Creating AI Assistants Using Claude Projects

Key Takeaways

now with AI assistant and what we're going to be talking about Claude projects in particular we are finally reaching that point where we can actually get consistent outputs um so we can start to fit them into our business on a day-to-day uh basis today I am very excited to be joined by Kyle Balmer if you don't know who Kyle is he's an AI business educator and consultant his newsletter is the prompt entrepreneur designed to help business owners start and grow with AI he's also the founder of the AI business breakthrough Academy Kyle welcome to the show how you doing today hi it's great to be here Michael thank you so much for having me I'm super stoked that you're here today Kyle and I are going to discuss how to create AI assistance using Claude projects now before we get on that rabbit hole and it's going to be a really fun discussion I want to hear a little bit of your story how in the world did you get into AI start wherever you want to start absolutely well we can go quite far back but uh I'll keep it relatively brief so my journey with AI and my entrepreneurial background has been relatively mixed I'm sure like a lot of your listeners um so I actually come from an entrepreneurial background and a marketing background and I've transitioned into AI over the last couple of years uh from an entrepreneurial point of view I've started over 30 businesses I've sold several including a television station in Vietnam that's a story for another time another podcast we won't talk about it now uh but my main focus has been digital marketing and I've run an agency in digital marketing for about a decade or so uh I actually used your guides about 10 years ago when I was first getting started when we were working out our kind of service offerings and stuff we would go into your Deep dive gues and be like guides and be like wow this is you know fantastic stuff so being with you today is really exciting for me um we ran this digital marketing agency for I'd say five to seven years and it was going well um but we became a little bit complacent and in November 2022 we had the release of chat gbt or the public release of chat gbt the real turning point in artificial intelligence uh being publicly available and at that time I started experimenting with a few workflows kind of messing around using it to write Facebook adverts for example but never really crossed over and got really excited about it I could see the potential and some of the potential risks uh for my digital marketing Mercy but I didn't jump in uh feet first at that point however at the beginning of 2023 we actually lost two large clients um you know these things happen we'd become a bit complacent and unfortunately we'd put too many eggs in uh one or in this case two baskets and um so we took a large hit to our um to our incomes and to you know our lifestyles and also the company as a whole so it was the coalescence of these two things the emergence of AI in the background making me think hm there's something here plus the push of losing two clients very quickly basically made me um look at artificial intelligence a lot more closely and for the last year so this was the beginning of 2023 so the last year and a half uh sorry year and a half I've been really throwing myself into artificial intelligence the main vehicle for that has been via prompt entrepreneur that is my newsletter the way that I learn things is I will uh I tend to write so I started to write publicly about what it is I'm learning and what can be used especially by entrepreneurs and people in marketing um in particular so that became my focus every single day um six days a week I was writing over a thousand words on artificial intelligence and specifically how it could be applied um to actual business problems because I saw there was a lot of um newsletters and information about the latest model or uh the kind of the hype around artificial intelligence but very few people were Translating that into the entrepreneurial world into the marketing world and saying okay that's great but this is what we can actually do with it and that's been my focus really for the last year and a half outstanding so um bring us up to speed kind of where you are today you've got your newsletter um what else are you doing oh wow that's a big question um so the newsletter is just hit a year uh we had our first anniversary about a month ago we have got 60,000 subscribers which is fantastic I also get to now fly around the world giving workshops on artificial intelligence to some pretty large companies uh and tech companies which you would not expect but um every company right now needs this kind of information about how they can start to leverage AI in their company um I am also helping other people to provide my workshops around the world as well and that's been very successful over the last um few months as well so it's been it's been a very busy year um there's a lot of demand from businesses globally in every single industry every single Niche about how they should be using artificial intelligence so I've just been sitting at that border between artificial intelligence and Entrepreneurship in business and helping to cross that divide sweet well I'm super stoked to have you here today um there are plenty of marketers and entrepreneurs that listen to the show and they have probably not yet embraced the concept of building an AI assistant for lack of better words um sometimes we call them custom gpts in this case we call them projects because we're going to be talking about Claude but why what's the upside uh to