S2. Ep29 - Set Up Claude Once, Use It Everywhere: Projects, Skills & Cowork Explained

Katie: Welcome to the AI Automations for Business Podcasts. We're your hosts, Katie and Null, and we'll be discussing how you can use AI for your business along with the latest news, updates and automations to help you stay ahead of the curve, allowing you to grow and scale your business more efficiently. Please be sure to subscribe

Noel: and I hope you enjoy this episode.

Katie: Hello and welcome back to another episode. Hi, hello, I'm Katie. And as always, I have Noel. with me today. Hi, Noel. How are you doing?

Noel: Well, I'm doing absolutely fabulous again this week. Just very, very busy with everything that's going on. How are you doing?

Katie: Yeah, all good. Thank you.

Noel: Good.

Katie: So we always start the podcast off with any news, any updates in the AI and Automation's world. So, Noel, what are those updates for this week? What do people want to know?

Noel: Well, I've had to write them down this week because it's been quite a... Few. I had to keep a track of them as I was seeing them. But I guess the first big one is, I know we've all been, you know, lots of people have been complaining about Fable 5's usage and it's not being very good. And at the end of last week, an Anthropic decided, hey, here's Opus Fife. It's cheaper than Fable and it's more powerful than Fable. And it won't go through your usage anywhere near as quick as Fable does. So, yeah, massive announcement. I've been used. and it lots in the past few days since it released. I can definitely say it's very, very good. It's a lot quicker than Fable 5. I was finding especially like coding projects, it was taking an age to get through things, whereas Opus 5 is accurate and fast, so just what I wanted. So yeah, really, really awesome release. Obviously, that's better than any other AI model currently on the market, which is pretty awesome. Well, apart from mythos, but yeah, we can't see that. No. We'll forget that exists for now. Okay.

Katie: It's not there.

Noel: Yeah, certainly you might as well. There are other, so there's two kind of related things. So this is kind of like with Open AI Ananthropic, maybe getting things slightly wrong. So I'll start with Open AI. They were testing their new Frontier model. They had it in like a closed-off environment. and they were they tasked it to you know show off its hacking skills and this agent was like I know what would be pretty cool you know to show off my abilities as I'm going to break out of this sandbox and I'm going to go and get things off of the internet to help me do a job and essentially it hacked the website of hugging face which is it's basically an open source website for open source AI models. And it went off and it grabbed loads of stuff from there and then bought it back into its sandbox to help it finish the task. So, yeah, the edge of ears, open AI, obviously hit the kill button. And we're like, well, this shouldn't have broken out. So it's obviously very good at hacking. But yeah, yeah, very interested. But I've seen that when I tested Clyde, when I first created the open source version. you know it has like its own file repository so you don't give it access to all of your files on your computer you know it should only access this certain working folder and yeah silly me I forgot to give it right access and yeah Clyde managed to work around that and then save it to my desktop and I was like ah that shouldn't be allowed because I haven't really put the guardrails at that point you know and it was like right they need to go in now to close it down to see it They're very clever these models, getting around things, which is, yeah, interesting. The other one on a similar note from Anthropic is, I don't think most people know about this one, is, you know, when you create like an artefact, or maybe you create like an app within flawed, within normal chat, there's like a little share option.

Katie: Yeah.

Noel: So you then get a URL, and I could give you the URL, Katie, and you can look at it and use it, whatever it is. Those links have been indexed on Google.

Katie: Oh.

Noel: Yeah. So they no longer get indexed on Google, but they have been, and they have been for some time, I think. So there's like people creating, you know, little apps that maybe has, API keys in there. There's been things for crypto wallet keys and addresses that have been, you know, found in these links, all sorts of personal information. You know, you might, like for us, you know, we could plan a holiday, you know, and it could have, you know, how much money we're going to take, what currency, where we're going to be, where and when, you know, and I could share that with you, but anyone could see it.

Katie: Oh my goodness. That's literally like my worst nightmare.

Noel: It is. Yeah. I mean, I've never used the share feature, thankfully. But yeah, I was like, I didn't quite read it. They would do exactly that. So yeah, I think they've stopped it now, thank you.

Katie: Okay. I was going to say, is there a way that we can, like, prevent this? But you think that it's been solved?

Noel: Yeah, they've stopped indexing those links on Google, which is the big problem, I guess.

Katie: But yeah,

Noel: I just.

Katie: So really, it's just be careful actually what data. still goes into that? Yes.

Noel: The safest option would be to download whatever that artefact is or whatever that chat is and then send it by. Yeah. So don't use their share

Katie: it directly from.

Noel: Yeah.

Katie: Okay.

Noel: I thought it was quite an interesting problem that one. But anyway. An interesting problem. Hmm. Understatement.

Katie: Yeah.

