Leveraging AI

307 | Stop Starting From Scratch: Build AI Projects That Actually Remember with Loren Bartley

• Isar Meitis • Season 1 • Episode 307

Share episode

Use Left/Right to seek, Home/End to jump to start or end. Hold shift to jump forward or backward.

0:00 | 49:28

What if the biggest thing holding back your AI results isn't your prompts... it's your workflow?

Most people treat AI like a chatbot—opening a new conversation, asking a few questions, and starting over the next day. The result? Lost context, inconsistent outputs, and hours wasted trying to recreate work that's already been done.

In this episode of Leveraging AI, Isar Meitis is joined by AI strategist Loren Bartley to reveal a smarter way to work. You'll discover how to build AI Projects that remember your context, organize your work, coordinate multiple AI conversations, and become a true operating system for your business—not just another chat window.

Whether you're using Claude to manage clients, marketing campaigns, business operations, or strategic initiatives, this conversation will completely change how you think about working with AI.

In this session, you'll discover:

  • What Claude Projects are—and why they're one of the most underused AI features available.
  • How to build AI workspaces that retain context and deliver consistently better results.
  • Loren's "Command Center" framework for managing multiple AI conversations without losing track of work.
  • How AI Skills can automate project setup, documentation, and workflow management.
  • Simple organization hacks that make working with AI faster, cleaner, and more scalable.

Loren Bartley is an AI strategist, marketing expert, and founder of Digital Business Momentum. She helps organizations move beyond basic prompting to build practical AI systems that improve productivity, streamline operations, and scale business workflows.

Connect with Loren on LinkedIn:
https://www.linkedin.com/in/lorenbartley/

 👉 Learn more about building smarter AI workflows here:
https://aimegasuccess.com/commodore


About Leveraging AI

If you’ve enjoyed or benefited from some of the insights of this episode, leave us a five-star review on your favorite podcast platform, and let us know what you learned, found helpful, or liked most about this show!

Isar Meitis

Hello, and welcome to another episode of the Leveraging AI podcast, the podcast that shares practical, ethical ways to leverage AI to improve efficiency, grow your business, and advance your career. This is Isar Meitis, your host, and I have an absolutely awesome episode for you today. You've heard me several times before talk about projects, projects in Claude, projects in ChatGPT, gems in Gemini, and every now and then we mention how powerful they are, and they are included in every one of these platforms, so you don't have to pay anything extra. The reality is most people never created a project. Some people dabbled with custom GPTs, uh, and that's about it. Projects are absolutely awesome. There are these mini universes of context with instructions, and they are extremely flexible, and they can do more or less anything you can imagine in your business. You can run a specific client in a project. You can run a project in a project. You can prepare for a campaign in a pro-- Like you can do many, many different things. You can do financial work for specific things in a project. Like there's many different ways to use projects. The biggest problem is most people don't know how to set them up properly. So many of you probably never created projects, and those of you who have probably have done what I have done, which is I gabbled a bunch of files and upload them as content and wrote two paragraphs of instructions, and I thought, "I'm really brilliant in creating projects." The reality is there's a whole different way to do that. Now, our guest today, Loren Bartley, is an AI expert with some very serious marketing background. She might have said it the other way around, that she's a marketing expert with AI expertise. Uh, but she has been running her marketing agency for almost 15 years. she's really, really awesome. She's really fun. She's an Aussie. We crossed paths, uh, both talking at, uh, Social Media Marketing World, uh, this year, and we really connected. And what she's doing is really, really brilliant. She's built a bunch of skills that help her build projects in a completely different level. So while projects themselves are very powerful, like I said, knowing how to set up a fully end-to-end, soup to nuts, everything including with feedback mechanisms and the right instructions and tracking of what's going on in the project is not straightforward. But if you know how to build a skill inside of Claude to help you build the project and manage the project, you can do significantly more with those projects. Now, as I mentioned, since I really like projects and I think they can be used for a huge variety of things, I find this very appealing, and I'm sure you will too. So In today's episode, Lauren will actually show us how this is done, like open the, you know, the curtain and show us what the magician is doing behind the curtain, and show you how you can build skills that can create and then help you manage projects that you can use for more or less anything in your business in a more effective and more impactful way. So I'm really, really excited to welcome Lauren to the show. Lauren, welcome to Leveraging AI.

Loren Bartley

Thank you very much, and that was such an awesome intro.

Isar Meitis

Um, yes This, this is what I do. No, I, I, I get the easy part. I do the intro, and then you get to do all the really smart stuff.

Loren Bartley

I love that you've positioned me as a magician, so I'm gonna go with that. Yeah. Yes. Yes,

Isar Meitis

definitely. I, I think for anybody who doesn't use AI a lot, you see what people are doing with AI, and it looks like magic.

Loren Bartley

It is. It is. It is, definitely. And you touched on a couple of really important things there when you said that, you know, a lot of people, they'll just open up AI, and they'll just start chatting away, and every time that they're gonna do that, they're almost like they're starting from scratch and, or they're bringing in too much context, or they've got all these chats all over the place where they're like, "Oh, I know I was having this really good conversation, and I know that I was meant to do something else, but I can't remember what it is." And they waste so much time trying to find that thing again, so they could pick up where they left off. And this is a problem that I had, and I consider myself an incredibly organized person. But for some reason, when it came to using my AI tools of choice, I was like, yeah, let's just, let's just be a bit more random than I, what I normally would be. And it wasn't until, you know, I was like a lot of people, started using ChatGPT and, and Claude was my thing on the side. And it wasn't until Claude became my main man that I c- started going, hang on a second, this is an opportunity for me to build this better. And that's when I started using skills and, y- creating a way that in a few clicks and a little bit of information, suddenly I'd spun up the instructions. I had track of everything. I had a system for knowing w- where I was with everything that was going on, and it was absolutely life-changing. I don't like to say game-changing. That's too much of an AI word, word. But it was life-changing. I'm gonna go that extra step. I,

Isar Meitis

I, I will take that. Yeah. So I, I think this is awesome, and I agree with you 100%. I think once you develop a system for anything, especially a system that then does the work for you or some of the work for you, it is absolutely fantastic. Uh, before we dive into the how to do this, let's talk in two minutes what the hell is a project and why the hell is it valuable to business people?

