AI Insider: The Simplest Way To Use Codex In Your Business, Content & Life (For Beginners)

When people say they had bad workflows or bad outputs, it's because we're relying on the model to be like us. It's not. We need to be very, very, very, very, very explicit. We're not going to allow the model to be creative. And with these agents, there's what looks cool and there's what works. I used to have a bookkeeper. I don't have a bookkeeper anymore cuz I literally dumped all my statements and then I asked to look at the transactions and look at what sounds like a restaurant or a food spot and then remove that.

Let's say that someone's watching this and they want to build their first AI agent that's actually productive. What in your mind is the step one?

Awesome. You know what? I'm just going to open Codeex and we're going to go through it together. Okay. So, a lot of you will be watching and seeing this show for the first time and so I wanted to ask for a quick favor and that's to subscribe to the channel. And if you do, the promise that I'll make is we're going to take everything that we do here to the next level. That means scale the guests, scale the storytelling, the production, every little detail of what makes this show great so that we bring you an even better experience. You hit that subscribe button, we make this show better for you. Do we have a deal? Let's get back to the show.

Here's where I wanted to begin because you and I, we had a conversation before this and I think for most people that I speak to that have tried using AI agents, it's not actually making them more productive. Like it's not saving them time, it's not helping them make money or increase their output. And so if someone is listening with that feeling and with that experience of using AI agents, what is going to be the value to them of listening to this conversation to the end?

Yeah, I think there's a lot of like um bad information out there on how to use these tools. Um a lot of times people are scaling for what looks cool, but really what you want is to scale for productivity. And just like in anything in life, simplicity always wins. And with these agents, when you use them with a simplistic mindset, when you have an end goal in mind, and we're going to, you know, discuss that and architect that together, you start to realize like, oh, this is actually a productive tool, right? A lot of people are attaching 15 different workflows from other people, not learning how to build their own. So, if there's one thing I want people to get from this podcast is they get an agent and they know how to build a workflow that works for them. It might not work for me and you, but it's going to work for them. And at the end of the day, that's what matters. My workflow is mine and yours is yours.

You know what? What you just mentioned and I know that you and I spoke about this. It's actually like a contrarian take because most videos creators content that we see is people that are using like 50 different agents that the architecture and the system is incredibly complicated and complex. Why is it that you have this different perspective? Like why is it that simplicity actually wins here?

Yeah. So my mom always told me to be nice. So I'm going to be nice to people who have contrarian takes. Um it's either one or two things. Um complexity looks cool, right? Like when you have like 15 different sub agents, I'm sure like and I'll do it too from time to time. I'll feel like Iron Man, like Tony Stark, right? But when it comes to actually being productive, there's what looks cool and there's what works, right? And what works often times is boring. I'm sure you would say in business with all the people you've interviewed in yourself, sometimes it's the boring stuff that gets you to the finish line. It's literally no different with using these tools. It's a matter of a lot of people, especially on YouTube, and I'm a YouTuber. I I do content. The extravagant stuff gets clicks and it's cool and it's and it's fun and it, you know, sort of paints this picture of a future that we can maybe have thousands of agents doing like, you know, thousands of things and you're just home sipping a pina colada. Uh, but the truth of the matter is when you want to use these agents, there's a couple things that are misunderstood. A, they're very powerful. B, they're very smart. C, this sounds contradictory. They're also very dumb. And D, your influence matters a lot more than you think. Right? When you take all this into consideration, 15 sub agents don't make sense because you're not doing 15 things at the same time, right? So, I hope like in this pod we sort of have like a mindset shift. People give it a week or two to test this out and they come back to this video and be like, "You know what? The guy with the messed up here was right."

I love it. You know what? Because you you talk about the the mindset shift and I think it's important. Can you just make it clear for people if they're able to go through that mindset shift and some of the things that you and I speak about over the next 80 or 90 minutes, they're able to implement, what is going to be the tangible impact in their lives? like what is it that they're going to feel once this is implemented?

Yeah. So, like the first thing is you're actually going to see productivity with these tools, right? Depending on like your personal work and stuff like that. Like if you're a super busy person with a business and you have 15 20 admin things, then you're going to love this. If you're someone who's just getting started out, you might see some value in some of the things. But the one thing I I look at and I think of is like investing in in in knowledge of these tools and how they work and sort of understanding high level how models and agents and stuff work feels like an investment for the future, right? So, like we can imagine next year from now based on the last year's growth the models are going to get better, the tools are going to get better, agents are going to be all over the place. It it seems like anyone who's made an investment now in learning these things will be well equipped for the future, right? So, it's not just a now thing in my opinion. It's also sort of prepping for the future because I remember last year messing with these tools. A lot of them were garbage, right? Like they were so bad, but you know, we kept like people like me kept tinkering cuz you saw like, okay, at some point this thing's going to get good and now it's really good. So imagine where will we be 6 months, a year from now. So we're going to experience um how to craft specific workflows and skills and all these things and I'll explain all of that. But we're also sort of futurep proofing our mind so that when the latest and greatest tool comes, there's parallels we can draw from the previous tools that we've used.

Yeah. You know, I think I think it's so good and and you make that point about superproofing your mind and like being ready for the future. And so one thing cuz you mentioned this when we spoke earlier. You said I happen to be in a position that gives me unique insight on all of the stuff that's happening with AI and the software changes that we're experiencing. When you say that I happen to be in a position that gives me a unique insight. Can you describe what that means? Well, can you explain what that means?

Yeah. So there's there's two things. First and foremost, you're not going to get a biased take from me cuz none of these companies pay me. And the job I'm in, uh, I work for a backend as a service company that a lot of AI applications integrate to. Um, I see a lot of the progress made. I like I see a lot of the updates made. I'm also very much a person who doesn't go outside. I go outside on Sundays for church. Other than that, like my free time is spent reading the latest papers, seeing the latest updates, trying the latest tools, right? So with uh when you take mere obsession plus my day job plus my content plus me uh not being bought by any of these companies again, you know, pray for me. Hope hopefully it happens. Um, yeah, I I I I have a unique perspective that's not biased and you know, I'll call garbage what's garbage and I'll call great what's great.

Yeah. You know what, uh Mike, because you make you make the point that you're deeply inside this world, like you spend all of your time doing this. I think also the thing that I respect from you and why we I invited you on the show, like I wanted you to do an episode with us, is um you don't gatekeep information, you know, like you you share information to people that are just starting out or even if they're more into this sort of thing. Can you just share with people why are you so open about sharing the information that you do? Because you're you're directly benefiting from using all of these tools like in your life. you don't necessarily have to share it. So, so why are you so open in that?

I remember getting into the space like I felt really dumb. Like I felt like, oh man, all these people are so smart. They're so intellectual. Like like they use all these big words like they they construct these sentences that I have no understanding in terms of what it means. And I remember like especially like early like 2021, 2022, I would watch videos by really really smart people. We're talking about like developers, researchers, and all that stuff. and I would force myself to listen to them. And this was pre-chad GPT. Then I would Google what they said trying to understand what it is they meant. So I went through a very painful process of learning and I realized, oh, a lot of this stuff isn't really that hard. It just sounds hard. Um, and I I shared the story with you. Part of how I started the YouTube channel was I was looking for a developer job and like it just felt like no one was hiring or my resume wasn't good enough. So, I was like, "Okay, maybe if I record a video of me explaining really deep technical concepts um that the recruiter watches and they see and they understand, then maybe they'll be like, "Okay, this guy is smart." And they'll push me like to the forefront. That never happened. But what happened was the YouTube channel started to pick up. Um, and then I saw that, oh, people actually want to learn about this stuff, right? Like a lot of people find technology fun, but it just feels like it it's above them and they don't understand and they don't want to make the investment in understanding. And yeah, I just kind of made it like a thing where I was like, you know, uh I'm going to explain it to one of the homies, right? Like I record my videos as if uh my bro or one of the homies from church was watching. Um and I guess that's helped a lot of people. So I'm I'm very thankful for that.