this audience that's listening as to why they ought to maybe consider building an AI assistant so I think AI assistance as a general term it finally fulfills the promise that we were we were given back when we first got uh chat gbt the public release a lot of people thought that we'd be able to use these AIS to uh save time on repetitive tasks maintain consistency of output to basically become an AI member of our Workforce and I think early on um people would try with these tools and the quality just wasn't there the AIS weren't able to consistently produce an output that could be used in a workflow and therefore I think a lot of businesses especially early on the people who experimented with the the models early they would bounce off they'd be illusioned because so much was promised and that confidence was betrayed um so business owners and marketers tried the early models didn't get what they were expecting and bounced off now with AI assistance and what we're going to be talking about Claude projects in particular we are finally reaching that point where we can actually get consistent outputs um so we can start to fit them into our business on a day-to-day uh basis and it's actually becoming useful I think for the first time for a lot of companies um there are obviously custom gpts which came before what we're going to be talking about today has taken that kind of idea and run with it and has a much higher output much more consistency and is able to uh match your tone of voice which I know in marketing in particular is extremely important yeah so let's talk about Cloud projects um why Cloud projects um versus chat GPT Uh custom gpts what's your what's your take on it I've gone down the rabbit hole of cloud projects I've not gone down the rabbit hole of Uh custom gpts but I know you've also gone down the rabbit hole of probably both so what's your take on Claude projects as to why so taking a quick step back Claude is actually a competitor to open ai's chat GPT unfortunately a lot of people don't really know about Claude um I saw some data recently um people tend to associate chat gbt with AI they're becoming synonymous in the same way that Google and search engines are synonymous now and unfortunately that means a lot of people are ignoring Claude um so Claude is a model from a company called anthropic um and personally it's become my go-to it's now my Workhorse that I use with pretty much every task um I know you've been using it yourself and you can probably talk to the the quality of the output it's also really good at coding and generally outperforms chat GPT in many many um different roles but people just aren't using it because chat GPT has become the default what we're talking about today though is something that's relatively new to Claude which is called a Claude project um and it's a bit like a custom GPT which in open AI chat GPT is a way to encapsulate a uh a set of information that you upload so data documents um blog articles social media posts whatever it is you can upload a set of information and then have the custom GPT or the clawed projects work on that information for you which is really powerful when we are building AI assistance because we can give them knowledge we can give them a knowledge base I love it um and let's talk a little bit about kind of um why Cloud projects might be better I mean it's got some unique advantages and a couple limitations as well absolutely and I'm so glad you brought up the limitations because as with all of these things we do need to address them before we run ahead first in and expect these AIS to do absolutely everything for us there are still limitations so probably one of the biggest and it's it's a little bit boring but Claude uh has a much larger context window than chat gbt context window without going into the technicalities of it is basically the memory um how much information you can throw at this model before it starts to forget stuff from earlier in the conversation if any of your listeners have used chat GPT they've probably got to a point when if you have a very long conversation suddenly chat GPT is begins to give you bizarre answers don't correlate to the information you've previously provided that's because it's falling out of the back of its memory and unfortunately chat gbt doesn't tell you this it doesn't say hey by the way I forgot what we talked about earlier on it will just try to fill in the gaps and that's when we start to get hallucinations so Claude has a much larger context window we can throw a lot more information into it before we hit those problems and that's really important when we're building assistance because the more information about the task we can give it the more information about how it should be performing the tone of voice the brand guidelines for example uh the better the output's going to be so the context window while quite a boring technical reason is also uh very important in this particular case yeah and let's talk about what it cannot do um which I'll just go ahead and throw out there it cannot search the web and this is important why don't you talk about that a little bit yeah this is a massive limitation especially compared to custom gbts so uh chat gbt can access the internet whereas Claude will not it doesn't search the web for you so when you are providing information um to your assistant you need to take this into account if you want an assistant which is specifically built to search the web and find information for you Claude projects is not going to do that for you um it's not suited for this particular job so it's really important that we think about