Loren Bartley

Yeah. So for me, I like to think of a project as like the desk that you're working on for a specific, project for a better w- better name. And as you mentioned before, the projects could be clients, they could be projects, they could be anything. And it... The reason that they're, that they're so important is because they help you f- they help you, one, be organized, and two, they help you start narrowing down that context window that we, can often blow out when we're using AI. And the importance, that I wanna focus on there is from a context window point of view, what we do is if we're giving too much information to our AI because we're just having a normal chat, and then in that normal chat we might have, you know, loads of files and relevant, ir- irrelevant information that's in there, or general instructions that we've set at the highest level across the whole account, then what can happen is your AI can get a bit confused. It can pull in some information that might be client-based information. Um, the guardrails aren't as tight as if you were to put it into a project and then say, "These are the only files I want you to reference as part of this, and this is the topic I'm gonna be talking about, and let's, let's put some boundaries around that." And then it becomes, one, we can do things, better quality because it's not making mistakes by pulling in the wrong information. We can do things faster because it's not taking its time going through all of your folders to work out what's the relevant information. And then also it can cost us less because we're not overloading it with a whole heap of irrelevant information that it then has to re- read through and reload every time that we're chatting. So they're the main benefits that I see from using, using projects.

Isar Meitis

Yeah. Great. I... One very tactical thing and one slightly just to add to what you said, and I'll start with the latter. Yeah. It is, to me, context is obviously the most important aspect of getting a successful output out of AI, and a project is a bubble of context. Definitely. You're basically creating a separate universe of context that is built for a very specific task with a set of instructions to tell AI what is it that you're trying to do, what are we trying to achieve, how to achieve that, how to use the context that you gave it. And all of that is just packaged in a place that is always there, which is the tac- leads to my tactical thing. It lives on the left side in the navigation bar of all the different tools. Again, it's called Projects, both in ChatGPT and in Claude, and it's called Gems in Gemini, but they all work in the same way. They all do the same things. So with that in mind, let's dive in. Stage is yours. Tell us how to do this better.

Loren Bartley

Awesome. So what I'll do, I'll start by sharing my screen for those of you that are watching along, and,

Isar Meitis

sharing my screen. Yeah, as, as you do this, for those of you who are listening and not watching, uh, if you do wanna watch this, you can watch this on Spotify, it is there with the video, or you can go to our YouTube channel. Uh, there's a link in the show notes, and you can see it over there. But do not worry. As always, if you are doing something that does not allow you to see, like if you're driving or washing the dishes or mowing the yard or whatever it is you're doing when you're listening to podcasts, we will explain everything that's on the screen so you'll be able to follow along, even without watching what we're showing

Loren Bartley

Yeah, great. And so as you mentioned before, in the left-hand side, you've got projects, and you've got projects across chat, Cowork and Code. But I'm gonna talk, and use the... This is in Claude that I'm, I'm showing the example. I'm gonna talk in, in terms of Cowork, 'cause to be honest, I do most of my work in Cowork these days. And part of the reason that I do that is whilst you can set up a project from chat and draw that information across into a, Cowork project, they're not actually the same, and they don't actually talk to each other. We can share files and stuff like that, but it's just, it's not quite the same. So I've made a bit of a decision to just do most of the things in Cowork, even though I know it's gonna use a lot more of my credits, but it's, for me, I like to have everything available and in the one space. So, um, basically- And, and I'm

Isar Meitis

100% with you, and I do exactly the same. So we're on the same- Yeah page on that.

Loren Bartley

Fantastic. So when we set up our projects, um, so we click on Projects over here, and you'll see that I've got quite a few projects going. I archive my projects when I'm not using them anymore, just more for my own benefit of not getting too overwhelmed. And I've set up quite a few different ones, and I can step you through, I'll show you one that's in action, and then I'll show you one, how to set it up really quickly, 'cause I think it's really good to, to see. Now, I'm s- I'm sponsoring a conference coming up, which is called the Byte Conference, and in here, on the right-hand side, once I've clicked into this project, I've got my actual instructions in here. And if you have a look at this, I, my instructions are quite detailed, when I scroll all the way down, as to what goes on in these projects. But I didn't write them myself. I have, over time, built up what I think is, a, an ideal template for instructions, and, but every time that I go to create a project, I use one of my skills, and he's called, Commodore Command Conductor, 'cause I like to give all my skills really weird names. And Commodore writes these skill- writes these, um, instructions for me. The other thing that Commodore does is he helps me set up a command center, and this is the thing that really w- like, when I started doing this, I was like, "Oh my God, this is so much better." Because what used to happen is I used to have all these random chats, and so I'd be having chats inside the project, and then I was like, "Was it in this chat? Was it in that chat?" Like, where was it? And to an extent, it doesn't matter which chat you're having it in, and you can just pick it up naturally inside another chat. And because we're inside our project, it understands the other things that have gone on in other chats, which is brilliant. However, sometimes you know that- It, it, it said, "Oh, I should do something next," and you're like, "Oh yeah, I'll do that and I'll get back to it," but I would forget about it. So the great thing about having a command center is the command center knows what needs to be done, and the command center can also then, r- create a tracker, which is one of the things that I've got it to do, which then gives me some traffic lights. I'll just jump into actually another project 'cause I've... I know it's, it's at the top. This is a client that I'm jumping into here, and this is their tracker. So I, I will say that I've moved on from this version, but this is like version one. So I wanna show people version one so they can get this done f- first if they'd like to. And so I, to be honest, I didn't really know what goes into a tracker, and initially I didn't even come up with the idea. Of course Claude did. He was like, "Would you like me to track this?" And I'm like, "Oh, sure. Go. No- knock yourself out."