Yeah. Yeah. That's that's awesome. And I I I love the intention like you can feel it in your work. Um, you know, Mike, I just want to I want to get straight into it. And um in particular because we started it off in this conversation and this has been to be transparent. This has been my experience because a few weeks ago we record an episode with our mutual friend Riley Brown and he talks about Open Claw and how he's using it in his business and how how he has all these agents. And so I get super excited. I don't actually start with using OpenClaw. I start with Claude co-work and I spend a few hours setting up this workflow that's going to help me do content or in my business with uh Claude Co-work. I set it up. It gives me an output. So I get to that point where it's given me an output. The output is mediocre at best. From that point basically from four weeks ago I haven't used it again. And I think that that's like a common experience. And so for people like me, what is the thing that we're like misunderstanding or doing wrong when it comes to building these AI agents where we're not actually getting a useful output at the end of this long process?

Okay, real quick. If you're watching this video, I'm sure at some point you've had to create a presentation in your life. And if you're a non-designer like myself, then that probably was not a good experience. The funny story is I actually started my career in consulting and I would only work in building presentations for clients and it'd be this horrible manual experience. It would be so frustrating trying to get everything to look just right on the slides. But now with tools like Gamma, you simply type in a text prompt and it will design a beautiful presentation in exactly the way that you want it. And so as an example, recently I wanted to create a short form content strategy presentation to share with my team. And so I simply went into Gamma. I selected one of their templates and I described how I wanted this presentation to look. And so what I asked Gamma to do was to build me a short form content presentation using some of the strategies from the top podcasts in the world. And you can see here what it came up with. And I actually think it's pretty impressive. You can see we have the platform strategy. Even created this checklist for choosing viral clips. And you can see it looks great. And so if you want to create good professionallook presentations without all of the manual design work that typically comes with it, then go to the link in the description and check out Gamma. That's Gamma using the link in the description to get started with them today. Thank you to Gamma for sponsoring this episode. Let's get back to the show.

Yeah, I mean I could share my screen and like diagram this out. Let's do it. It really comes from um like when you understand how models work um it will all make sense, right? So you can think of this giant blue box right here as a model. You can it could be Opus uh 4.7 which is Enthropics uh latest model or it can be GPT 5.5 which is OpenAI's uh latest model. Both are really really capable and smart models. The issue with a lot of people and how they use it is a lot of people think the model is similar to them in a sense where you know the model kind of sounds like us, acts like us. You might hear these stories where like oh they did some testing and the model they got the model to blackmail one of the users and all that stuff. It it feels very humanlike. Um but it's not. And understanding this is important because when you understand where it lacks and where it's great at, it becomes a great uh co-pilot, right? I think agents are a great co-pilot. You're still the pilot. You're still in charge. Uh but they're a great toolkit. Now, one of the interesting things about how models work is they actually um don't think the way you and I think. Models uh predict tokens. Now, a lot of people are going to hear this and be like, "Oh, this nerd is about to speak some jibber jabber and it's going to confuse I I I promise all this will make sense. Tokens are basically numbers like weird looking and these numbers are plotted on a graph. If anybody remembers in grade 10, 11 or 9, whatever like year it was like at math class, we'd had to draw these graphs and then we had to plot them and it was annoying and it was like why is this ever useful? It so happens that the researchers who build these models needed that stuff. So glad to hear that at least some of those things were useful. So what the model does it it understands and predicts tokens. What does that mean? Let's say um Callum I prompt what is the capital of France? Right? This is my prompt. What is the capital of France? You and I know that the capital of France is Paris. It's been taught to us. We have it stored in our brain like in in some part of the memory layer of our brain and we know this instantly. The way model works, a model works is it's going to when I type in this text, it's going to convert this text to a bunch of numbers like this. Again, how it converts, it doesn't even matter. I don't even know. But it's going to convert these number these text to the numbers. It's going to plot the number on the graph. Mathematically, and this is impressive, the closest answer, which is Paris, happens to be a number very close on the graph. So that's what the model does. It doesn't think. It doesn't like ponder the way you and I do. It literally maps words on a graph and finds the nearest one. I'm going someplace with this. It's going to map it and then it's going to be like, "Oh, the answer is Paris." There's even another test right now. Um, especially with the anthropic model, you can ask it, um, I want to wash my car. There's a car wash 50 mi away. It's faster for me to walk than drive. What should I do? The model will tell you to walk. I'm going to a car wash to wash my car, but the model will tell you to walk. So the reason why I say this is the model does not think the way you and I think. So when you understand this, you have to understand the prompts that you give it, the text that you enter, the messages, the workflow, whatever it is that you construct has to be good. It it like the quality of input has to be good because when the quality of input is good, the quality of output will be good. But if we talk to the model the way you and I talk to each other where there might be sarcasm, there might be context of understanding based on our relationship, you know, I can say something to you and based on the context of our relationship, it can mean totally something different than if I say it to somebody else. In the same way, the model is not human at all. It sounds human. It acts human. It's been trained on so much data where you think it's conscious but it's not. So when you understand this, you understand you have a really smart but at the same time dumb machine. So when people say they had bad workflows or bad outputs, it's because we're relying on the model to be like us. It's not at its current state. It magnifies the abilities, the wisdom, and the knowledge that you have. So if you're someone who says, "I I don't need to read books anymore." Ta. You got to keep reading more. You got to got to keep growing more in knowledge. But this is how models work. So when you understand this, it's going to help like especially when we start to craft a workflow, it's going to help us craft a workflow cuz we're going to understand we need to be very very very very explicit. We're not going to allow the model to be creative. We're going to give it our creative sauce and we're going to want it to replicate that.

Just so just one thing m before you before you go on because I think this is so good and important when you say um it really comes down to like the the prompts and like the inputs, right? It's like good inputs versus bad inputs. Can you crystallize for people exactly like what is the distinction between what makes a good input or how someone can know if they're giving the AI a good input versus a bad out input?

Yeah, I can explain that. So let's say we have this line uh where on this spectrum this is a person they have no agency right and on this end of the spectrum they have very much agency I know that just broke English I apologize um but basically let's say this individual like we're looking to hire somebody and as a business we obviously want someone who has like, you know, a lot of agency and to have agency means you're given a problem you might not have all the context text uh but you go out of your way to get the context um you have this feedback loop where you keep on iterating on this feedback loop and at some point you're going to achieve success right? Like for example if I hired an assistant u one thing that I may do and I'm going to show us how to do is generate uh a report for sponsored videos now I'll give context on this I run a YouTube channel and one thing I use AI for is after a video's gone live especially if it's a sponsored video, I'm going to send out a report of how the video performed, right? Like sponsor wants to see if they got a good investment on their money. Now, if I told this to a very high agency person, they're probably going to research, okay, what does reports in the YouTube space look like, right? What things do I need to report? Is it just views or is it link clicks? Do I calculate a specific thing? Right? Someone who has high agency will go through the motions, will probably continue to iterate on a specific thing and generate a report that might be decently good. Someone with low no agency will probably be like, "Yeah, like here's the video. Here's the link clicks done." Right? So, um we we we see this as humans, right? Like you you want to work with like the very high agency people and the you know the ones who like make the right decisions, ask the right questions. Models are somewhere here. Right? And the reason why I say this is it is going to like it it will produce the amount of effort you give it in the question you ask. Right? So if I say generate a report for a sponsored video, it's going to generate it as if someone with no agency did. But if I let's say change the prompt to generate a report for a video, right? And then I add, let me just make this a long line. I add um let me add a new line. First get YouTube views, then get link clicks, then calculate CTR, then generate HTML page for me to view the stats. So this explanation and this get generate a report for a video to me and you especially maybe we've worked together you know we're both creators generate a report for a video might make sense to us but to someone who has no agency you're going to have to give them step-by-step direction. The model is pretty much the same way. you're going to have to be very like you have to think of this as a very junior no agency person but that is very capable and has all the knowledge in the world consumed in their brain. So this has to uh the the the the way you prompt has to shift. You can't give it oneliners. You can't uh say just do this for me. It doesn't know you or understand you. Right? You're going to have to give it step by step by step instruction at least one time. And then I'm going to show us later down in the in in in in the video how we can take this convert this to what's called a skill. This is stored in the agent and the agent can call this again and again when it needs to. But the very first time like hiring a new employee, we're going to need to train them. And this is the big difference on like good inputs versus bad inputs.

Yeah. You know what? you you just made the point and I think it's actually the perfect way to look at it and it's what made it click for me.

100%. 100 like that's literally the perfect analogy.

Yeah. Okay. Where do we go to next?

