What kind of, of my own ideas might I want to incorporate into this? You know, if you're writing a blog, what's the angle? Tell the model what your angle is so it moves in that direction. So doing all of that thinking, taking time on your prompts to get as much talent as you can. I tend to say in my, in my courses that if you think about it as an intern, so if you are asking an intern to write copy for you, if you're asking them to write a blog or a social post, you're not just going to say to them, go and write me a blog post on workplace wellbeing. You're going to say, I need to write a blog on workplace wellbeing. This is who it's going to. This is where it's going to go in this publication or it's going to go on our website. It needs to be, you know, 500 to 800 words long. You probably would also say, I've got these ideas. I'm thinking it probably needs to include this, this and this. So maybe start there. Have you got any questions? And basically that's what each. You would do in your prompt. You know that think about it as an inter, what information would you give it? Think about context, a bit of background, how long do you want it to be, where it's going, who's your target audience or all of that stuff. And so for me, putting being really detailed in the prompts then guides the model in the right direction. So. And I think what also really kind of still slightly intrigues me is the fact that it takes me a lot longer to write a prompt than just for AI to generate. So it will take me a while to get my prompt perfect and then it will generate the result in like a matter of seconds. It's like, that's wild. But I, yeah, but I do think that it makes a huge difference. And also to bear in mind that a lot of people are coming to the models and just giving them a one sentence, very un thought through prompt and say what you're going to get is pretty vanilla, pretty generic, pretty. Oh, it's definitely been written by ChatGPT. Um, so I think doing that early thinking, so that's the sort of human bit of the sandwich and then in the middle, which is the filling is the AI. So then you get the AI to do, once you've done your thinking, get the AI to go off and do its thing and it's brilliant and it's fast and it's quick and it will get you loads of it, give you 20 ideas in a few seconds, give you overviews or insights or data analysis and then you come back to the human again and when it comes out and you've got your, your response trimming whatever model you've used, the first thing we need to do is fact check it. So as you know and anyone knows who's using these tools, hallucinations are a thing and we, it's not, it doesn't hallucinate all the time, but it may have done. And so we have to check it. So fact checking everything, any kind of stats or facts that come back, just make sure they're true because they sound so viable but you know, it might not even exist. And then we also sense checking it is another thing that I do because I just think that it's really easy, it's, it's so easy to get wowed by the AI thing. The fact that you generated a blog in what 20 seconds, you kind of go, oh, great, I've got a blog. Brilliant. And I also think on first read, sometimes you can go, oh, that's great. But then on second read, you're like, oh, do you know what? It hasn't quite got the depth I wanted. Or maybe it's a little bit repetitive here. So I think censorship and just pushing past the kind of wow and actually looking at what you've got. And again, this is where we need to use our analytical brains. Like, am I happy with that? Another question I ask myself is if I wrote this from scratch or created this from scratch, would it look anything like this? And if the answer's no, probably need to think, well, you know, maybe need to go back in and think about the problem. Because, you know, the fact is we're. We're quite lazy naturally, aren't we? And if we've got a blog done in 10 seconds, it's like, brilliant, I'll go and walk the dog. To me, you just need to, like, analyze it. And then the last thing is craft. So I still feel like in this point in time that we still need people that know their stuff, people who have taste, people who have experience. And so for me, adding the human craft of copywriting, which I've done for 23, you know, I've been writing for 23 years, I still think it makes a difference. You know, I know what good looks like, so it helps me to analyze the copy and go, yeah, I think that's good. Or this. It needs more of this or it needs less of that. So, yeah, I still say to copywriters, there's a lot of copywriters, they're, like, really worried about their work. But I. I still think there's a real need for people who have deep expertise, because I also think, you know, there's a lot of talk around AI at the moment with the deep research tools, where it says, oh, you can have a PhD research 24 7. But I always think it's a bit weird because if it generates something at PhD level, but I haven't got a PhD in that thing, it's like, how do I actually know if it's any good or not? So I still think we need to be applying our critical thinking. So that's the kind of sandwich. So prompting thinking, briefing it like an intern, you know, if you were really putting in your thought and actually thinking of your own ideas. So rather than just relying on the model to come up with ideas for you, what would you like to see in your blog? You're just about to write or your social posts that you're just about to create. Then the AI does its thing and then you go in sense check, fact check, add your craft. So that's how you get more authentic writing. I mean, there's a load more to the prompting and stuff. But I basically, if you want to make something sound really beautiful, you need to add a little bit of you. Brilliant.