Isar Meitis

Yes, please.

Loren Bartley

And so, so it created this tracker for me, and then over time I've said, "I'll be more useful if you had this, this, this," and then I kind of came up with a bit of a, a template for that, which I then baked into Commodore Command Conductor so that he will instruct each project to create one of these. So the command center in each project. So basically what the command center does is it keeps track of what's going on. a... Whenever I say I wanna do something, it just adds it to the tracker, which is awesome when you just have those random, you know, ideas where you're like, "Oh, maybe I'll do this," and it just gets put in there. So this is a, a new project that we're I'm kind of working on for a client. It's... There's not a lot in here at the moment 'cause it's just been started, but this is what the tracker will look like. then-

Isar Meitis

Ju- just to pause you for a second for the people- Yep who are just listening, what we're looking at is like a document-based dashboard that has a list of all the different things that needs to happen in the project, and they either have green, yellow, or red lights, which the red, there's like a little legend that says the red lights are either something that's open, so decision needed, or blocked by... meaning it's waiting for something else to be completed first. Then there is yellow, which different steps, and then green is obviously done, and it's broken into segments of the project. So stream zero is a project setup, and then there's all the other steps within the project. So by just scrolling through this very quickly, you can very visually, see where you are in the project and what is supposed to happen next and what is blocking, uh, what else. So very easy to understand what's going on without actually having to read 15 different conversations and trying to understand what's going on between them.

Loren Bartley

Definitely. And so that's one of the roles of the command center is to keep an- keep track of this. But one of the ways that it does keep track of this is that when it, it... The command center, 'cause we talked about context windows before, you can be having a... If you're using the command center to do all the things, it's gonna hit its context window fairly soon. And one of the ways you can know when it's kind of done that, and everyone would've experienced this before, is when it starts, like truncating the conversation so that it cont- can continue on. That means you've outlived any chat. or it might just start throwing up really bad responses, and it might start getting really slow. So when those things happen, it's because it's rereading that whole chat every time that it's coming back with a response and it's just getting, you know, a bit tired like we would as, humans. And so th- what we do in the command center as such, we don't wanna clog it up, so we use this command center chat inside a project just to help me, be the c- be the commodore. And so what the commodore does is the commodore directs all the other ships. The commodore doesn't drive all the ships. And so what m- our commodore command center does is he basically Will keep track of what needs doing and help me command all the other chats. So in this instance, in this project, if there's something that I need to do, I would say, "Okay," and let me just go back and, click into this for a moment and find something. So I can say, in this one there's an e- an email that needs to go out. So I could just say, "I need to do an email. The email's gonna be on this topic. write me a brief that I can get this done." And then it'll write me the brief, and then I can just go and cut and paste that b- brief and put it into another chat, and the other chat does it. And this is the, where the beauty of the cohort comes in because I can look at each of these things that needs to happen and say, "Write me a brief for 1.1. Write me a brief for 1.2. Write me a brief for 1.3." And then I... all I have to do is go back to, the main project itself, and then basically put that brief in here. So I can say, "Run this brief. Run this brief. Run this brief." And then on the left-hand side, I'll have all those little, sub-agents working to do the work for me. So that's where, the, it's super, super powerful from a command center point of view. It doesn't do the work, it commands the work, and then the work happens in all these other chats. And something I'll, I'll flag here, because those that are watching will notice this, is that I've got these kind of like minute work signs at the beginning of a lot of my chats, and this is just an internal thing that I do. It's manual. But whenever I'm starting a new chat and I'm working on it, I'll put the little minute work sign at the beginning, which is, I don't know if, is there's another better word for that, but it's like whatever... any emoji will do. And that tells me that there's still active chats for me, so I know that I'm still working on that and there's still things to, that need to be done. But then over time, when I've finished them, I'll just go and rename those chats, and it's as easy as clicking on the, the three dots and saying rename, and I'll just take that out of there, off the front of it. And that knows that I'm, that one's done. That one's done to me. So that becomes another way to make it easier to know where I should actually be working inside my project at any given time

Isar Meitis

So I'll pause you for just one second just to reiterate a few things that are important that you said. Some of them are kind of like hidden gems that people don't know if they, uh, if they didn't use projects. One is that all your chats inside a project happen within the project, meaning they don't get buried in the 150 other chats you had in the last three days that are on the left menu. They are living inside the bubble of the project, so it's a lot easier to find previous chats. Two, what Lauren said she's doing, and again, for those of you who missed, she manually adds an emoji so you can rename the single chats inside the project. She manually renames them, but she doesn't actually rename them. She just adds an emoji at the beginning, which tells her that-

Loren Bartley

No, I do rename them too. I will say that because- Yeah usually they're terrible names that are given, and then they don't make sense to you. So I always rename them to something makes sense to me