So there's I would say there's a spectrum um when it comes to these agents and the spectrum um really is the difficulty right how difficult is it to set up? We'll actually just have one line here. How difficult is it to set up? If like this is super difficult and then this is uh easy, uh the following agents fall as follows. Open AAI and um OpenAI codeex and uh Enthropic their tool I would say is somewhere like not in the like not on the easy spectrum but somewhere like right here. meaning um there is like a back and forth um there is like a cost of time um that you're going to put but I believe like especially after we go through an example um you're going to feel like this is super easy these open claws her these like new agents I would say especially for someone nontechnical are on the difficult side uh when it comes to I'll just say open claws are on the difficult side when it comes to setting up but like using them directly um the setup is a bit difficult. Now there's pros to that. The pros to that is I can have a really highly customizable agent like to the core like its personality how it works like everything is fully customizable and I own like the code with open ananthropic you're sort of tied to an ecosystem you're tied to specific model um so these are the pros and cons for first timers or people who are not technical or people are giving this like a try and you're pretty early on I before we chatted I was like oh co-work seems to be the one, but I've changed my mind. I think Codeex, Open AI's uh Open AI's Codeex is the best place to start. A, if you have an itch to build an application, a web or a mobile application, it's a great place to do so. But B, they've started to really focus on um this concept of being like a super app where you can use it for knowledge work. You can use it for workflows and tasks. You can connect it to external tools. Um, and that way you get the both of best of both worlds where I can maybe develop apps one day if I want to or I can also automate my life and my business, my personal if I want to, right? So, um, for today's video and probably for the near future, um, I would say Codeex is the best bang for your buck.

So, So, so Mike, before we get into it, cuz this is interesting. you and I spoke I want to say three days ago, two days ago. I want to understand and and and when you and I spoke initially, you said that um your belief was that for beginners looking to start out, the easiest tool and the simplest way to get started if you want to use AI agents is Claude Co-work. And so I want to understand what is it that has happened in these last three days that your thinking has shifted because I know Codeex um the developments that they've made to it are actually pretty new like it's getting better all the time. What has happened that your position has shifted?

So the biggest one the biggest one is the subsidy of credits. Um, what that means is like when you subscribe to the op to the codeex $100 a month month plan or $200 a month plan or $20 a month plan and same thing for Anthropic, you're not actually getting $200 of value. You're getting like $3 to $5,000 worth of compute. For example, the Claude uh $200 subscription, you are technically getting $5,000 worth of compute, meaning they are viscerally burning money. um you are getting like the best value on the $200 a month subscription recently the last couple of days and especially like the last two days um Anthropic has been like cutting down on this right and open AAI on the other hand has been increasing rate limits right? So when I look at this from a cost perspective if both of them are equally just as good what I want is I want to use the platform that's going to give me the most compute meaning I can keep going back and forth with it and I don't get rate limited I don't have to wait till next week to use it again. And OpenAI's rate limit, Codex's rate limit is extremely extremely generous, right? So, because I have no loyalty to any of these applications cuz none of them pay me, I'm going to pick the best one for my pockets. And that's when I was testing both of them yesterday. Codeex's rate limits were just great. And to your point, they pushed a lot of updates recently. So, it like based on all that, it felt like the best choice to recommend.

So, so simply put, codeex at this point in time that you and I are speaking will allow someone to build more to to go back and forth with it more to build more things for the same or similar price than what Anthropic did with Claude Co-work or Claude Code.

Yes, exactly. You're going to get more value for the do for the subscription you subscribe to with uh Open AI. before we get deeper into it and how you would go about building your first like AI agent using codec that's actually productive and useful whether that's making money or saving you time. Can you just share some examples with people of what codeex is actually capable of like use cases that you've seen either for yourself or with peers, friends, creators, uh people online of like what they've been able to build with codeex.

For mine, there's a couple of things. First and foremost, the uh biggest like time sync for me um was going back and forth um was not even going back and forth was researching sponsors, right? There are a lot of people that will email me, especially in the space I'm in uh because like everyone's building an AI now. There's like thousands of emails I get per day. Like my email unfortunately is has been vicinerated. So, I have this one specific workflow where every single day, right, around, I would say 10:00 a.m., uh, I have a workflow that does the following. Check my emails, right? Check if any email. So, first it's going to check my emails. Then, it's going to check if any email um is from a potential sponsor. Now, the agent is able to catch this because usually they'll put it in the subject line or be in one of the emails. It's pretty easy to catch the sponsor. I'm about to share some secret sauce. I probably shouldn't have, but I'm I'm going to share some secret sauce. Then what my agent's going to do is it's going to research if the company's raised money. I'm going to share why. if the company has raised money first and foremost um in this AI space, dev tool space, software space, um especially for my niche um which is like technical and non-technical people more so technical people um that's a valuable audience, right? And a lot of the companies that want to sponsor a channel like mine raise are raising a lot of money now. And if obviously if you raise the money, there's two things. First and foremost, you're a legit company, right? So, we've verified leg legitimacy here. Well, most likely. There's I'm sure there's scams that raise money, but the likelihood of it being a legit company is high, number one. And number two, they have money to spend. So, the price is going to be high. Uh, so I get my agent to do this. And then my agent has its own email, right? I use a tool called agent mail. And I'll explain like different tools to integrate uh later in the video. My agent has its own email and then it's going to email me and this is a private email I have that no one has access to but my agent. It's going to email me if the sponsor is worth it. So what this does is this is basically checking if the email I got from a sponsor is it worth it or is it not like is it worth looking into it? Is it worth responding? And I would say nine times out of 10 this works, right? The first few times I had to really massage it, right? There were a couple rules I added. For example, most likely a sponsor that hits me up with an@gmail.com. Could be like a scam cuz there are scams out there. Like there's a friend of mine who's a YouTuber who connected to a landing page that was like, "Oh, connect to your YouTube to so we can see your analytics." And like he got hacked, right? So, I have to be careful with these things. So, something like this saves me a ton of time. Another one, and this is the one we're going to build, is the sponsor report. And the reason why I like these is because this is the type of workflow that everyone watching this can set up today. There is some sort there's data in your life that is scattered between multiple sources that can be aggregated together to be used a piece of information that is valuable to you. Right? Reports aren't just boring old documents. It's an aggregation of information that should be useful to you. And the report that I generate is you get YouTube views, right, for a specific video, views for a video. You're going to get link clicks for the sponsor. You're going to calculate all the nerdy marketing CTR. I don't even know half what half that stuff's mean. uh and other metrics generate a HTML page. Right? This again was something that I dreaded that I had to do and it also got to a point, you know, praise the Lord, I started to grow and a lot of sponsors started to hit me up and I thought, you know, I'm an agent. I don't get tired. Let me accept 15 of these and now I'm overwhelmed. I have 15 different things to generate. This saved me a ton of time, made me super productive, and this is the best example I want to go with because again, I don't want people to watch this. If you're watching this, I don't want you to watch this and build the same thing that I built. What I want you to see is I I purposely picked built an example, picked an example that's going to show you how to think about it. And then I want you to dream. I want you to like whatever it is in your life, you could build a workflow and to build that.

Yeah. You know, it's such a good breakdown and and a few things that just listening to you use cases that came to mind. I'm even just thinking and and you confirm or deny this just came to my mind. Even if people are looking to kind of track their uh like personal expenses in like a more systematic uh way. If you're looking to get into content creation, you post on Instagram and you want to get like weekly, monthly, I don't know, quarterly updates on like your analytics, what's working versus what's not working. To your point, there's so many places in our life where we're getting data or information that we're not tracking. It could even be like meeting notes from uh like your weekly meetings at work. You want it condensed into a brief. No, even food that you're eating like you like you said it perfectly like you know how there are these expense tracker apps like you got to take the picture and stuff you can use the agent you can literally take a bunch of pictures of your receipts throughout the day dump it into the agent and tell it oh put it in a spreadsheet and you could download that spreadsheet like anywhere you can ingest information it can be turned into something valuable and that's what I want people to think of when they think of workflows think of all this information that exists around you around your business and personal life. Ask yourself, are you efficient with the information? The answer is no. And if the answer is no, how can I feed this to an agent and produce something actionable that is actually beneficial, whether it's condensed information or it's actual work done? Like that's like if people can think about that, then you know this is a W episode.

You know what, Mike? Here's here's where I want to go, which is let's say that someone's watching this. they have a few hours, you know, coming up this weekend, um, or like a free evening and they want to build their first AI agent that's actually productive, like it either takes work off their plate or helps them do more in less time. What in your mind is the step one? Like where should they begin if they're going to use codeex?