the scope um and what we are actually going to be using our assistant for there are reasons why this is actually I'm put an optimistic spin on this but there are reasons why this is actually a benefit when it comes to creating an assistant though because when you give the an assistant the ability to access all information in the world it's going to pull in IR irrelevant information because what it's drawing in from the internet is not necessarily going to be what's useful for the project whereas if you have a closed um capsule of all your information that you have provided you can tailor and make sure that the quality of the information you're uploading is High um so depending on the task this can actually be a benefit but obviously if you need your assistant to con connect to the internet to pull information from other sources Claude projects isn't going to do the task for you and it's a really important limitation to know upfront yeah and we'll talk about this a little bit later but the good news is you can copy and paste big chunks of information in you could take screenshots PDFs we'll get into all that stuff a little bit later all right so um let's talk about the kind of assistance we could actually create um with something like like cud sure this is always a difficult question to answer um whenever I'm asked by a business what can AI do generally the answer is like pretty much anything it's it's a very wide use technology it's a bit like asking what can we use the internet for um you know 20 years ago well yeah kind of a lot let's explore some creative ideas so people can at least wrap their heads around it let's uh go for that so I've I've actually come up with a a brief framework um I'm calling it the SP framework so it's scope priming uploading and narrowing scope is so important up front so the s for scope scope is about working out what you want the assistant to do like we already know it cannot connect to the Internet so we're going to remove that from the type of tasks that we would be building an assistant for instead we might want to do um something like have it help us write a newsletter so I've started to actually use Claude projects to write my newsletter whereas I've spent the last year year um despite being an AI guy despite being extremely Pro AI I have avoided using AI because the quality wasn't high enough um now with Claude projects I'm able to give it enough information I'm able to prime it in such a way that it's actually really good for becoming a co-writer for my newsletter um similarly I have another one to add uh we also use Claude to uh do the social Med examiner newsletter and we train um basically uh we train it based on um content that we provided for example the news section um will give it some information and we'll have it write summaries of news to be in our news section of our newsletter also we use it to write articles from all these podcast interviews so this actual interview from this podcast when you go to social media examiner.com 24 I mean a24 uh you will actually see that we used Claude we trained up Claude on um on our best content and trained it up on how to take the transcripts from this and write the actual articles um but keep going so here's a question for you why do you not use chat GPT for that is it the quality or uh some other reason uh because we've been able to train Claude um on our writing style and we feel like Claude is a superior writer as you mentioned earlier it's always been it's always been a better writer and I think Kyle it's because the data set that it's trained on is you know the Washington Post all the Amazon data uh let's not forget Amazon is one of the major investors inside of anthropic I feel like they've got a better data set to train on on on on English language writing and I 100% agree it's hard to um to objectively say it's a better writer but everyone I talk to especially writers as soon as they use Claude it clicks for them they're like oh wow yeah no this is much better and especially when you upload as you have done um your own content it's able to mimic and replicate the style much better than chat GPT ever would chat GPT has a bizarre robotic chat GPT style and it's very recognizable especially if you use AI a lot you know immediately oh that's chat GPT whereas Claude sounds human now I will tell you a little side note that I I will sometimes take Claud content and have chat GPT enhance it and actually chat GPT is excellent at editing um something that's pretty close but not 100% there and um lately I've been taking the claw content and asking um cat GPT to kind of just simply the word enhance it and it just makes it slightly better and then I take it back into Claude And I say Claude what do you see is different about this that's fascinating have you tried to use Claude to edit Claude or that doesn't lead to I I have not yet I have not yet tried that because the problem there is that it might see its own results is already very good so go to a you know a different allows you to get that differentiation I've done a lot of back and forth between Claude and and uh cat GPT uh and a lot of the work that I've done and I find that they kind of they kind of enhance each other it's like having two different sets of eyes on the content and they find different things it's fascinating very cool okay so um other stuff you can do with AI that we haven't mentioned uh there's a million other things sure with assistance so social media post um Creator promotional email drafter legal document reviewer proof reader Ghost Writer basically I tend to when I'm working with clients suggest go