Isar Meitis

Fair. Uh, so but the emoji in the beginning, and you can use different emojis for different things, tell you which chats are still active, in her case, which chats I'm not working on anymore, which is the o- like these kind of things. So it's just another cool, tactical thing. The last thing that I, that I will say, and I wanna maybe ask rather than say, in, in all of these, there, uh, are two components that we didn't discuss yet, right? So what we're looking at so far is how to manage between the chats, which is this Commodore that helps you, that creates this dashboard and that helps you manage between the chats. When I say manage between the chats, and that's the other thing that I wanted to add, in everything you do in Claude Cowork, and by the way, in the regular Claude as well, but it's just a lot more effective in Claude Cowork because it's agentic and does its own thing, you can run multiple chats in parallel. And it shows you in a little tiny little icon next to it, uh, that either flashes when it's working or turns blue when it needs an answer or turns green when it's done. Like you can see a visual sign next to it in every one of the chats when it is ready for you. And if you turn on, uh, notifications, which I highly recommend you do, it will go like boop boop, it will pop up on the screen regardless of which screen you have open, and it will tell you that Claude finished working on a specific thing and it's waiting for you. So when Lauren is saying that she prepares the briefs, but then she opens five different chats, each and every one of them works in a separate brief, she's sitting there and just jumping back and forth and back and forth between the five different conversations that are actually doing the work and just giving them feedback and approving different things and progressing the steps. So she has five different mini agents and sometimes more doing the work. She's jumping back and forth, and whenever she wants to get back two days later because she didn't touch it for two days because life happens and there's other things in the business, you go back, you look at your dashboard, you're like, "Oh, what do I need to work on next?" And then you can continue from there. So from a day-to-day perspective, this is absolutely brilliant and it makes the work, A, more organized, and B, way more planned and structured because there's a process that you're following But I wanna, unless you wanna add anything to this, I really wanna know how you create the instructions, what's in the instructions, and how do you decide which files you're gonna add as far as the knowledge base of the projects?

Loren Bartley

Yep, great. And that's what I was about to show you. So I'm gonna start up a new project, and I had a bit of a think before what, what could I do? And, something that's pretty easy. I've just been booked to speak in Singapore in a couple weeks' time, and so there's a lot that needs to be done in order to make that actually happen. So let's, let's use that as my case study. So I can come in here and say I'm gonna start from scratch. So I'm in projects at the moment. I've just clicked on New Project, and now I've got a window that's telling me, do I wanna start from scratch? Do I wanna import a project? Which is where you can import them from cha- the chat if you previously had that, and that will bring across all the file structure as well, or an existing folder. I'm gonna say I'm gonna start from scratch. So I'm gonna say here, uh, Singapore... I'll just call it Singapore Trip. That'll be fine. Now, I don't need to worry about the instructions because Commodore's gonna help me write them in just a moment. But I do need to potentially add some, files here. And if I just click on this, it's gonna take me to my Claude Cowork file here, and I set up this, um, folder here f- which has got my travel, preferences in it. So I'll just say that's what I want you to have 'cause it's gonna help me book my flights and all that kind of stuff. So I can just say, "Okay, let's create it." So now I've come to a screen which basically has the little chat where I could start chatting straight away, and on the right-hand side, it's got the ability to add instructions to s- schedule off some tasks if I wanted to. And then it's also got the context. And at the moment it's, um, created a folder automatically for me, for the Singapore trip, and then I'm bringing in the travel, folder that I already have there as a bit of context and information it can draw from. So this is a blank slate. So I'm starting my brand-new project, and all I really need to do here, because Commodore's gonna help me with this, is I can just type in run Commodore. and people might n- if... For those that aren't aware, you can also go forward slash and then type in Commodore and find Commodore Command Center if that's what you wanted to do. But because the instructions are written in a way that it just knows if ever I mention Commodore, that I want Commodore to run. So I'm just gonna hit Return on that, and then Commodore's gonna go and start doing his magic. Now, I set this up so that it will ask me a few questions about what the is... what I'm gonna be, U-using this project for. And then once I answer them, it's going to then spin everything up for me. So here it's saying, "I'm Commodore. Here's what I do plainly. I set up work inside Claude so it runs properly. I can stand up brand-new projects from scratch." you know, it-its folder, its instructions, the right knowledge, a tracker, and its command center. Or if the project already exists, just brief a command center to run it. So I set it up that way because retrospectively I had all these projects and I was like, if I just started a project without running them first, I can still use this skill. And then it just explains what it is. So it's, The command center that we're gonna be setting up as the first step is one chat that keeps the key documents, holds a single tracker so you all know-- always know where things are up to, decides what to do next, and briefs separate chats to do the actual building. It coordinates, it does not do the building itself, and that separation is the whole trick. So it's saying, "We're sitting, in your Singapore trip project, so let's start with one choice that shapes it." So it's asking me i-is a new project or that I wanna start from scratch or do I just wanna brief a command center? So in this case I'm gonna start from scratch and now it'll be able to go off and start... It knows what it needs to do, so it needs to do all those things that I, just mentioned. And it, you know, like anything, it takes a little bit of time, but now it's saying great, now it's gonna set it up. It's asking what it is. So is this, a personal trip, a work, client work? I'm gonna say, it's client work. And then, yeah, it'll come back and ask me a few, different things. I can also, if I want to, just dump a whole heap of information in there. So because... And this is one of the great things about Cowork, is that Cowork, you can interrupt it and just keep adding it stuff while it's still thinking as well. So this is saying, quick note, Oh, I don't know why that's not working, but l- let's not worry about that too much. I'm gonna put some more information in here. And just to make it easy for everyone else, I kind of, typed this before to... But I was just... Here, what I'm saying is I've basically said I'm going to Singapore, the dates, what were the workshops for, and I've said that I love to do Parkrun, and I'm gonna be across two weekends, and the weekend, the first weekend, there's actually a special... It's Singapore day, so there's a special Parkrun on, and so I'm hoping to do two Parkruns in the first weekend and one in the second weekend. And the other th- and then I've told it which Parkruns I've already done, and I've saying who I'd like to catch up with while I'm over there. So that's all the instructions that I'm basically gonna give it, and then I'll, I'll kick that off. So this is more than what it actually asked for. but while this is thinking, what I do wanna do is, before I said there was the tracker that we have, and I showed you the static tracker that lives inside the chat. The other thing I wanted to show you, and, yep, I do have it open. Cool, I'll just make this a bit bigger while that's thinking, is the other... What we can also do by integrating tools. And so we can int- I use Notion, a lot, and so, but you saw that, that project before, and wh- where was it before? this is the project that we were looking at before, and that was an older version of the tracker. but these are the things that are still going on. So it, what I've, what I get my, I- is written into all of my instructions that Commodore puts into the command center. It used to be to spin me up that tracker, but now I get it to write it to Notion. So this is the great thing. We can use the tools we already use. We don't have to jump... and, having one static tracker in each of the chats becomes not as manageable as having them in here. And I've got the view at the moment that's incomplete, but then we've got, you know, the other views that'll alsch- also show me what's done, what's ready, and all of this across each of the projects. Now, I will add- Uh, I wanna- if you look at this and go, "How do you do this?" I have no idea. Claude did it for me. Claude did it for me.