Yeah. So, there's two things and like I I want people to make an honest assessment of themselves. Step one, if you are like point number point one point I want to make if you are delusional like uh uh Callum shirt says meaning you you just have this drive where you're going to figure like you don't need to be motivated to do things. You're going to drop to step number two which is we're going to build a workflow. We're going to build a workflow. But if you're someone who needs a little bit of motivation, you need to watch a David Gogggins video before you get into it. I'm actually going to tell you to open Codeex and create a random app. Here's why I say this, and I know this has nothing to do with workflows. The reason why I say this is I found uh Callum, especially with people who are nontechnical, when they just create something random, and it doesn't have to be polished, it doesn't have to be finished, it doesn't have to be live, but when they create something random and and they see it and like it's functional, the dopamine hit you get is the equivalent to whatever class A substance is popular now. like there is just just this excitement and drive and like like I remember I got one of my church friends to do this and he hasn't stopped since. Right? So if you are someone who was like man I've tried these tools I'm just I'm tired you're going to open Codex and I'm going to show people how to do that. Um, but for anyone else um who's just ready to go there's a couple there's one specific tool we're going to need. Now, a lot of people don't share this tool, so I'm going to share this tool. And this tool is called Composio. You're going to go to Composio.dev and you're going to make an account. What Composio does is Composeio becomes, and this is going to be a new term for people. It's going to it's called a tool router. And basically what this becomes is this becomes like the layer that allows our AI agent to connect to anything. So let's say I'm using uh OpenAI, right? We'll call it O AI. And I want OpenAI to connect to my analytics platform um called Dub, right? I use an analytics platform called Dub. What Composio does is I give OpenAI instructions that Composio gives me. OpenAI connects to Composio. Composio then connects to Dub and then Composio feeds that information back to OpenAI. So now I can give OpenAI access to all the random tools that exist if they're in the Composer directory while not giving up my password, right?

It's like the ultimate middleman in a way.

Basically, it is the ultimate middleman. It's like the guy with the trench coat. What do you need? And they have everything. They have a generous free tier. This is one of the tools we're going to need. Um, this is going to be basically our main connector. So I would say, uh, Callum, this is step number one.

When you say connector, Mike, can you just make it clear for people what is it? What does that mean?

So, the agent can do things, but it needs access to your information. For example, let's say I want to give the agent access to my email. It needs to connect to Gmail so that it can read my emails. That's what I mean by connectors. Literally, all you do on Google is go openaiex download. The URL you're going for is openai.com/codex. I've already installed it. You can install it. And then this is what the app looks like. That being said, plugins is basically how you connect external services, external tools to um codeex. Now I can see here they have uh one that allows me to control my Chrome browser. They have one where I can create and edit spreadsheets. I can create and edit presentations. So again, even looking at this, I can sort of already think of things like, oh, I could do my taxes, whatever. I could connect my notion, right? This is pretty cool. Now, let's say I wanted to connect my notion. How I would do it? I would click the plus button and then blah blah blah blah blah. I'm just going to tell it to reference memories and chat, meaning I want it to remember the stuff it's done. And I literally click install and it's going to basically connect my notion. So this is what connectors are.

Yeah. So, so just to make this um clear for people when they start using codecs, open AAI already has plugins like connectors with a bunch of companies like typically the biggest companies your Gmail, notion like things that you would use. Where composio comes in is composio. So that is openai connecting directly with this third like this other third party company. Composio is like this middleman that you can uh it will have the integrations with your yes your notion and maybe I don't even know like an Instagram or

like someone using Netswuite right like something random right like

they're not going to build a Netswuite integration because it's probably not popular maybe it is I'm wrong

co composio their whole business model is there's thousands of tools that these companies don't care about we're going to make it easy to connect. So, if something isn't in the official plug-in directory, guess what I'm going to use? I'm going to use Composio.

Yeah. So, you you get access to more plugins.

Um, how how do you actually integrate um how is Composio integrated?

Yeah. I'm going to go to Composeio.dev. Right. This is their website. Ooh, very fancy fancy. I'm going to create an account. And um when you are onboarding, they're going to give you two options. They're going to say, "Is this for you?" Meaning, do you want to connect apps to your AI client or are you building a platform, right? Platform is for the developers looking to build on top of Composio. What you and me want is the for you. So, I'm going to click on for you, and you're going to see it tells me, "Welcome back, Michael." Um, explore what's possible. You can see here it says, "The most used app is YouTube. I connected YouTube um to my coding agent and I'm going to show an example of how you connect apps. There's a plethora of cool things here. You can actually click on connect apps and you can like look at I mean I'm scrolling and I'm scrolling really hard. Like there is a lot, right? Like I'm still scrolling. I'm still scroll scrolling. I I think I I even just saw Poly Market, right? Like if someone wants to connect their agent to Poly Market, you can, right? But how do I make this connection? The way you do it is you click on install, right? And it gives you actually a couple options. Do you want to use this with OpenClaw? Do you want to use this with Claude Co-work or Cloud Code? Or do you want to use this with Codeex? And all you have to do is I'm going to click install. Any of these work, but I'm just going to show you what is going to work the smoothest for you. You're going to click on MCP and you're going to click on API key. And then you're going to I'm going to reveal this uh but then I'm going to change it. So if any of you pesky hackers is watching this think you got an API key of mine. You did not. You take the same screenshot. So I take this reveal this right here. And then I'm going to drag this and I'm going to say I want you to connect to Composeio so I can so actually so you can connect to external tools. I'm literally This is what you do. You hit enter and it sets up itself. And the reason why this is possible is because the agent writes code that's going to connect to Compose. And Composeio is built in a way where it gives you access to all these tools, right? And to show you how this works, I'm going to go back to Composeio and let's say I wanted to connect um what's a good thing to connect to? Let's say I wanted to connect to

cal.com. I use cal.com every now and then. I'm going to say I want to connect to cal.com using composio. I'm going to hit enter and we're going to see what happens. What's basically going to happen is the agent's going to realize, oh, I have Composio connection. Composio has access to cal.com and it's basically going to give me a link to connect to cal.com and then composio is going to give codeex access to it.

"Yeah," let me know if that verbiage makes sense.

"No, it it does make sense. One one thing I wanted to point out and it's something that I'm noticing as you're going through this the cuz this is my first time actually seeing uh codeex and even like its interface. It's very similar and and you let me know Mike. It's very similar in how it works to just using chat GPT. I know I know most people have obviously used chat GPT at least in America. uh is the functionality feels pretty simple and intuitive for someone that's used chat GPT."

"Yeah. And I think what they're going to do is they're probably going to merge the app. Like I think codeex is the experiment on like developers and like getting them to like getting them to see if they like the model and then because the Chad GBD interface is pretty familiar with most people, they're probably just going to merge the two, right? So that's what I again my honest guess I think it is. And yeah, like and to your point, like it shouldn't terrify you, right? Um, it looks the same, it feels the same, it's just a lot more powerful."

Now, going back to this, it says Composio found.com toolkit. There's no active connection yet. It says I'm going to start an offflow. So, this is basically it trying to connect to the MCP server. I'm going to allow this to happen. The cool thing is, um, these agents won't go rogue without your permission. It asked me, can I make the connection? I said yes. Now, check this, Callum. It says, "Open this Composio link to connectcal.com." I'm going to click this link. And now what Composio is basically doing is it's it's basically making me log into the app. Compose handles the credential management. My agent's going to have access to cal.com. So I'm going to click on allow. It says successfully connected. Let's go back to codeex. And then it says the cal.com account is uh active. I'm doing one readonly probe through composio. So we know the co the connector works beyond just off. Now someone might say how the heck am I supposed to understand some of these words. What you do is you copy this you open a new chat. What does this mean? Literally like it and and this is how I started my career. It's like just asking like the instead of like being threatened by the difficult words asking what they mean. And you'll be surprised they actually are very simple.

"Yeah. I think it's such a great point, you know, especially what you mentioned earlier about um like future proofing yourself."

So many people that I speak to have this like uh fear and anxiety of being like replaced in the in their job and in their occupation by AI. And it's like, yes, these learning how to build with these agents can be incredibly useful right now, but also moving forward in the future, that kind of like hustler, selfarter, self-taught mentality of like I come across something that I don't understand, I take that thing, I give it back to AI and ask it to explain it and I learn is actually to me it feels like what's going to be a key skill uh for people like moving forward in this kind of new era of AI that we're going into.