- [18:14]
Daniel Rolls
I love that. I mean, I keep coming to this phrase of like, lean into your humanity. When everything's AI and everything's deep fake, that becomes really, really important. What about the project feature in Claude? How can you use that in your kind of working process?
- [18:25]
Kerry Harrison
Yeah, so project. The projects is really good. The projects is pretty much an equivalent to the custom GPTs and ChatGPT.
- [18:32]
Daniel Rolls
Right.
- [18:32]
Kerry Harrison
So for me, that is a reason for me to pay for Claude. And now also because they've got, you know, this more advanced reasoning model. So projects allows you to create a little area or what they call a project. You give it specific instructions, you give it knowledge, and then you go into that space whenever you want to do something. So for example, I've got quite a few different projects where I go in. So I've got ones that do very simple things. Like I've got one called Ned, who's a newsletter snippet, basically. So I have a newsletter, write my newsletter, and occasionally I'll make them my articles in my newsletter a little bit too long and I want it to be snipped. So rather than me typing out a very long prompt every time, which basically says I want you to, I want you to change this to a different word count. But I don't need to take out my jokes. All my content, all my, you know, I. I've got this whole like long spiel of what I don't want it to do. So instead of putting that into a prompt every single time, I just want to go and snip a bit my newsletter, I've created a project. So just as I would with a custom GPT. So I've given it that there's details. So when I put something, give you something, can you, you know, edit it down, ask me what the word count it needs to be and then I want you to, you know, keep as close to the content as possible. Don't take out my jokes, not that they're any good in the first place, but you know what I mean, Say exactly on tone, but just cut it. That's all I want you to do. And so it's just really easy now because I just literally drop in an article that I've written and it will just tell me, ask me what code word can't it done. So it's just really, really easy. So I've got, I've got ones like that, I've got projects that are, I've got like my customer Personas. So one of my customer Personas is founders. So founders of businesses. And I've given it this really, really detailed Persona, so marketing Persona of a, of a founder. And then sometimes I'll go in and I'll just want to say, you know, what do you think of this idea? Or if you know, as a founder, what, how do you feel about this? Or I might take in my copy and say a landing page that I've just written or a new sales page for a course I'm creating and say what resonates about this and what doesn't. And so things like that's quite nice. So this idea of, I really like the idea of creating this kind of interactive Persona because generally as a marketer or as a writer or any kind of creative, you get given these Personas and they're basically just a made up person on a piece of paper. And I love the fact that now you can get something, create a really detailed Persona and put it in and then you can actually interact with it. And I know it's not the same as talking to an actual, actual customer, but then in reality the ones you get on a piece of paper aren't a real customer either. It's, you know, a strategist has made that. And so I put it in. So I've got, I've got a project that does that again, it just means I don't have to say to it, you are this role, this is what you believe, this is who you are, this is your, what demographic you're in. It's just all there in the project. So I can just say, what do you think of this? They're really, really quick. I'm trying to think what else I've got in there. I've got ones that help me write LinkedIn posts. So I've given it really, really detailed, granular instructions on how to write a blog style LinkedIn post. Just go in with what my current insight is and it will help me write one. Um, I've also got a tone of voice one, so slightly more detailed than the, the one that you get if you just go down off the prompt box. But you know, really detailed view of how I work, my tone of voice and what it sounds like. And how I write everything from the syntax to the. The sentence lengths and all the rest of it. So it's all in there. And again, if I've written something that's not maybe not exactly as I wanted it to sound, it's like I want it to sound like my normal, like, newsletter voice, then I can just drop it in there. So. And the same, I suppose, if you can create tone of voices for all different things, different brands, different businesses, I've got one that's really bold and irreverent. Sometimes I'm just like, oh, I just want to create something that's a little. Feels a little bit. A bit more cheeky to them. So I'll have literally trained on this, like, really irreverent tone of voice and I just go in and just say, make. Just make this, give this some life. And then I'll just bring in, bang, in and off again. So those are just some examples. There's loads, but there's. I've also got a business mentor as well, where I've given it loads of details around my business, my belief systems, the things that I love, my. My methodologies and my ethos around AI, which is hopefully, as you gather, very much a kind of human and AI combination. So I've given it all that information about me. So then if I'm working through something, like something in my business, I can just go to that project because it already knows all the information about it, I don't have to give it a massively long prompt. So basically, anywhere that you would use a custom GPT, you can. You can use Claude projects. And to be fair, I've got the role. I've got ones in ChatGPT and one's in Claude. And yeah, I've got some that exactly the same. I've just taken instructions from one and brought it over to the other. So it. And it's not difficult to make.