through your business processes first find the tasks that are repetitive laborious um or take up a lot of time and these are the things you should be focusing on automating using Ai and this is where you should build an AI assistant um so I you start from the business task and then you combine it with AI um rather than just try to shove AI in wherever although a lot of companies are still trying to do that they just want Ai and they're not necessarily sure where they want that but I would just say start with what is already quite repetitive and taken up a lot of time and see if you can build an assistant that will help you there yeah I'll just add a couple quick things in here um as a as a marketer also if you can train it up in your products for example I've trained up uh a project on social media marketing world I've given it all the um the sales page data screenshots of the sales sales page emails that we've written in the past and I created a project so it kind of understood what social media marketing world was I've I gave it a lot of background on like who the primary customer is and all that kind of stuff and I know I'm getting ahead but so anyone is listening if you are in marketing and you have a product that you're marketing which you almost always are you could quite literally have uh a custom I'm sorry A A A Claud project trained up to be kind of your your um set of eyes you're a creative advisor on anything you create related to marketing related to that product so you know let's just maybe make that an easy way forward for any marketer listening right now so let's get into your um once you figure out so so the first part of your process is deciding on a role right so does this mean when we're setting up a project that we should set up a project to be an expert on our product and have no role or would it be better to have a specific role what's your thoughts on that like email so this would be going into priming uh specifically uh I think very very important is um one of the biggest mistakes I see when people try to build AI assistants whether it's custom gpts or clawed or doesn't really matter is that they will try to build an assistant that does absolutely everything it's really important to build an assistant that does one task really really well um because this is going to be apparent um later the data that we upload to it and the instructions that we give it the more precise and specific they are the better the quality of the output and it's very tempting to try and create a marketing assistant that will do all of our marketing tasks or a product assistant that will deal with everything to do with product whereas we really want to keep them specific so we get higher output U higher quality outputs so that's really important then one distinction from what I just said is hey if you do like five different tasks related to your product you might want to actually have the same data set in five different Cloud projects that's really what I'm hearing you say right instead of having one project do all those tasks so that you can get that role super specific like Facebook ads expert um email marketer dot dot dot right absolutely yeah they should be individual projects um either with similar information about your um company about your brand about your tone of voice there's going to be a base layer that's going to be similar for each of your projects but then with have additional information specific to that project specificity is always key here I'm trying to do too much trying to a jack of all trades assistant will lead to disappointing results so what else do we need to do when we're priming sure so for priming um I tend to use what I call my risen framework so it's R ien so first is the role that is defining the specific job of the AI assistant this is just saying act as and we're giving it a certain specification um of what type of job it should like an email marketer for example absolutely yeah because the thing about AI is it can act as anything so we need to limit that scope we need to tell it okay I know you can do everything but I today I want you to do this you're going to act in this particular role and that helps to focus um after that is instructions so providing detailed guidance on how to approach the task I like to think of this as if you had hired um a new employee someone onto your staff or maybe a freelancer you're not just going to give them a task and say off you go like work it out you're you're going to give them detailed instructions you're going to give them a step-by-step guide um so that they can go and do that work it's like giving a standard operating procedure to a new hire we need to give the same level of detail to an AI otherwise we can't expect quality results um and I think this happens a lot with AI where people will give it an extremely generic task like write the company report for 2024 and then be disappointed when they get a bad um get a bad output but in reality that's because you didn't give all the information that you would have given to a human the AI is not going to do any better um than the human so instructions is the next step just giving detailed guidance on how to approach the task the next part is steps so that is specifically breaking down the instructions into clear sequential steps so literally a b CDE e f these are the steps I want you to walk through um in order to complete this task and then I like to finish off with the end goal e this is clarifying and telling the AI what success looks like we're actually saying this is what a successful output looks like and potentially even this is what a