100%. Because like you have to think about it, right? Like just a couple years ago, you were sort of limited by the uh you know amount of knowledge and information you have either within yourself or in in close proximity of the people you have. Now for like $20 a month, I have PhD level intelligence in front of me, right? And it would be such a bummer to not take advantage of this. And even in like my development journey, there's a lot of technologies that I would be I would have been afraid to try. But now I'm so delusional with it. Like I'll try new things. I'll build random things. Like my mindset is there's nothing I can't build if I have the right information. Now I have the right information. Is it going to take time? Of course. It might it be painful? Of course. I'm sure everybody watching this knows greatness takes time. Anything worth value takes time. But now I have the information. Information is no longer a blocker. Right? That's how I would love people to take these tools, right? Like like that that this tool can help me progress and push forward.

"Yeah. I I I love what you said uh greatness takes time. Um, you know what you mentioned it earlier like for that delusional person uh for the person that's like high agency, self-starter, just wants to make things happen, wants to build. Um, you said that the the step one for them would actually be to build a workflow. And so I want to talk to that person for a second. When you're thinking about workflows, I know you have like the sponsor agent. How can someone even decide what workflows would actually be good to have their AI agent take over? Like talk me through your process of how you even identify the workflow that makes sense to use codecs with."

Back back to the diagram. So how to create how to think about workflows? This is how I think about them, right? A number one, anything repeated often. So if there's any task in your life that's often repeated, right? Um like whether it's checking emails for a specific thing, whether it's like you know synthesizing specific information, anything repeated often can be and should be a workflow. Um, number two, um, and this is I would call this discovery. Um, you know, data is a gold mine and believe it or not, most people because they use 15 different tools have a lot of data about themselves, right? Um, most of us are probably not performing at the level we want to, right? And there's all these different things that we have to do. So the second type of workflow is what I call discovery and that is you know connect you know every tool that is important to me right email being one of them notion might be another one um you know Figma linear whatever those tools are and basically having a discussion with the agent on the stuff that you do right and when I say discussion it can be um what are some actionable things that you see that I should do from all the information right like read my emails read my this, read my that. What are some actionable things that I can do? Um, generate a report on how much things I've done. Like the the way I want people to think of workflow is I have all this I have this agent, right? I have OpenAI codeex right here. I have all these pieces of information, right? I have this right here, this right here. Uh, I have this tool right here. I have this tool right here. I have this tool right here. All these different tools that I'm using. The way I want people to think is to use this agent as a synthesizer for all the external tools they use. Combine that information and see what productive thing can be done. So a lot of it unless you have repeated work is discovery. But in discovery I've noticed a lot of um useful things. For example, um I didn't know that like when I when I'm talking about discovery, I didn't know that I was spending um I had a lot of emails unread. Meaning like I would have this problem of I would open an email in my mind sometimes my mind races so fast in my mind I've responded. I've written the response in my mind and sent it but I'll go back and I'll do something else. And the one thing the agent caught is like there's a lot of opportunity in your emails that you haven't responded to. Right? Again, not like it wasn't a thought of a workflow in the moment, but I realized a like I'm really bad with my emails, aren't I? So, every week I have a I have a an agent. Every week it checks all the emails that have been sent in that week. Have I missed any opportunity? Is there anything I need to check? Is there anything um uh I need to anyone I need to respond to? And anyone who's emailed me at least twice knows at least one of those emails I responded a week after that was sent. And that's because the agent reminded me and I responded, right? So I would think of repeated things first. And then number two is I would go discovery mode. connect all the external tools that you use that have your information like that you work on whether it be your email calendar whatever it is and synthesize that information to see what can I improve what can I automate what things am I slacking on what can I do better am I do I need all these tools right think of it like a consultant right like it's honestly a great consultant uh when you steer in the right direction that's how I would think about workflows

"Yeah, you know what two two things come to mind cuz what you said is so good so so the first thing is and This is what I did is actually so you said anything that's repeated, anything that you're doing weekly. And so one thing that's helpful in the beginning is actually just starting to document what are the things that you're doing on a weekly basis like either writing it down or putting it in your notes and you'll come up with this list. It'll give you the list of just potential workflows off of that. The second thing, and I actually hadn't thought about this, and you mentioned it with uh discovery, is in this digital world that we're in, we're being bombarded with so much information, whether it's like our inbox, social media, um like text messages that there's like, and it's actually kind of scary to think about, all of the things that we're not aware of, like the thing that we forgot, but is actually important. uh an opportunity that we were like excited about but we let it drop off and now it's gotten buried. And it's funny because um one of the things that I'll do and maybe this is a use case for me personally and I'm sure for people that are listening at home is uh when I'm on Instagram I will be like saving posts like if I see a post that could be like good inspiration to create content or I want to respond to I'll save it. I'll do the same thing on Twitter and I just have like these uh these bookmarks full of posts. I never look at them again."

"And it's like you could have an agent I I think that's like a relatable thing. You could have an agent that's surfacing like learnings or things from these posts so that you can actually use them."

And this is why I hate when people download or use people specific workflows because you've now limited yourself to their box, right? The whole point of this is for you to like start wide and start to figure out what makes sense to you. And in in this case, like for you, you said um that use case made sense. In my case, this use case made sense, right? So, it's just a matter of connect tools, figure out what to do with this data, something actionable comes out of it.

"Yeah, I I I think it's such a good point of like the whole game is making this work for you. And so, uh, Mike, if someone's listening, I want to go back to, uh, codeex for a second. And I'm thinking about what you mentioned in the beginning, which is like most people build AI agents in completely the wrong way. Like they do it the opposite of how you should. I've even I've heard you talk about that. Um, like they maximize for what looks cool over what's actually productive. Can you share? So I've connected codeex with composio. Composio has access to all of these plugins. What am I at high level? What am I doing so that I actually build the agent that's productive?"

Connecting composio was as simple as follows. You create an account. And by the way, you can you can do this. If you're like a this is too, you can do this. I believe in you. You go to install. You go to codeex. Click on MCP. click API key, reveal this. You can copy this and paste it in the chat. But then I would take a screenshot of this and then you send it over to uh Codeex, right? And basically what I to what I tell Codeex is the same thing I did here. Like um where is it at? Right here. I basically dropped the screenshot and I basically told it to connect to Composeio. When it connects to Composio, this is what's going to happen. It's going to say Composeio is configured locally and I also asked it to connect to my YouTube. Once Composeio is connected, right, that's the first step. Connect Composio. Number two, you can go to connect apps on Composio and you can search if your integration exists, right? So, let's say I wanted to connect Twitter. Let's say I wanted to connect Proplexity. Let's say I wanted to connect to Google Docs. In this case, you see I connected YouTube and I connected Dub, right? Again, connecting was as easy as this. Like I'm going to show you another example. Like this is the easier easiest part. Like anyone should be able to do this. I want to connect dub.co for my analytics. I've already connected Composio. It's as simple as me telling it, let's connect. It gives me a link. I click the link and then it connects it. In fact, here's the thing. And I'm glad I took a screen. I I kept this. I clicked the link and I went to the washroom. I had to freshen up for this interview. Um, and I took too long and it said invalid or expired link. Now, the nontechnical person is probably going to see this in panic. What do you do when stuff like this happens? You take a screenshot and you give it to the agent. And that's exactly what I did. I said I even apologized. I shouldn't have, but I did. I said, "Sorry I took so long. It expired." And then it said and it fixed it and I asked for it to pull some analytics and then it did. Right? So the basically what I'm what I what what the first step is you connect compos. Second is how do you connect further tools? You literally just have a conversation. I'll show one more example so people don't think I'm crazy. Let's connect um you know what linear I'll connect linear. Linear is um a tracking platform for developers on to track progress like what you've shipped, what you haven't. So I'm going to show you how easy it is to connect Linear. I'm just going to start a new chat and I'm going to say please connect to Linear and I'm going to send that and we're going to let the agent think and the agent is going to give me u uh uh whether it be a link or a button to connect. So this is the first thing that I want people to do is just connect the tools that you use. Don't connect the tools you want to use. No, connect the tools that you already use. Right? So we can see here it's saying the linear tool name space is available. I'm going to make it read only. Oh, I've already connected it before. So it's like linear is connected and OOTH is working. Verified Michael Shimlas and these are the different teams I'm running. I say that all to say connecting and Callum, I hope I make sense, is literally as easy as telling the agent. You don't have to write code. You don't have to do anything. You tell the agent. You check a composio. See if it has the tool, right? See if it has the tool. If let's say I'm a Shopify store person, there's a Shopify connection. I can literally say I can go back and say, "Okay, connect connect to Shopify now." And it's the same thing. It's going to check. It's going to fire off Composio. Composio is going to give me a URL. I authenticate on that URL. And now I've given aid, my agent, access to Shopify. Does Does that make sense before I continue on?