Isar Meitis

So, so I wanna pause for just one second to, to touch on a few important points that you're mentioning. One is Claude Cowork, and Claude Code for that matter, knows how to use external tools. Yeah. What are these external tools? Any other piece of software that you're using in your company, your ERP, your CRM, your marketing platform, your email solution, your accounting set, like whatever it is. It can use it in multiple different ways. It could be through a direct API. It could use third-party connectors like N8N and Zapier. It can use an MCP if it has an MCP, or it can even use the browser just like you use the browser and do whatever you do in the tool, quote unquote, "manually." So there's multiple ways it can connect. As Loren said, you do not need to know how to connect it. All you have to do is say, "I want to track this in whatever." I do something very similar to what Loren is doing. I do it in ClickUp because it's-- I use ClickUp and not Notion, but you can do this in monday.com, in Asana, in, uh, whatever other Jira, whatever other t- task management platform you're using, and it will figure out how to connect. It may ask you for some assistance, "Give me this key. You can get the key by going to this page, logging onto this, clicking on that." It will tell you exactly what you need to do, and then it can set up the screen for you. The broader idea behind this is human in the loop, right? You don't want the AI just running rogue doing its thing. You want to know what it's doing and be making the decisions in the main decision points. And you can do this inside each of the chats, but very quickly, and again, you can see Lauren is doing this, I'm doing this, a lot of other people are doing this, and we did not exchange notes before. It just makes a lot more sense to use the tools you're already using to run your business to also run your agents and the stuff that's happening inside the agentic environment. And so it becomes as if you're working with other humans the way you work with other people in your organization. In my universe, and I assume the same thing for Lauren, inside each of those tasks, there could be a chat associated with that task. So when I want to communicate with the AI about a specific task, I don't go back to Claude. I stay in ClickUp, and I open the task, and I chat inside the task as if I have human people that are watching this, and it's gonna communicate back through the chat. And again, how did I set it up? Just like Lauren said, I don't have a freaking clue. I asked Claude to set it up, and it did, and now I can communicate with it just like it's a human. So a few really, really brilliant points here, right? So one is manage the process. Two is you don't have to manage it inside of Claude or ChatGPT or whatever. You can manage it in the tool in which you're managing the entire work that you're doing in the same way you're managing the rest of the work. So you can give Claude access to your existing board and said, "This is the way I wanna manage your projects as well." And then it will learn exactly how it's set up, and it will set it up the same way, for that. Let's continue from here. Brilliant so far.

Loren Bartley

Yeah. Yeah. And as you can see, and for those that can't see, this basically mimics what was in the spreadsheet that, that... Sorry, the static tracker that I showed before. So it's got the same traffic light sy- system. It's got, you know, what's happening. If I click into these, it's gonna give me more details as to, it may or may not actually give me more details as to what's going on. And then there's a whole heap of other fields in terms of date added, all the other stuff that's relevant. And it also tells me, which chats this comes from as well. So if I see this task and I'm, "Oh, yeah, and I wanna return to that chat," I can do that really easily. And then if I change the status in here or anything else, as you mentioned, this is where, uh, Claude's reading from. So it's not gonna come back later and tell me that I still need to do a job that I didn't tell it in Claude, but I updated the status here to say it's done. It's gonna automatically go, "Okay, that, I know that's done," without me nev- necessarily having to do that, which is super cool. Okay. So we've come back here and it's asked me a few questions. Is the year 2024? Uh, when,

Isar Meitis

when we're saying come back here again, for those who are listening- Oh, come back to the chat we left Notion- Yeah and we're back inside of Claude setting up a new project