non-successful um output looks like we can give it examples as well saying this is a good version of a you know good high quality social media email yeah an email um whereas this is a poor one and it's going to be able to learn from that and then isn't there a last part too narrowing there is a last part in the Risen framework which is narrowing however when we are building an assistant in particular we can actually do this afterwards so there's going to be a process of feedback um which we can talk about in a moment where once we have built the basic assistant once we have got some outputs from it we're going to have a conversation with it again like if we were talking to an employee they've gone away they've produced our piece of work they've brought it back to us we're going to sit there and correct it we're going to tell them what's good about it and what's not good about it that's the narrowing process and it's about giving feedback to an assistant so that it can learn exactly what it is you want how much context how much outside of um we're going to get into the uploading of all the data and stuff here but how how long of an instruction set are we given when we talk about the role the instructions the steps and the end goal we're talking about a paragraph multiple paragraphs so it would depend on the complexity of the tasks however if we come back to the point we just made we want our task to be a sing single focused task so if you find that you were given it 20 pages of instructions chances are that's multiple tasks that could be broken down over multiple assistants so if you do find yourself in that position where you are uploading like a whole standard operating procedure or a whole manual for you know customer service or customer relationships chances are you're throwing too much at it and it's going to give you uh a poor output so really we're talking about less than a Page worth of instruction that should be sufficient to provide the priming um for the assistant at least to get started okay so a couple quick ground rules before we get into some of the specifics related to Claude here number one is you have to have a paid account with Claude and that's currently I believe $20 for a professional account per month uh that's the only way you can use projects and it can get a little confusing when you first set up a project and I found this out the Hardway um so let's talk a little bit about like from your perspective what do we need to do when we set up the project so that we're setting ourselves up for a good output so the first step is going to be working out the scope then we're going to put together our priming instructions we're then going to upload content into Claude now the I believe the difficulty you're referring to here is there's a complexity in the UI where it's not quite clear where you should be uploading your documents um I think Claude could certainly improve on this when you create a project there is a space for the files that are uploaded to the project so these are your you know your blog articles your brand guidelines um your tone of voice documents they can sit at the project level however Claude also allows you to um upload those any files at the chat level but it doesn't necessarily translate the information between the project level and the individual chat level it can draw information from the project level down to the individual chats but it can't take information from the chats up to the projects it's a bit of a limitation it takes them getting used to um and I think they could do a lot better on their design to make sure that's clearer yeah and just for anybody who has a cloud account or chat GPT account and you're used to just operating in a single thread um in Claud there's this thing called project knowledge which is off to the right and that's where you can set up custom instructions and add content so presumably these custom instructions are what we were just talking about in the prior role right like this is you know your uh your acronym that we were just referring to right what's your role instruction steps and end goal that would be set presumably in the custom instructions not in the actual chats if you put them in the chats you're going to learn the hard way that when you create a new chat inside the project that chat doesn't know what you talked about in the other chat it only knows what's at the project level and that's kind of an important discovery that I made uh just before getting on this this interview today and that's really important for everybody to understand so um what can we uh let's talk about how we can train the model like what kind of information we briefly gone after a little bit of uh of it I mentioned briefly but you know what how how much information do we really need to put into the project so generally the more the better the more information we give it the more it can work with that said it needs to be very relevant and high quality data just throwing information at the model for the sake of it doesn't really help we want to make sure that anything that we're uploading is going to be relevant to the task that it's doing so there is a a very understandable um impulse to want to give it absolutely everything about your business every single time regardless of the task that may not help though um because we want to keep it focused so really this comes back to the question of what is it we want our assistant to do and then again thinking if we were talking to a human being and if if we were providing them with instructions if we were providing them with the relevant kind of knowledge base the relevant