"Yeah, that makes sense."

So, beautiful. So, I'll just create a new chat. I have a couple things connected. I have my YouTube um analytics. I have my YouTube analytics. I have my Dub connected. The one thing that I do is uh again I generate these reports. Now I held off on this tool because this tool should only be discovered by people who are serious and if you watch to this point you're serious. There's a tool I don't know if you're familiar with this um Callum called Whisper Flow.

"Oh, I love Whisper Flow."

So I'm using the free tier and the reason why I love Whisper Flow, Whisper Flow allows me to voice to uh voice to text with the agent. I click on the function button on my keyboard and I can talk to it. So I can say I want to generate um a report that basically tracks the performance of uh sponsored YouTube videos so that I can use it as marketing material uh for sponsors. Basically, I do a lot of content. Um, and you have a connection. So, you can see my content and some of the videos are sponsored and you can see the sponsored links um in dub.co and there's a connection for that. I want to generate a report that basically or some sort of marketing material that I can send to sponsors so they can send me their hard-earned money. Now, typing that would have taken me forever. But what's cool about Whisper Flow is there's a lot of information here that sometimes is hard to distill via typing because it takes too long. I will voice to text the heck out of this. Another thing that you mentioned, Callum, that I'll add, and I'll just hit enter with this is you said um to voice to text your day, your thoughts, and I would 100% do that, right? You can use notion, some people use Obsidian, really documenting your work, right, via voice to text and then feeding that into an agent. You'll be surprised how lazy we are naturally. Um will help you a lot. Right? All these things are very simple but when you put them together you start to become very very very very productive.

"I think talking a is a skill that everyone should have. So I mean using whisper flow almost like forces you. Um but b I find at least for me I get a lot of information out of myself when using whisper flow. Um, that being said, I typed in this giant prompt and this agent is added, right? It checked Composio. It checked the tools. It notices I have 50 recent uploads. It notices that I have 33 links and now it's trying to match um the videos. Now, this will probably fail. Now, the reason why this will fail is I gave it too broad of a task. If it succeeds, I'll be surprised. If it fails, I'll understand why. And I I'm lowkey hoping it fails, but if it doesn't fail, then it's just proof that the agent is smart. Um, but essentially what I did was not a good prompt."

"Yeah. My my my question to you, cuz you said I think that's really interesting. You said that you gave it too broad of a task in your mind. Kind of take people behind the scenes. What is the signal to you that you've given the agent too broad of a task?"

Okay. So, give me 60 seconds of your time because you're going to want to hear this. So, I've done over 200 episodes of this show. I've been doing it for 4 years. In the last 6 months, I started to notice a shift in the conversations. Things that the guests would talk about was different. The common message was that we had entered this new period of time where the rules to be successful and have a great business and a great life had fundamentally shifted and changed. And so, I started to realize that we had entered a new era. And so a couple of weeks ago, we launched a secret newsletter called New Era that pulls together stories, supporting documents, step-by-step guides, even unseen footage from the show, and we send it to you in your inbox every single week. And so, if you want to be involved, just go to the link in the description, plug in your email, and you will get an issue of our new era newsletter every single Monday in your inbox. Thank me later. Let's get back to the show.

I'm glad you asked and I have an example for that because I was hoping you were going to ask it. So I basically in this prompt said I want to generate a report that basically tracks this this pretty pretty general but if I go to the last um where is it is this one right here. I want to show you one interesting thing. I'm going to show you the steps I took it. So I first connected the tools right? So you can see here I gave it my API key and then it says it's configured. I told it asked it tell me what my last video did in views. This is a very simple prompt. I want my last video and I want the views. Can't get this wrong. It says it's currently sitting at 12,000 views, 800 likes, 44 comments. Simple, right? Now the reason why I told it to do this is this action is in the context window. meaning uh it's in the it's in the it's in the mind of the agent. The next thing I tell it is let's connect to Dub which is my analytics platform. G gives me the URL. Remember I I went to the washroom to fix my hair. Took too long. I said sorry but then it connected it and then look what it did. It says I verified a sponsor link from your latest video. Because I asked it to check my video first and it knew that I wanted the analytics for some sort of analytics. It checked the link that matches and it says here, oh, here are the current results. 534 clicks. This is the destination. This is the last click. I'm not tracking leads or sales or sales amount. And then it did it itself. It's like combined with the YouTube number from earlier. The current sponsor CTR is 4.43%. Right now, this prompt is going to feel lazy, and I'm going to tell you why it works. It's And I said, "Yes." Now, do me a favor. Generate a clean looking page showcasing this number. This is for a sponsor. I'm allowed to be lazy with this prompt because I've given it context with the previous conversation, right? It's like I don't have a perfect example, but it's like leading someone on, right? First, you're like, you know, I really like your shoes. And then you're like, I really like your t-shirt. And you're like, I really like your smile. At some point, you're going to understand, "Yeah, this person really likes me." Right? That's essentially what I've done, right? I first gave it access to my YouTube uh video views and then I I gave it access to my analytics and now I'm telling it generate a report. And what it does is, and I and here's the thing, I I tell it to generate a clean looking page. Here's why I do it. When it generates this page, it's going to write HTML. HTML is uh is basically a file type. It's what a lot of websites render. This file type is great for agents. Agents excel with HTML and markdown files. I told it to generate this. If I click on this right here, you can see that it generated this report. You know, not too shabby. If I don't like the style, here's what's cool about Codeex. They have an annotation tool. I can click on this annotation tool. I can select something and then I can tell it I don't like this font. I don't like this cut. Right? So, I can I can go pretty like specific with this, but I don't care. It generated this report and I liked it. Now, here is where you don't download people's skills, but you create your own. We had a successful run. So, you know what I did, Callum? I said, see, this right here is a great report. And you could tell I kind of talk it to talk to like I talk to the homies. I say, "Can you turn it into a skill where I just tell you the video and you generate these pages?" So, I've given it what I want the end result to be, and I've told it what input it can expect from me. What input it can expect from me is a YouTube URL. What I expect from it is the is this right here. And this took a second. This took 5 minutes. And here's one thing I want people to realize. Sometimes the agents will take time and there have like for example in this instance it was waiting for me to give it access and I didn't. So right I have to click allow and it's probably going to keep on working. But going back to this example and this is why I generated these examples ahead of time. Um cuz this video would probably been way too long. You could see it took its time. I could maybe work on another task. I can maybe do another thing. Again this isn't my full-time job. I have other work to do. But while this was happening, I could go do something else. After 5 minutes, it created, you can see here, created the reusable skill. This is very very important. The reason why this is important is the next time I want this done, which I have another example for you, I can tag it. So, I can click at on the text box and you can see a bunch of these tags like it it it it it wants me to tag one of these things. All I have to do is click generate and you can see this skill. This is the very skill I created. So, I created this skill and what I'm going to do is I'm going to show you actually in action. Yeah. Okay. This video was sponsored. I'm going to copy this link and I'm going to paste it. So let me paste it here. Remember I told the skill earlier. Let me go back. Um I told her it right here when I generated the skill. Can you turn this into a skill? What is it turning into a skill? It's turning the workflow basically the step by step I took. You see a lot of people Callum will tell the agent I want you to do this. I want you to do that. I want you to do that. Turn this into a skill. Wrong. Have a successful run first cuz sometimes it will fail. Have a successful run first. Once you've had the successful run, because that conversation is in the AI's context, is in the agents context, you're just going to turn it, we had a successful run. Turn this into a skill. These are the best skills. The best the ones that you generate after a successful run. I'll stop here because I think you're about to say something.

"Yeah. Yeah, I am. I love how passionate you are about this. It's it's uh it's good and and it's so useful and it's interesting the the point in time that we're speaking at because like I'm learning a lot of this stuff right now for people that are listening and might be unaware. Can you explain what is a skill in like layman layman's terms and then what if I'm looking to be more productive make more money save time what is the value of using skills?"