Loren Bartley

Yeah. And it just asked me a simple question to ask if it's this year or next year. So it's shaping up nicely. And I will also mention, you mentioned before about, in the left-hand column, we get these little, flashing symbols that go on. So this is a visual representation from those that are watching of just the actual chat going on on the left that it... We know it's working. And often I'll have multiple of these going on that will then, and as you said, just jumping between them as necessary. So we can see that it's thinking at the moment. and interestingly, on the left-hand side as well, you'll see I've got one that's got a little, jigsaw puzzle instead of the minute work kind of emoji. I said before I use different emojis. This one tells me that's, that I'm working on a skill. So I did update Commodore the other day, and I, I went in there, but you can update your skills in any chat, but I often like to go back to the original, chat if I can to keep it, that's just... It works better for me. It doesn't necessarily work better for Claude, but for my, logic side of things, it definitely does. And, on the left-hand side as well, I've got some of my chats have a little pink brain, and the pink brain emoji is the emoji that I use for my command center chats. So I know that they're, th- that's my command center chat that I go to, to assign, work to the other chats, and that just works for my, logic. And then also what, something that I know a lot of people don't realize, in the left-hand corner, when you click on any of your chats and click on the three dots, you can rename it, but you can also pin it. And so I pin those chats that, I c- I pin my command center chats, and if there's another chat that I'm working on a lot, so you'll see here, take control of your AI, that's a presentation I'm doing on Friday. Because I'm really active in that at the moment, and it... I probably don't need to pin it because of the fact that I am so active in it and it sits at the top of my chats usually anyway, but I just pin it there t- as a reminder to me, "Hey, Lauren, that's what you should be working on." So, that's just a few other little, hacks that can be really good to help organize yourself. And then when I clicked on those three dots alongside a chat, the other thing it does allow you to do is to change the project. So some people, some- sometimes I'll be working on something and then go, "Actually, that really should be in a different project," and you can move it, which becomes handy 'cause you can move things backwards and forwards as well. So that becomes handy. the conference one I was talking about previously, I was, building out a brochure to put on, to use at the stand, and I was doing it all within the conference, chat. And then when I finished it, I thought, "You know what?" 'Cause that's, it's done now. And I thought, "But this would be really handy context to be inside the branding, that 'cause I'm doing a rebrand at the moment with my AM Mega Success, uh, brand. And so I took that because it was basically an AM s- AM Mega Success brochure that I created, and I moved it across into the AM Mega Success rebrand project because I wanted that context saved in there, for later. So this is some of the flexibility that you've got with this. and quite often, so I always go to a project first and then start the chat within the project, and but sometimes you just go straight up here on the left-hand side, you click that new task thing, and then you start working, and then you go, "Oh, actually this should have been inside a project." So I just wanted to give people the heads-up that you haven't broken anything. You can just move it when it suits you

Isar Meitis

Fantastic. one last quick question. Yeah. Uh, how do you pick which files to connect? Do you use AI to help you pick the files or define what needs to be imported, or do you have a system for that? 'Cause the... Again, so far we spoke about creating the actual instructions, which it's, I assume that's what it's doing right now when it's running the thing- Yep after asking you all the questions. While it's doing its thing and we're waiting for the instructions, let's talk about the files themselves. Like, which files do you upload based on what? Do you have a system for that as well?

Loren Bartley

Yeah, so I have a, folder which I call, Impactivate Knowledge. Impactivate's my, my, my company brand. And so I have in there my brand voice, my ideal customer profile, like a whole heap of things that are relevant to that. That gets put into most of my, um, personal, so- so my business work, but not all of it. So for example, in the client's, side of things, I'll put their brand voice documents and those types of things in there. But then I have folders specific to each project where I put in the relevant information. So for this one, so I have a travel folder as you saw. I've got other folders, like I have a branding, the branding folder. So th- they really become specific to the project, and that again goes back to that context window because we don't wanna overstuff it with too much stuff that might be irrelevant or contradictory in- information as well. So that's kind of how I work on that. But I can see this has come back now and you'll se- and it's given me quite a few documents. So the first thing that it's given me is my project instructions, and if I click on that in the center, panel, it pops up in the right-hand side with what those instructions are. And as you can see, it's quite a bit considering I didn't give it very much at all. And- It's like

Isar Meitis

two to three pages of instructions.