- [23:07]
Daniel Rolls
So, yeah, I was just going to say some of the ideas you were coming up with there are just absolutely brilliant and actually apply to all of the AI systems as well that you could use. So I think there's some brilliant ideas in there. So. And then this kind of approach to prompt engineering, how do you do that with different types of marketing content? Do you approach it in a different kind of way?
- [23:23]
Kerry Harrison
Yeah, I guess so. I think for me, I've talked a lot about the AI sandwich and a lot around what goes into a prompt, so I think a lot of that still stands. It's just being as detailed as you can, I think a couple of other things that I would do in terms of prompting is to give the model examples. And I think that doesn't matter whether it's called or attracted to any model that you're using. If you show it what good looks like, I really think that makes a big difference in terms of guiding in the right direction. So recently, for example, I was working on some case studies. My case studies follow a pretty similar structure. So it's like what's the problem, what was the solution and what were the results? So a three part process essentially. I gave it two examples of case studies already written and then a load of bullet points about the new one that I was just, that I was just about to write and then gate and then ask it to do to have a look to use the two examples as a guide to tone and style. And then I was, I was actually really, really surprised at what it generated. As in like it stayed really. Because obviously AI loves a pattern, doesn't it? It's, the whole thing is, you know, statistical prediction models. So it loves a pattern and I, and it really stuck to that pattern very well. So it get, it made the new case study for me. It, it instructed it in their problems, solution, results. It get like headlines and suburbs. I was a bit like, wow, this is, this is pretty good. So I think giving it examples makes a really big difference. If you're, if you're writing blogs, give it a couple examples of blogs you've written. If you're writing headlines rather than just trusting it to do some great headlines, get show it examples of ones headlines that you've done that are really high performing or that have worked really, really well for you. So again it has an understanding of your, your tone and your style. So I think examples makes a big difference. I guess the only thing just to be aware of examples is yes, it makes a massive difference putting examples, but just especially if you're on the free models, just be careful what you put into the models. I'm always very much like, don't put anything private, confidential, proprietary into the free models. So just be aware of that. And also if you're writing press releases and you want to give it some examples, just make sure your press releases aren't embargoed and stuff like that. Writing reports, just make sure that you're happy with what you're putting in. Nothing confidential or private, but generally speaking, if you, if it's, if you're okay to put it in, put it, put it in. And I think that that will make a significant difference to the output.
- [25:41]
Daniel Rolls
And then what about going beyond copy and kind of content creation? What, what else is, is Claude particularly good at, do you think?
- [25:49]
Kerry Harrison
Yeah, I think I mentioned earlier, but I, I use it for a lot of marketing side of things. As I mentioned the, the customer Personas thing. I really like that. And I can ask you about copy, but I could also talk to it generally about any kind of strategy or marketing as I was talking about positioning. So, so any kind of like strategy, content strategy. So not just actually the writing, but it helping to inform your writing as well. So it might be looking at customers, looking at their pain points, looking at. I've got this prompt where I look at a customer's fears, frustrations, dreams and desires and you know, create this whole scenario of them and what they, what they might think about a product or a service which can then help me to again look at those fears and frustrations, desires and go, okay, so maybe I could create some content around that or around that. So I think strategic stuff is really good for my own business. I've been doing, working a lot on positioning as I mentioned before. So it's been, I've been working it through that I think it makes a really good thought partner. So not necessarily giving me the answers. And sometimes I think it's quite useful to not ask for answers but to ask for ideas. So just as a different way of probably because I think we often go to the models and look for. Look for answers. But actually sometimes just getting ideas back is really helpful. So I like the fact that it might come back with something and I'll be like, oh, that's really interesting. And it might take my thinking