data what would we give to them so we wouldn't necessarily give them the annual reports if we're asking them to do social media posts for example it's just not relevant to the task at hand yeah so um you talked when we were prepping about pre-processing um information and kind of you have any wisdom or insights as to kind of how we should discern what to put in there and what kinds of things you normally put in there when you're creating project sure so the main difficulty is going to be running up against the upload limits um so one very useful thing is there is a progress bar which shows you how much of the knowledge base has been filled up so every time you upload it say Okay 10% is gone 20% is gone that's quite useful um if you are uploading let's say information from a website you'd want to go ahead and strip out all the HTML and CSS and any kind of metadata that's connected to the um the actual information you want to provide the model just because we need to keep that memory clear and anything that's not relevant we could just strip out um so that kind of pre-processing just to make sure that the data only contains what's useful for the model um I think is going to help because it allows you to fit more relevant data within the memory yeah I also ran into some limitations with file sizes um I think 10 megabytes 10 megabytes per file yeah which can be really easy to hit if it's a massive screenshot you know what I mean so you might have to take those screenshots and Save compress them or save them as jpegs or copy and paste text instead of a screenshot um so but do you have any sense of what the you can put a lot of data in there right it's just um the file size could only be 10 megabits 10 megabytes at a time so you can put multiples up there or is that not true correct so 10 megabytes at a time and you can upload five files at a time but you can then upload another five another five so it's uh all going into the same memory pool um so you can get a significant amount of information in there over the last um year for my newsletter so when I'm using my newsletter assistant I have 300,000 words worth of information that I'm able to uh to draw on from there and that's why I'm able to get very high quality results because I have so much data that I can work with Okay so let's review kind of where we're at right now if you don't mind like um like we're starting to create a cloud project and we have identified uh we we've gone in we got a cloud account we created a custom project we've identified a unique role for example we're just going to stick with this email marketing role where you're going to help create emails um and we've identified the kinds of um steps right the instruction steps and end goal now if we don't know what kind of the instructions and steps should be do you recommend having Claude Andor chat GPT assist you in identifying the steps if the steps aren't obvious to you you've just done it by routine instinctively absolutely so I would recommend for this going outside of your project um so that we don't confuse the project by getting too meta with it we want to ask how we can best give information to a project so that's better to do within a separate chat just to separate out um so it doesn't get confused about what we're talking about but absolutely U so I find now whenever I have a question about pretty much much anything any process I no longer go to Google I will now just ask an AI how it is what are the steps to get this done um so in this case this is exactly right you can you can ask it how best to condense um image files for example how best to um chop up a database so you can upload it into 10 megabyte chunks and it will give you instructions about the best ways to do that yeah and the truth of the matter is from my experience that whether you ask it in a project or out of a project it's still clawed so it's still smart it's going to do its best to answer um whatever questions like for example if you want to send 10 emails over 10 days and you want it to help you decide what the topics ought to be um it doesn't really matter whether you do that inside the project or outside the project but I would imagine if you did it inside the project it'd be better because it would know at least what the product is and maybe some of the common it could read the data that you've given it and try to discern what some of the common objections might be to your product where it would have to guess on it if it was outside the project right that's true yes no absolutely in that case it can help you to create the priming instructions based on the information you've given it already um so yeah you can say my end goal is to write a series of 10 welcome emails from my marketing campaign for my product you have the information about the product give me some um potential Frameworks I can use for these 10 emails or give me five different variations of 10 email campaign and then you work from there yeah and I I've done that exact thing where I said here's the start date here's the end date we want to do multiple emails on the end date um and I just said what do you recommend and it came up with a really good plan and then I started working each one of those emails kind of one at a time and um and I find it really interesting so this is where okay so we let we we've built the project we've trained it on the basic data now we're about to like start using it and I guess this is where we get into this narrowing concept right so talk to me a little bit about how once you're starting a project um how we can kind of refine and iterate to make it better for what we want