Loren Bartley

Yeah And the reason, the reason for that is because I've put some, I've put some, I've created a template and said these are the things that kind of needs to go into the template, knowing what's good. So basically, we get a project snapshot. We get this is... And then it'll say what type of work. So in this case, this is client work. the know- knowledge files and resources of truth, so it's telling me, um, which folders that, and files need to go into that. The confirmed facts, because that's what I gave it already, and how this project works. Then it's got the save location, and I've set this up, and this is an important thing, is that I have this other, rule that I do, which is versioning. So what happens is whenever my chats, spin up any form of document, I ask for it to be in markdown format, and then I also ask it to, save it into the project fo- folder. But then each project folder gets an archive, fo- subfolder, and when it r- makes a new version of it, it moves the previous one into the archive version. So the main folder for the project only ever has the most recent version, but I don't ditch the old versions. I don't override the old versions because sometimes we go, "Actually, I'm pretty sure, like, we used to do it differently." And I can go back through those or get Claude to go back through them, find the bit that I wanna, that we might have, you know, deleted or changed or whatever, and then reinstate it if I want to later. So that's something else that I do there. It gives instructions as to how the command center is to work, and then it puts some, project guardrails and then if there's any overrides, and these overrides, are usually things that might override, let's say, the system-wide instructions or anything like that, it'll list them there as well. So now that I've got this, I can just basically copy these instructions and it, up here, in this middle section, it's telling me what I need to do. So it's telling me that I need to rename the chat, and that's how I get my little, brain emoji in there. So it's saying rename the chat to brain emoji Singapore trip V1, and I'll tell you why V1 is important in a sec. And then it's, it's saying, "Put in place in the app creator called project called Singapore..." I've already done that, so that's fine. I did that at the beginning, but it's reminding me in case I didn't. And then, I've got an issue some, for some reason Notion's not tracking properly. It could be 'cause I upgraded the account last night. and then it's asking me what I need to do. It's telling me what I need to do next. So interestingly, it didn't tell me... It usually also tells me to go and update the instructions, but I'm gonna go and do that now. So basically, because I'm working in a chat that's inside the project, I just have to click on the name of the project, which is in the top, left of the middle panel, and I click on that which says Singapore trip. I click on, on the right-hand side where it says instructions, and I just paste in those instructions and I go save So that's basically saved the instructions for me. I can go back into that chat that I was working on, and now I can do what it's asking me to do, which is to rename this chat into my command center. And the reason it says V1 is because this is the version one of my command center chat. When I feel that it is getting, to the end of its lifespan, th- I usually just say, "Hey, we've been chatting for a while." it- because it doesn't tell you in Cowork whether or not you've hit your context window. There is a way you can do that in code, but not in Cowork, not that I've found anyway. And then I just say, "Do you think you've, you know, we're getting towards the end of your Cowork, uh, your context window?" It'll usually honestly say, "Yeah, I think I have. It's been great working with you." And I'll say, "Can you spin up a new brief?" And it will do a new brief that I then put into a new chat, and then I basically take the emoji off the beginning of the name of this one, and then it, I rename the next one Singapore Trip V2. And then I work out a V2 moving forward, but none of the other stuff is lost. I'm just working with, someone who's, had a nap or had their coffee instead. so that's... So I'm not quite finished yet because there's a couple more things. So it's, I've done the instructions, so they were the instructions. It's spun me up the tracker straight away 'cause that's what it's instructed to do. If Notion was working and, um, for some reason I'm not sure why it's not at the moment, but it would've then gone and created the Notion version as well. And then, and then it's given me the command center briefing, which is here. Now, what I do, and it's, it may or may not be necessary to do this, but if I wanted to do a different chat, I would take this into the different chat and say, "Okay, y- give it this brief," and then say, "You're now the command center." but I just do this. I just basically copy that because I'm gonna use this chat as the command center, and then I'm just gonna paste that into here. But before I do that, let's just look at the other documents that they've got. so it's given me the command center briefing. It's given me also my Parkrun schedule. It's just gone and done that straight away as to what I could potentially be doing for Parkrun. And for those that aren't aware, Parkrun is a five-kilometer run that happens Saturday all round the world, and I'm a bit obsessed with it and even though I'm not a runner. And I do it without fail. I love the tourism side of it. And then it's given me a command center checklist as well. So all of this has happened. This is now my command center, so I'm just gonna basically brief it to say, "You're now the command center." It's gonna know what it needs to do. And then the next thing I can do in here is I can, So it, it's basically telling me what, what's going on here. So it's saying the command center's active. These are the open decisions that I need to make. it's ready to run now, and, okay. So what I, what I can do now, it's basically telling me where we're at, and then it's saying flights. So I can now say, um, "Can you create me a brief that, I can put into another chat to organize my flights? And then I'll have a second brief that can then go and research, some accommodation. I'd like to be somewhere around Orchard Road. And then also, If you can draft me up an email because I wanna let Vicky, Katya, Melissa, and Jodie know that I'm gonna be in town. and if you can write them as drafts and just have them sitting in my, draft folder, that would be great. That's in a separate brief. So now that's me just verbal diarizing this into, my i- into Claude, and Claude's now gonna go and create those, multiple briefs for me, and then I'm basically gonna go and cut and paste them into other chats within this project and then let them all work together to do the things that they need to do. And as you would have seen, one of the tasks I gave it was to write emails to, certain people and then, and because I have my Gmail account connected, it's gonna write them and put them in as drafts, which is kind of super cool.

Isar Meitis

Awesome. I wanna do a quick recap for those who are somewhat lost because you covered a lot. So the, it all starts with a skill. A skill is a set of instructions that tell AI how to do something specific. In this case, it does several different things, but one of the things that it does is it knows how to set up a new project. So when Lauren said, "Hey, run Commodore," that's the skill. The skill is called Commodore, and Claude says, "Oh, what do you wanna do?" Because there's several different things it can do. It can either update an existing project or create a brand-new project. It said, "Let's create a brand-new project." So the skill itself contains a whole set of instructions on what needs to happen in order to set up a new project properly, and that includes the task setup and the command center and the components that needs to go into it and ask her a bun- a bunch of questions to understand what is this project about, and it does all these things on its own. So this is step one. One of the outputs that it creates after it asks her all the questions is additional prompts. She calls them briefs, right? But it's just another prompt that you can copy and paste into a new chat inside the project to achieve different things. From that moment on, it's a snowball effect because every one of these briefs can create more options that can create more briefs, which again, are just new prompts that then will do more things. But the cool thing is from like the second conversation and on, because the project is already set in a proper way with the right context and the right instructions and the right reference files and so on She can just open the microphone and say whatever she wants to say, and it will happen because the AI already has the scaffolding and the context in order to do all these things that needs to happen. The other cool thing that you saw, and these are two things that I do very much the same, one is stop typing. Like all these tools are really, really, really good with voice, and you can speak way faster than you can type, even if you type very fast. I, for Lauren and me, it's very obvious we're very good speakers, uh, because that's what we do for a living. We speak on stages, and we have podcasts and stuff like that. But for any person, it's easier to explain yourself in, just speaking out loud, and you don't have to be exact, and you don't have to be perfect, and the sentences could be horrible from a grammar perspective, and the AI will be perfectly fine in figuring it out. So this is one thing. The other thing that you saw is that you can give it multiple tasks in one prompt, and because the scaffolding in there and the instructions is there and the reference information is there, it will figure it out. So a great example was the email. She didn't say who these people are or what their email addresses are. She gave names. However, the project knows she's going to Singapore. It knows it's connected to a specific client project because that's how we got started. She said it's a client project. It understands who the clients are, so it understands who the people are in context to these clients. This cannot happen in the open chat. if you just go and click on chat and say, "Hey," literally the same exact prompt, "I want to send emails to so-and-so and so-and-so," it, like, it will not know what to do because it don't know who these people are. It doesn't know they're in Singapore. It doesn't know she's going to Sing- Like, all of that information that it gets from the project and from the skill setting up the project, it doesn't have. And this is why this is so magical. Because in 10 minutes, and the reality is most of those 10 minutes was Lauren explaining what she's doing. She can probably do it in three minutes. She has a setup of a new project, and from that moment on, she can speak on very broad terms and the AI will still figure out what to do, and will go and execute multiple tasks in parallel. Again, in this particular case, it figured out the flights, it figured out the accommodation. Uh, I mean, it didn't figure it out, but it came up with options for flights, options for accommodation, and a draft email by her saying

Loren Bartley

one sentence. Well, it hasn't actually done that. It hasn't done that. It's done the brief for that.