Noel: there is a new image model coming soon. This got me quite excited because before we went all silly about nanobananas and, you know, chat GPT images and creating, you know, model figures of people, the leading model was from Black Forest Labs called Flux, and that was excellent at, you know, photorealistic images. And it was really one of the first ones that was actually very good. but they're going to release in a few weeks I believe they're going to release Flux 3 and I've seen the previews and it looks incredible so it's not just going to be images it's also video and video with audio as well so yeah I'm really excited to see that one coming out I think it's going to be pretty awesome and probably kick things like nano banana to the curb a little bit maybe yeah it all looked very accurate Like the, I get, with most things, these companies will cherry pick the samples and whatever. But I've not seen any crazy sort of videos and stuff with things going wrong. So, yeah, it's interesting to try that one out.

Katie: Mm-hmm.

Noel: And my last bit of news is about Substack. So.

Katie: I was going to ask you about this because we had this conversation a couple of days ago. And I was like, surely we need to mention this on the podcast this week.

Noel: We do, yeah. I guess if no one's ever heard of substack, it's a social media platform. You can have like your mailing list in there. You can earn revenue from paid subscribers. There's like a social media feed where you can post notes and things like that. So it's very, you know, it's very writer focus is their main sales pitch.

Katie: Yeah. So like you can't post like, like you. wouldn't create videos to post on substack. It's all about writing.

Noel: Yes.

Katie: You can go live and you can host like calls with your subscribers so you can have free subscribers, paid subscribers and your subscribers. But yeah, it's mostly a text-based platform.

Noel: Definitely.

Katie: And it will show you different people based on the interests you have, which I really like.

Noel: They also have a really cool algorithm as well, which allows you to grow a lot quicker than you would do on, say, LinkedIn as an example. Yeah,

Katie: yeah.

Noel: But the reason we're talking about it is because they're the first social media platform that I know of that have now added in AI text detection on all of their written content. So this is something that was released last week. And basically in the notes feed, you can hit on the little three buttons on a post, and then you can then go, right, scan for AI text, and it will give you a percentage score. So if that note is less than 100 words, it doesn't bother. It's only 100 words more. Every written bit of content on the platform will get through the AI detection. but what people are finding is now this detection isn't particularly infallible you know it does make a lot of mistakes I've posted this stuff which just comes straight out of Claude and it's kind of 100% human and it's like well that that's not true because you know I've got the receipts for it in my Claude account or it could you know score things which are AI which aren't AI it's something which has been handwritten so there's a lot of upheaval about it on their platform. And yeah, I don't know, I hope other platforms don't go down this sort of route because it kind of penalises those that actually write the content manually. Those talented writers that are on the platform, like some of their stuff is being, you know, put out as AI generated. And they're like, well, it isn't. And there's no review process either. So the score is the score. You've either got to rewrite it and hope for the best. Or you just go right with it.

Katie: I just think as well, like you've, you've just got to say to yourself, well, actually, do I enjoy reading this content? Yes. And then therefore, you've got to think, well, how important is it if I know if it's original or if it's AI? And then I just think, make up your own mind from it. Yeah.

Noel: But as chat GPT would say, here's the kicker. when they announced the update there was one little bullet point which I spotted in there and I was like, that's interesting because what they're going to do is at some point they're going to put in an option. So readers in their preferences can tick a box and say, I do not want to see any AI generated content.

Katie: Oh, God.

Noel: Which is fine. That's a personal choice. But for those writers that are being penalised, their content's going to be hidden.

Katie: So, yeah.

Noel: Yeah, it just all seems a bit, you know, self-defeating because, you know, people are earning revenue on the platform, which is paying substack in royalties. And, yeah, this content is going to be, well, technically, I guess, shadow band, really, is there, is a way of putting it? You know, it's just going to silently disappear and never get read.

Katie: Well, not everyone will be ticking. you know no AI but the thing is what is heartbreaking is the people who are writing everything themselves but it's being flagged as AI and then there's people who will then say I don't want to read anything from AI I feel like that's the problem I think they need to stack need to make sure that whatever program or software they're using is actually working 100% otherwise what's the point of having it?

Noel: Yeah, well, I had to check with Claude about this and basically there's no, there's no way to get it 100% accurate with text. It's impossible. You know, they're fighting and losing battle because these models are getting better at writing humanised content. So it's like even today that, you know, these algorithms aren't good enough to be accurate. And it's quite interesting on the website of the provider, they have a bit about education. So I'm sure there's people that listen to this podcast have got children, you know, so I think it's kind of interesting that their homework could be graded through this system because they target education universities and whatever to check the work. But if you get a false positive or false negative or whatever, then, you know, they could be hauled up and say, well, you've written it with AI and when they actually haven't. So, So on their website, they said they're 100% accurate. It should be believed. And then in the FAQ on the same page, it goes, yeah, but this shouldn't be the sole evidence for like a disciplinary. It's like, well, what is it? Yeah. It's either accurate or it isn't accurate.