off in a new direction or what I've done with positioning because I've had quite long conversations with Claude about my positioning that sometimes it'll bring something back or an idea back to me and then I'll look at it and go, it's definitely not that I don't want to do that made me question my. Oh, it's been really good at just helping me even tap into my own intuition because it will present something back to me or a target audience. And I'd be like, no, I wouldn't want to do that. I don't want to target these people. That would not make me feel very happy or wouldn't make me feel fulfilled. So I've really loved that side of it as well. Because if it just gave me an answer, I don't think I would necessarily go through those thought process and Think what do I actually think about this right now? Or like, am I happy to do that? Would that make me know? Would that fill me up or not? So I've used it for that, I think brainstorming, it's really good for, not just for copy, but for content, just for life, to be honest. Just anything where I've got ideas. Anytime that I just feel like there was a point in time where often it'd be like, oh, I just don't have any ideas, or I'm really, really tired and it's five o' clock and I just need some ideas. And the fact that I can get ideas within a matter 10 ideas, 20 ideas in a matter of seconds, and they're not going to be perfect by any means. And they're. If you're doing anything highly conceptual, as much as I want AI to help me to do that, I don't think it can do it. You know, things like strap lines, it's just really poor. It just generates a load of generic outputs. And so I sometimes start with it, but I always have to use my own brain for those kind of things. But for general sort of idea starters, I think it's really helpful. And normally I'm just, it just gets over the blank page thing. So I'm like, I don't panic anymore. It's like, okay, well I've got something down, that's the start. And then, and then I'll be like, okay, so that's quite interesting. Or I quite like that angle. I hadn't really thought about that before, so it might take my thinking in a new direction. It might be that it comes back with two ideas that if you blend them together, work pretty well or so I just, I like it for brainstorming, for getting me started. But yeah, hopefully a few different things.
- [29:11]
Daniel Rolls
Yeah, definitely. And I, I, one of the things I found with it is that, and I do this chat GPT, I'll get it to come up with five different ideas and then compare and contrast them. And I'm not necessarily going to use one of those ideas, but there's the thought process that it goes through. Getting to its conclusions is what's going to spur my thinking with this as well.
- [29:26]
Kerry Harrison
Yeah, yeah, and that's, that's really true. And actually with Claude, you've also got extended thinking. So extended thinking is another little toggle.
- [29:33]
Daniel Rolls
That'S like the deep research mode, I think.
- [29:35]
Kerry Harrison
Yeah, it's a bit like deep research, but you just literally toggle it on and it will show you it's thinking so it's a little bit slow.
- [29:42]
Daniel Rolls
I see. Fantastic. Okay. Because that, you saw that in Deep Seq and that was one of the great things about, explained his reasoning behind it.
- [29:47]
Kerry Harrison
Yeah. So I really like that if you just, if you just wanting to work through something, you want it to slow down a little bit because obviously if you use the default models, it's pretty quick. If you want to slow down or you want to think slightly wider or get it to do more, consider like considerations and come back with multiple considerations or slightly different creative angles, things like that. If you click on extended thinking, it will then yeah, it will just give you more and you'll see its thought processes. And it's like sometimes you're like, oh, that's really interesting because I wouldn't have necessarily gone down that route myself but if I do go down that route, I wonder where that would take me. So I do, yeah, I do think as a thought partner it's really useful.
- [30:24]
Daniel Rolls
And then what about things like data and analytics?
- [30:26]
Kerry Harrison
Yeah, so it's great for data analytics and I think, you know, not, I suppose comparable with ChatGPT. And it's also good visuals. So if you ask it to do data analytics, it will also generate graphs for you or diagrams for you and things like that. So in terms of marketing, if you're analyzing campaigns or how your social media is going or things like that, it's really useful. You can, you'll get that results and you can make them pretty and choose your colors and all the rest of it, which is great for any kind of reporting. So I use it for that. I've also turned on recently they've got now introduced in the last month or so integrations.
- [31:03]
Daniel Rolls
Right.