so it's already got the priming instructions it's already got the uploaded data so the first thing we do is we just ask for an output so if we are doing an email campaign for example we'd go ahead and ask for the first email in that campaign um and then we are going to as a human we're going to review it and then we are going to provide feedback on its output and this is how we start to train the model to get better at knowing what exactly we want because we're going to go back and forward we're going to say that first paragraph is a bit lengthy or you need to punch up uh the ending and we're going to start giving that feedback in human language to the model and it's going to be able to use that to redraft uh we're going to give more inter uh more feedback third draft and then we're going to continue to iterate again and again so sometimes my newsletter I will go uh back and forth about 20 to 30 times each time um giving feedback as if the AI assistant is my ghost writer talk to me about how you do that because um I mean there's a million ways you could do it but I'm curious what your process is right let's say you're having it right the first email and there's something about it that's off what do you tell it specifically to do so I always recommend you just use natural human language the AIS are smart enough to understand that so even if you don't necessarily know what's off with the email you can say I don't like that there's something wrong with the first paragraph and you can give it you know hints like oh it's too long it's too short or it's too salesy or it's not salesy enough and it's going to be able to create new drafts based on that um so in the same way you would talk to a person who is drafting up your emails you can give similar levels of feedback uh to the AI and it's going to be able to work out what it is you want uh it's much those it's more patient so if you ask for 20 redrafts it's going to keep redrafting for you it's never going to get upset yeah and I'll give you an example like um first output I got out of an email in a project was very formal it didn't match my tone of voice and I said make it more casual in the voice of Michael stellner assuming it knew who I was um and it got really casual so then I had to say okay find a happy medium between the two and when it found the happy medium between the two that third iteration was much closer to kind of what I was looking for so I think this is really important for everybody who feels like you know you know what it's like if you've ever outsourced to a writer right or you've been a writer yourself as as I've been if you don't like it you might be like oh this thing sucks right that might be your natural disposition but you got to keep working it and you got to keep working it and then I've been able to say okay whenever you sign these emails sign it this way Michael stellner comma founder of social media examiner you know all on the same line right and I just find that I have to keep the more I tell it like this is you know don't use these kind of words uh use an emoji in the subject line it's just one of those iterative processes that goes and goes and goes but I've even found and I'm curious if you've done this like um maybe there's a sentence or a paragraph that seemed completely off the Mark um I've asked it to rewrite just that one sentence I mean I don't know how far down the rabbit hole you go with these with this editing when you're doing this so I will as I said for a newsletter I'll go through about 20 or 30 different rounds so some will be small things like you know you missed off the uh the introduction some will be larger like I want you to reshuffle around these sections um so going back and forward what I will then do when I'm am happy with the draft I will copy and paste out into my email uh software I will manually make changes I will rewrite it I will get it ready for publishing to my standards that's that will go ahead and publish that that's fine I will copy the final version back into my Claude assistant and say hey this is what I landed on so this is including my human edits learn from this and it will go through and compare to the last version um with the final published version and it will summarize okay these are the changes You' made I will include these in the future and this is why using the AI assistant is really powerful because it allows us to have these running conversations so when I go back for my next newsletter it's going to have remembered all of that information whereas if we are doing this in individual chats like on chat gbt or even Claude we're going to start losing that information between the different tasks but within a project we get a much larger um context length we get um a much larger a much larger um upload pool as well so that allows us to have this continuing conversation and to make it a true AI assistant well and it's my understanding also that with Claude um I think they have a teams um I'm almost certainly have a teams uh version where you could potentially share your projects with other people inside the company I feel like I've heard that before I don't know if that's true have you heard that to be true yes so it's not a different level as soon as you have the U premium membership you can create projects and projects can be shared within your team you can publish them okay so wait is this with any paid membership then yeah you mean with the professional oh interesting because I don't have I'm the only one in my company well I have other employees that have their own claw accounts but I haven't figured out I haven't upgraded because