Katie: Exactly. I feel like I get what they're trying to achieve, but until actually the technology is available to make sure it is 100%. Then I think, yeah, don't bother. I mean, what's happening on substack right now, I'm not even going to believe anything. I'm not going to be ticking no AI. You know, I'll leave it all open because, yeah, if we're not 100% sure, then I could then be missing out on reading blogs or, you know, other things from people

Noel: that I

Katie: actually enjoy following and, you know, reading their things.

Noel: so yeah exactly yeah yeah

Katie: okay interesting yeah

Noel: fun week yeah okay

Katie: so this week we've actually had a question from long-term listener and friend of podcast phil who is all the way down in Perth Australia and she asks how can you set up Claude Skills for a membership that includes all the different areas of running a membership. So like social media, emails, content, community, customer service, so that you're not having to re-enter the same information over and over again.

Noel: Great question.

Katie: Great question.

Noel: Yeah, yeah. I think it's one that, you know, every business owner will come up against when using AI. So the easy answer, I guess, for this is using projects. So within Claude and ChatGPT, there are projects. You can collate and gather all that information. You can then have chats within that project. So they're all hyper-focused on exactly, you know, those areas that you wish to not constantly repeat. You know, I get that. You know, it's very annoying, isn't it, with AI? I've got to re-go over the same point you did last week. So, yeah, the first step is setting a project. Within these projects, you can set instructions as well. So you can see that as kind of like the system prompt for an AI agent. So if there's anything you want it to focus on or don't want it to focus on or do, you know, that's the place to put it in. You know, I would spend quite a bit of time in those instructions,

Katie: you know,

Noel: because that's just going to save you. lots of time in the future you know you're not having to rehash things every time if you do find that you you know you are coming across things that you don't like you can always go back and edit the instructions so any future conversations are a bit more accurate but yeah projects definitely the way to start so you you could have you know I guess for me like I would see like a project in my business is kind of like you know it's a project for one client that and then another project for another client kind of thing. Yeah. But you could also see this as like certain verticals within your business. So it could be your marketing projects, your substack projects, your community projects. You know, you could have multiple setup which are hyper-focused and you can use at any time. It does mean you do have to switch in and out of projects to do stuff, which isn't, that's just a user experience thing. But yeah, if that's what you need, that's the way to go. And I guess to make it even better is to use Claude skills. I can't remember the terminology in chat GPT off the top of my head right now. I don't have a chat GPT account anymore, so I can't go and check. But you've got skills within Claude, and basically they're just kind of like your process instructions. And your project can use those skills to get the things that you need right. first time every time. And you can describe them. You know, you can tap away and say, well, this is the skill I need to create. This is what I need to do. Fine, it will go off and create it, and you can then use it in the project. But one thing that they released this week actually is a thing called recorder skill. So for me, we're creating skills. I always find it quite difficult because you're having to type everything out or dictate it somewhere and you might forget things, things like that. Whereas with record a skill, it will record your screen and you know, you could be a document, you could be in a spreadsheet and you could go, right, well, this is where I get this from. This is why I want this to go. And it takes screenshots as it goes and transcribes it and create steps. And then once you've, you know, recorded what you need it to do, it then creates a skill based on that, which I found incredibly useful. You can use it in the browser as well. So if you want to click around websites to do stuff, it will watch you on that website and then create a skill based on that. Yeah. So really, really powerful to use skills within projects. So that's kind of how I would tackle it. There's lots of other things you can add in. You can add in documents for context. You can add in links, which, you know, maybe to like sales pages and things like that, or copy from sales pages, all of that can go into projects and then you would never have to re-teach AI ever again how to do that particular function. So that's how I would tackle it, I think. Yeah,

Katie: okay. I think that's a good solution, and I love that. You can, you know, take Claude through your screen and documents far. I think that's really helpful.

Noel: Hugely, yeah. I didn't know I needed it until I tried it out. That was like that. That's actually really awesome because we're only human, aren't we? We're always going to forget something when we're typing something out. Of course. Yeah.

Katie: And is that available on free accounts or just paid accounts?

Noel: Great question. I think it's available on all accounts for Claude. It's not on chat GPT. You're thinking, but have at least the minimum. There's the Go plan, isn't it? It's the $8 plan. So I think you need that to get projects. But also, actually, within projects in Claude, you can also use co-work and have scheduled tasks as well. So if you've ever used co-work where it can access your local files and, you know, do complex tasks, you know, autonomously, that can also be done within a project. So you can have all of that context and the automation to go with it, which is really awesome. Okay.

Katie: Good. Well, we hope that answers your question. And if you've got a question that you would like us to answer on the podcast, please send it over to us via email, hello at makeautomations.aI. And yeah, we'll try to answer your questions on the podcast. But that's it for this week. We really hope you've enjoyed listening to this week's podcast episode. And we will catch you next time for another episode very soon.