- [31:04]
Kerry Harrison
You can now integrate with. Because they've been, they've had investment from Google Anthropic. So they had a lot of investments from Google. They also had huge amounts of investment from Amazon. So I think it was 6 billion of investment from Amazon. So I think they've got these links with Google so you can link it up literally with really easily. Just literally click through, link it through to Calendar. Just check if you're going to link it through to Calendar and Gmail. Just check the privacy policy and make sure you're happy with that because then you have to be careful. It's like I haven't yet linked it up to my Gmail, my like main Gmail because it's also my personal Gmail and it goes back all, you know, so far now there's probably loads of personal stuff on about all Sorts of things. I'm like, I'm not sure if I want to give it that, but I've given it my business, my business account. So that's been really useful. So a couple of things I've done with that in the last week or so is to get it to tell me what are my priorities for this week. So it'll have a look at my calendar, it will look at my email and it will say you need to do these. And you know, sometimes it will say you really need to get back to this person because this seems like it's really important for you. So, so I like that. So it'll prioritize or even my day. So today I just said to it, what are my priorities for today? So obviously I knew it, it got the podcast. So that was on there. So that's, that's a good one. It can analyze that. I've also asked it to analyze my time. Like how am I spending my time? And that's really interesting from a data analytics point of view. And, and it even came back. Cause then I was saying, okay, so now you've analyzed my time, tell me how I can be more efficient. Really Interestingly, it said something like, you'll have, you're doing too many 20 minute introductory calls that aren't necessarily leading to. For work. So how wide. How about creating a, you know, a questionnaire so that when people come through to you for a call, you've already vetted them. And I was like, God, that's, you know. And obviously I would have thought, could have thought of that. In fact my friend suggested to me the other day, but I just thought it's amazing that Claude has just been able to look at my, the way I spend my time. It said to me, you probably need to do a bit more exercise. So it's like I'm not, you know, often I'd have like yoga classes. In definitely the last few weeks I've been so busy, there's not been any yoga classes in my, in my calendar. So it's just, it's pretty incredible what it can do and just the different angles that it can look at your time from. You know, not because I asked it how I can be more efficient, but I could ask it how could I improve my well being. And it may well say, actually you need to put 10% more time into going to yoga or going running or whatever it might be. So that's pretty life changing. So I found that really good. So yeah, how I spend my time. And then another thing I Tried it for the other day. I get so many AI newsletters and I love reading them but the last few weeks I've been so busy and I just said to me, can you scan my AI newsletters that I've received in my inbox and give me a summary of each one? So it just said, you know, this is this one.
- [33:52]
Daniel Rolls
I love that, that's great.
- [33:53]
Kerry Harrison
Yeah. So it just meant that because I haven't had time, it's just summarized the newsletters that I've had through in the way that it thinks is most relevant to me and then what I would do then because I've been so strapped for time, I probably now I've got this summaries, I'm going to go, actually do you know what? I'm going to read that one and that one from top to bottom because I think that's going to be super useful for me. So I feel like those integrations which have gone in very recently could be so useful for work, for planning for your own personal wellbeing. So many different things from a business point of view that it can guide you on. So that's, yeah, for me that's been a real game, like a total game changer actually the last couple of weeks.
- [34:32]
Daniel Rolls
It's interesting because ChatGPT are going down that route as well and it's interesting to see which tools are they going to integrate into on how that changes things. So look really great introduction to Claude, but actually loads of ideas in there that applied to AI full stop. So thank you so much for those, Kerry, and the time you've given us. Tell people a little bit about what you do on a day by day, the services you offer and how people can get hold of you if they want to.
- [34:51]
Kerry Harrison
So I spend most of my time training people in how to use AI for their marketing. So everything from content to data analytics. Sometimes I do very specific copywriting, you know, all day copywriting for copywriting teams. So it depends what you need. I also speak at conferences and yeah, little channels, all that kind of thing. I've got a newsletter, it's called Minds and Machines, it's on substack. I go in there and I give tips and keep you up to date with the latest news and normally share some of the things that I've learned and I'm exploring. I'm on LinkedIn, Kerry Harrison, so you'll find me. I talk a lot on LinkedIn, not just about AI and all the incredible things it can do, but very much about the human, how we can keep thinking how we can stay creative, how we can nurture everything that makes us human. I just feel like, as you said earlier, I feel like that's going to be incredibly important. And outside of the AI, I'm also a yoga teacher and I run women's circles in the woods. So this next week I'm actually running a retreat down in the woodlands near Salisbury with a really super experienced retreat host. So off pretty much off grid, working with analog creative practices, writing with pen and paper, sitting around a fire. So I do all of those things too. And so somehow my whole life is all just trying to smash these two worlds together of high tech, but also just what it means to just sit on a log around a fire under the stars and to just go, right, how can we bring these two together? Because for me, they feel like they're two sides of the same coin. Almost. Brilliant.
- [36:20]
Daniel Rolls
Well, we'll put all of that into the show notes. Thank you, Kerry, so much for your time. Some brilliant tips there and please do let us know what you think and your takes on all of this as well.
- [36:27]
Kerry Harrison
Cool. Thanks, Daniel. It's been lovely to be up with.
- [36:29]
Daniel Rolls
You for more episodes. Resources. To leave a review or to get in contact, go to targetinternet.com podcast.