Skills. They're defa they're noted as skill.md files. What's interesting about skill files is they will they will contain instructions on how to do a specific task. But here's what's interesting about it. The specific task like the full task the instructions of the task are not fully given to the model. Right? I I'll even go a step granular. Every scale file contains the following three. the name, the description, and the steps, right? The name is the name of the skill. The description is it describes what the skill allows you to do. The steps are whether it's code or a step-by-step instructions. That's what the agent follows to do set task. What's given to the agent when a skill is created is just the name and description. Why is this important? The reason why this is important is we don't want to fil we don't want to fill the mind of the agent with too much information. Remember, if you give it too much information, it's going to be overwhelmed the same way you're overwhelmed and it's not going to perform well. Skills are a trick. Like, we don't want to dump in every single instruction that we have. And this is why skills are so important. It's minimal information that's called progressively. And when it's called, it gives all the steps. And all this is to make the agent more performant. Um hopefully that that made sense.

"Yeah. So it sounds like it's minimal information that is still guiding the agent."

Imagine having um this book and I have this book has all the information here but all I know and that's stored in my head is is the chapters. And if someone tells me, oh such and such chapter, I don't need to know it off hand. I'll just open a book, go to the chapter and read the specific thing. That's what the model does with skills. It stores the name and the description. It doesn't store the steps. But when it knows it needs the steps, it then reads it in. This makes it minimal. And you can think of this almost like a a computer. You know, the less the more memory you have, the more space you have in your computer, the faster it is, right? The more stuff it is with files. And the closer it is to its memory, you start to see it slugs and it's slow and it lags. That's basically what skills do for models. It just gives it enough information it needs to know when it needs it. And when it needs it, it calls the entire thing.

"Yeah. No, that's really clear."

I love that. So, that's what was generated here. Now, let's go back to the prompt I typed in here. Uh, this one right here. I said, generate a sponsor report, right? I tagged the skill, right? And how you tag skills is you type in at and you just type the name of the skill. In this case, this skill was named generate sponsor report. and I tagged and I gave it the YouTube video and it says I'll generate a second report. I'm fetching the YouTube metadata. It's asking me does it have access to call these tools. I'm going to say yes. And what's going to happen is it's going to pull in the information. Notice how it's asking for another request. I'm going to say yes. And again, if any of these lines don't make sense to you when you're using it, you copy this, you create a new chat, you paste, and you get answers. Um, and now it has the metrics. You can see here I have the live metrics, 15,000 YouTube views, 279 tracked clicks. I'm creating a JSON payload, rendering the page as a standalone HTML page. So, it has the information. It's now going to create this page. And in just a little while, the HTML page is rendered. I'm checking the output. Agents do take time. The smarter they are, the longer they will take. It says it's generated here. If I click, hopefully this works. And there you have it. I have a repeatable process. Now, let's say I wanted this done daily. What do I do? I go in my chat. I open up Whisper Flow. Thank you for generating this report. Can you make sure that this happens every single week? I want a report generated every single week for the latest video. I do upload weekly so it makes sense uh make that happen and I hit enter and now the model has the skill it has access to my YouTube channel what I've essentially created Callum right now is a weekly workflow where reports going to get generated and notice how it's it's so simple it's literally conversation it did it right here so it says set up a weekly latest sponsor report it will run every Thursday 9:00 a.m. American Toronto time. And if I click on this right here, I can see information. The the OpenAI calls them automations to sound fancy. Um, and look what it it generated. It telling me it's telling me here, generate a sponsor facing performance report for the latest public YouTube upload on the connected Ross Mike channel. Use the generate sponsor report workflow. Remember, we generated it earlier. Fetch the latest video metadata and statistics. Identify the sponsor dub short link from the video description. Fetch the dub link info and click counters. Calculate tracked link CTR. Then render a standalone HTML report plus a JSON data payload. Name the files with the sponsor name and the video ID. So each weekly run keeps its own output. Keep conversion caveats factual. Do not expose API keys, OOTH tokens, and account IDs or raw tool logs. This is going to run the next run. It says here May 21st, 2026 at 9:00 a.m. the status is active. This is going to happen every single week. Now, how I built this, I didn't see someone on YouTube build this and copy them. I built this on based on what's useful to me. So, connect your tools. You can use OpenAI's native plug-in marketplace. If the tool doesn't exist there, which most likely it won't, you connect Composio. Composio is as easy as going to the dashboard, taking a screenshot of the instructions, giving it to codeex and saying connect. It will do it. And then after that, ask yourself, what tools do I use? Ask the chat, I want to connect to this tool. Every time you ask to connect to a specific tool, it will give you a link. You will authenticate. It will bring you back. And now the agent has access to it. Then you can enter discovery mode. I want you to do this. I want you to do that. I want you to do that. And when you realize a couple of the steps that you did, you want it to be done consistently. What are you going to do? You're going to turn this, you're going to tell it itself, turn this to a skill. Once it's a skill, it's become a workflow. And if you want it to happen on a consistent basis, nothing fancy here. I literally said, "Thank you for generating this report. Can you make sure that this happens every single week?" And guess what? It set up an automation and it does this every single week now. So, on May 21st, next week, 9:00 a.m., I'm going to get a message from CODC saying, "Here is the latest report."

"Yeah. You know, you know what, Mike? It's so good. And and thank you for sharing that. And the reason I say it's so good is because of what you mentioned in the beginning, which is that it's simple. It's not 50 different agents and these like complex workflows and demos. It's very simple. And so when you and I spoke, I actually wrote down three steps, which is basically step one, you you're using uh codeex, you connect it to uh composio. Step two is pick a real task that you do every day or every week. Um, and you coach the model step by step. So you go through that workflow step by step with the model first so that you get uh like a great output. Then once you've got a great output from the agent, you then tell the agent to turn that into a workable skill and then you put it on some sort of repeated cadence. You know what, Mike? So, I'm going to ask a a selfish question here because back to my experience of using Claude Co-work and like reflecting on it because it was a frustrating and like a demoralizing experience cuz I spent hours setting it up and then the output that I got wasn't useful. And the funny thing is it told me at first it's like yeah it won't be great at first but it'll get better over time and all this stuff. And what happened in my experience because I didn't get a great output to begin I didn't really use it moving forward because I knew I wouldn't get a great output. And so when we talk about the steps I think that step two of people understanding kind of how to coach the AI agent initially to give them a great output. That is the key step because once you get the great thing then it's so easy as you've just demonstrated to turn it into a skill. But I'm curious for you, can you talk about your experiences of getting a mediocre output or like a suboptimal and average unusable output from this process and then what are you doing to actually make it good so that further down the line you can then turn that process into a skill."

"Yeah. So, I uh grew up in an African household. Uh which means if my grades were an A+, I got beat, right? And some might call this craziness, but now I look back at it and this was just a great feedback loop. I do good, I don't get beat. I do bad, I do get beat. I bring that example up because you are going to have runs where, again, I'm going to use this diagram so it's super super clear. You're going to have runs where you are just going to be frustrated because what the agent gave you, what you you gave it a good prompt, what feels like a good prompt and what it gave you was pretty mediocre. What you are going to do is you are going to continue to work on it recursively as if it was an annoying family member that you're stuck with but are frustrated with. What do I mean by this? Most of the times the agent will probably mess up, right? Um the models are getting better. So luckily it worked out on our end. But let's say it messed up. And in this case there was a perfect example of actually not even it messing up but I think me taking too long. If I go back here, I took too long and it expired. And I know for a fact most people would see this and would just panic and would probably give up. What I want you to do and this is depending on the task might be timeconuming is you recursively work with it meaning you tell the output that it's given you is wrong and it needs to fix it fix itself. So let's say it tries to connect to something and it fails connecting you're going to tell it you failed at connecting at it please fix this. You'd be surprised by the third or fourth time it figures it out cuz each time it'll probably try a different strategy in doing so. When it comes to creative work, this is probably the most painful because in creative work, um, the sauce is not trained into the model, right? Your specialty, your flow, your cadence. And I know there are a lot of people that are like, "Oh, I'm fine-tuning a model, so it sounds like me." Um, humans are very unique in where a lot of the things we do are very subtle and are very hard to replicate uh by a machine. So when it comes to stuff like that, the feedback loop that you're going to give it is the same loop that like my parents did. You do good, we create a skill. You do bad, we continue to work with you until you create a skill. It's literally just back and forth. And and this is why I'm saying like the models have gotten really good. The models are so intelligent now where if you tell it this was the wrong way and then you show it the right way or you go back and forth and it does it the right way and you create a skill, guess what happens in the skill, it will write, I tried these different ways and this was wrong. The person didn't like it or it didn't work. Never use this method again. Right? So step two to your point and you put it perfectly is the most important and it's probably the time you spend the most. Now, if it feels frustrating, I want you to think of this as a human that's being trained on the job, and you would have a little bit of compassion with a human. I hope at least you would be nice to someone who just started working for you. In the same way, I'm not saying be nice to the model, but understand there might be a little training that's required once you have that back and forth. And the back and forth is simple. It's just prompting. It's just communicating with it. Something breaks, you tell it it broke. Now, let's say Compose, let me give you an example of how I would fix an issue. Let's say Composia went down and now Composio is just no longer a company. I would go on the agent and I'd be like, I want you to search the web and find a greater Composio alternative and instruct me on how to set it up. I would go then set it up and if it breaks again, I would continue to prompt back and forth. And that's one thing I want to encourage people. If something isn't working, prompt the AI. If that isn't working, prompt AI. If Codex isn't working, prompt Claude. Prompting is where you fix a lot of the issues you might get in a workflow that's not working correctly. For some of you, it might be one shot, which praise God that works. But for some, it might take a couple of tries. Hang in there. Continue to work with it. Once it has a successful run, you're going to have the best skill of life."