I felt like it was a little more expensive to have the teams account just a little bit more expensive and for whatever reason I'm being cheap and I'm not doing that but what I'm hearing you say is could share projects with other people the projects can be shared yeah so they're really useful within the team so once you've created your assistant you can share that huh very fascinating um is there anything that you've discovered have you also used chat GPT custom gpts yes um but coming back to the technical reason the context length it doesn't allow you to upload enough information for it to necessarily capture your tone of voice so I've never had um success with them I've always been disappointed also the fact that as we discussed the written output from Claude is just so much higher um so because personally most of my tasks are to do with the written word so newsletter social media I just find Claude so much more Superior and that's why despite having written my newsletter for over a year I've never really used AI in the workflow up until now up until uh the release of claw projects and that's why I wanted to talk about it today because it's it's such a powerful tool that I don't don't think enough people are using have you discovered anything that Claud projects can do outside of what we've already discussed like is there any cool little I'm just curious if there's any little tips or anything that you've found that's unique to projects that that's maybe not just inside of Claude generally speaking and if you haven't that's totally cool I just um I kind of feel like it's this I mean first of all the fact that it can be private or public is kind of intriguing I did not know that um are there any other things that you've discovered inside Cloud projects that we've not yet discussed no I would say it it really is just the quality um that is astounding and it's so hard to communicate to people until they try it they actually go and try Claud um I'm not affiliated any way anyway but I do bully people into try and Claude um so I think it's not a necessarily a hack or a tip or anything like that just the underlying quality of the model is just so high that I think it's very important that people try it out there is something that I just discovered quite literally during this interview um which I did not know was there there's a capture screenshot button inside of Claude and I'm in I'm in Chrome and it allows you to pick any particular tab that you have open now that's kind of cool were you aware of that yeah yeah so you could you try that on your images that you trying to upload um although I know that you're trying to capture a whole page yeah uh sometimes which I don't think it's is going to be able to do I know it can't do that it can only do the the straight screenshot but the fact that it is even there that allows you to capture a screenshot is kind of maybe a little hack because I didn't even realize that there was that little camera thing there I've not yet tried using the mobile app have you found any advantage are you using the mobile app for Claud at all or no yeah it's a very slick app I actually do most of my newsletter writing on the mobile app which sounds absolutely wild but it's such a nice interface um that it's entirely possible to work with projects on a telephone um so I often write my newsletter on the bus Which not many people can say I'm sure wow how are you doing that on your phone I mean like there's not a lot I mean are you speaking to it it doesn't have a verbal interface like chat jpt does it or does no it doesn't no um so I'm primarily doing the rounds of revision so because it takes so many revisions um I might over a few days be going back and forth back and forward over a particular newsletter issue uh so just having it there on my phone and being able to pick up a chat that I've been having on the computer anywhere and to kind of go through its latest draft and say maybe you can change this maybe you know you can change that uh being able to do that on the fly on the move is really powerful are you doing anything inside of a Google doc and then bringing it into um Claude or are you doing the whole darn editing of your newsletter completely inside of Claude so I do the final edit in my newsletter um Tool uh in beehive but up until then everything is in Claude wow very fascinating Kyle thank you um first of all for answering all of my questions and hopefully opening people's eyes to what can be done with Claude uh projects if people want to discover more about you where do you want to send them sure so my social media I'm primarily active on Twitter and Tik Tok and I'm I am Kyle bmer um on both of those platforms um for the website I've actually prepared I am Kyle Balmer or just at Kyle Balmer on those I am sorry okay yeah cuz I wanted to clarify cuz you said I am so it's I am Kyle Balmer uh all right keep that's good clarification I can tell you work in social media and what were you going to say about your website sure the website so um because I got so fascinated in this topic after we first decided to do it I've actually written up a whole guide on how to go through this process um so I know we've covered it in kind of broad Strokes today but if anyone is interested uh I've put together a written guide it's about four or 5,000 words um about how to build an AI assistant so I'm going to make that available on my website so that is AI business breakthrough.com ssme for social media examiner awesome Kyle thank you so much for coming on the show and sharing your your insights and wisdom with us today thank you and thank you for having me