Isar Meitis

Okay. Oh, correct. Correct, correct, correct. You're right.

Loren Bartley

Yes.

Isar Meitis

So the- It creates the prompts.

Loren Bartley

Yes. Yes. So c- can you give me one sec to just now show what happens here? Yes. So basically I can go and, and say show in Finder if I wanted to, and you can see now that it's popped it into this fo- folder that I've got here. And I mentioned before I have an archive, so this is the archive stuff that would've been put across into here. But now what I can actually do is I can go back to my Singapore project now, and then I can just take that, this here, this fold- this thing that it's done, which is the Singapore trip catch-up emails, and I can just say run brief. and then that one's kicked off. Then I can go back to my command center, and I know which one it is 'cause it's got the little Face there. And again, I can go show in finder. I could have just scrolled through and found the next one, but I'm just gonna do this to make sure I've got the right one happening. Pull that back up. Oops, where have I gone? I'm going back to my Singapore trip again. In a new chat again, I'm going to pull that one in and again, I'm gonna say, I'm gonna say, run brief. Run

Isar Meitis

brief.

Loren Bartley

And then it's gonna run that brief, and then I go back to my command center again. You can see two of them are working, and I find that third one, which is the, catch-up emails. I'm gonna go back to here into my, main project, and I'm gonna put the catch-up emails in there again and I'll say run brief. And then... Oh, run brave it says. This is Whispers flow I'm, I'm using if in case anyone's wondering. And now in the left-hand side, we can see I've got three things happening at the one time. Now, I didn't even read those briefs 'cause I was pretty confident now that it's gonna do the right thing. I could have read them, I could have edited them, and I could have come back now and, and finessed it further. I could have got... I could have given feedback to the command center he- and the command center could have th- could have rewritten the briefs if need be. but most of the time I don't because I've got so much confidence in it now that it's going to do it right. And then in this chat, if it goes a bit haywire, then that's when I'll just re-brief it as part of the chat and say, "Oh, no, actually this," and, the... and give it more, more context. And you can see this one's popped up as blue, the Singapore catch-up brief, and then it's telling me uh, that those emails are already sitting in my outbox ready to, to catch up with those people. So that's one of the, really cool things about this. Now I can go into my drafts and there'll be a draft there saying, "Hey, it's Lauren here. Coming to Singapore, let's catch up." and then I can finesse a little bit. Obviously, if I'd given them more context at the beginning, you know, I could have said, you know, tell Jodi that I wanna meet her at Parkrun on Saturday," like any of those things and it would have done a better job, but that was just for demonstration purposes showing you at the really high level what it can do, um, rather than the quality of what it can do. So that really kind of does the full circle on how to use this. And if anyone's asking like, "How do you set up a Commodore?" Like, that was just me taking, like with any skill I create, taking what I've been... Once I've done the thing and I'd set it up the way that I liked it, and then just basically saying to Claude, "Okay, can we package that as a skill now so that I can repeat this over and over?" That's the magic.

Isar Meitis

Absolutely brilliant. so a- again, I... This is a whole different level of creating and using projects, and what you see is that the concepts are the following. One is you don't do the work Claude does the work. Two, you manage the work, you feedback the work, you sanction the work. So there are steps in which you as the human is heavily involved to push it in a direction you want, but the actual work is done by Claude. The last thing is you can do many of these in parallel, and as long as you're watching them and seeing what they're doing, uh, then you can do that as well. And all of that is managed by skills. And skills are just same kind of thing as a project. It's a bunch of instructions with some context that it knows how to repeatedly do the same thing time and time again. In this particular case, the skills knows how to set up a new project and how to set up the command center so it can spit out briefs that can do more or less anything else you want inside that project. Lauren, this was absolutely fantastic. If people want to follow you, learn from you, connect with you, meet you for a park run somewhere around the world, what are the best ways to do that?

Loren Bartley

Oh, that, that park run one would be the best one. But, um, failing that, if they go to aimegasucces.com, that's probably where they can find out, and connect with me best. And then if anyone actually wants, I've created a generic version of Commodore, so if they go to aimegasucces.com/commodore, then, they can download, uh, the, Commodore as a skill. It is generic. It'll set up the trackers. It won't connect you to Notion or Asana or ClickUp or any of those things, but you can build on it. So you can use that as your base and then say, "Okay, and now, let's have this connect to monday.com," and it will do that. Or, "I prefer this in my instructions," and get... And just keep updating that skill until it works right for you, and then, you're off to the races. So that'll be a good starting point rather than necessarily starting from scratch if it was a little bit overwhelming for anyone.

Isar Meitis

Awesome, awesome. So thank you so much. Again, absolutely fantastic. Uh, you're already on the 7th of July, which is the very last day to use your, Fable five credits before, uh, Anthropic takes them away. So I will not take more of your time so you can go and do that. I really appreciate you. I appreciate your time, and thank you so much for sharing with us.

Loren Bartley

Thanks. It's been a pleasure.

Head Shot

Isar Meitis

Host