"Yeah. No. Uh Mike, the the analogy of like the the African or like the immigrant parent is like very uh vivid. uh to me. Um but you know what? It's a it's a great one. And so I want to kind of go behind the scenes of your process for a second. So you get like a bad output from your agent and and you correct me if I'm wrong in this. You're hitting whatever that key is that activates. So you're like studying the output first of all, like you're looking at what it's given you. You're then hitting that key that gets you to Whisper Flow and you're like dictating out what was wrong or what you want corrected in the output. You're doing this process repeatedly until you actually get to a good output and then the instant that you get to a good output, you're like, "Okay, save that workflow as a skill." Is that correct?"

"That's that's exactly it. That's the That's the step by step summarized perfectly right there. Right. Because it has all the perfect information. It has all the right information in context. I just want it to be turned to a skill as soon as possible."

"Yeah. You know what? One one final thing, Mike, cuz you've been so great. When you set it up on this reoccurring basis and you walked people through how they can do it, so it actually, you know, every week it delivers this. Where is that output going to and do you control that? So, for example, are these sponsor reports, I don't know, before you even send them out, is it going is it like an email that it's sending you? Is it uh uploading it onto like your computer like on a local drive? Um, where is it going typically for you? And what have you found works best when you're using an agent?"

So, when you use something like Codex, Codex can do all of the things you just mentioned, right? So, I can have it just pop up in the chat, right? like like just message me in the chat when something's done because if codeex is important to my business then I probably have this thing open or I'm using it regularly. So it could do via chat. I can also tell it to email me. Right? Again all it would take is and this is what's so cool. All it would take is for me to connect my email and tell it, oh send it to me, right? Alert me. Um there are even tools that can allow you to connect it to a telegram or to all this stuff. And how do you like how would I go about setting this up? Check this out. Prompt it. I want you to send this information to my telegram or to this or to that and it will do it. And that's the cool part about these apps. So I say that to say if you want the information delivered to you via email, tell it. You want it

In a specific folder in your file system, tell it. You want it uploaded on Google Drive, tell it. It'll tell you to connect and you could do it. You want it sent to you via Telegram, tell it. How you want things delivered is completely and utterly in your fingertips. The power is in your hands. It's just as simple as prompting you.

>> Yeah. No, that's so good. What have you found has worked best for you?

>> Um, I'm an iPhone guy and I really like Apple. I like, I really like iMessage. Um, so I have like my own, I can show it here, but like this is like my own agent. But I think if you're starting out, I would really focus on using the app and getting used to the app because the app has so much functionality. Like another thing, and this is just a side quest that people can do, is you can type at and I believe I can click like build. Yes, I can tag build iOS apps, which is like a plugin they have, and I can say build me a to-do list app that looks like uh the Apple native reminder. And I also want you to add light mode, dark mode, toggle, right? And then I can hit enter and I can let this work. I can work on another task, right? I think there's value in getting used to the app, right? Especially if you're new, focus first on the app. Get good at it, use it, tinker around, click all the random things, touch all the settings, like just, you know, use it profusely. And then once you've got to a good stage, then you can worry about okay, I can connect it to my iPhone to this to that because I find that a lot of people will do all the unproductive stuff that's cool and then be like, I just wasted so much time, like all of this was kind of like useless, right? But if we scale for productivity, make the productive thing first, then it just becomes something you're stuck with. Like I can't stop using agents because they make me so productive, right? So that's um, how I would think about like where to use and how to use the things. I would stick to the app first.

>> Yeah. I'm curious for you reflecting on kind of what you've experienced and getting to the point that you are now, what would you say to the person that's listening, if they had to take one thing from this conversation and even really just from hearing your story and experience, what would you hope is the one thing that they would take from you?

>> Yeah, like I, I genuinely think all the information you have is available, right? Um, it's there. It's on YouTube, it's on Twitter, it's on, it's, it's, it's all there, right? What is important is consuming information and then acting upon it, right? Um, a lot of people um will consume and not do. And I've done this before. Or I've been like a tutorial junkie before where I'll watch a bunch of tutorials on how to do X, Y, and Z and it, and there is a dopamine rush in learning something new. Uh, but that can also be a mistake because you want to actually do, right? So I would consume information and do. I would consume information and do. And I found that especially in my own personal experience, after a certain amount of time, at some point you become better than what's average, right? Like I remember in August 2022, I decided to take um, Harvard had this, has this free course called CS50, which is like an introduction to computer science program and it's like an eight-week program and it was probably the most like humbling, borderline humiliating uh thing. And by the way, look, the app is being built itself while we talk.

>> Yeah.

>> It, it was very humbling and and like I almost felt embarrassed because I, I just didn't feel I could keep up. Like it was so hard. It was so difficult, but I stuck to it and that led to me building my first few apps. I sucked at it. I stuck to it. That led me to starting a startup. Um, that startup did really, really well. Um, I stuck to it, but then I had a feud with a business partner. I ended up leaving the company with no equity, no cash, no money, even though that business was doing like a couple million dollars a year. I stuck to it, right? And then I got my first corporate job. It was annoying, but I stuck to it. Right? So there's just like this consistent nature of like sticking to this idea of learning and improving, learning and doing, learning and improving, learning and doing. And it never happens right away, but you'll realize at some point, whether it's a year, six months, two years, at some point you'll realize, oh, you're a lot more smarter than you used to be and you're a lot more valuable than you are. And like, and that's the big thing, right? Like when a lot of people are like, oh, these tools are scary. This is even if it feels like a technical tool, so what? Try it. You know what I mean? So what? You, you don't know how to cope. So what? Give it a try. Use AI. Ask. Fail. Try it. And if it sucks, it sucks, right? But at least try.

Um, another thing I'll say is and like um, like a lot of one thing that grounds me is like my faith grounds me. Um, you know, I, I have motivation. I have a family I need to take care of, right? So aligning all these things together um makes it so that like yeah, there's some things that I don't understand. So what? There are a lot of people don't understand. Let's go learn it. Let's invest time. Whether it's buying a book, whether it's watching some videos, whether it's trying it out, whatever it is, whether it's paying for somebody's time, um, the information is out there. It's just a matter of who's going to do the work. And unfortunately, most people won't do the work. Mike, man, thank you so much for coming on and being so open and not gatekeeping. Um, I really enjoyed this conversation.

>> I, I and I appreciate you having me and, you know, for sharing and just to show everybody, I know we're closing up, but like yeah, the, the, the app's done and like that was one prompt. So, like you have access to this. There should be no reason why you don't try. At least try. Um, but yeah, Callum, I really appreciate the opportunity and the time and yeah, thank you for for allowing me to be here.

>> Yeah, it's pretty crazy that like as as we're talking, the the AI like the the agent is just building the app and it's like popping up on the screen. Uh, that's cool.

>> That's cool.

>> Thank you, mate. That was great.

>> Appreciate you, Callum. Thank you.

>> So, if you enjoyed this conversation and you want to hear even more stories like this, then just click here. And also my team is going to put some more videos that you can watch here.