The n8n Masterclass
Welcome to The n8n Masterclass. I’m Dylan Watkins.
Each week we break down real business wins using n8n and AI automation. You’ll learn what worked, why it worked, and what broke along the way. Founders, automation experts, and AI agencies share how they use n8n to simplify operations, scale delivery, and move faster without adding more people.
The n8n Masterclass is not about tutorials or tech jargon. It focuses on the real business side of automation, the frameworks, decision patterns, and creative problem solving that turn workflows into results.
You’ll leave every episode with one principle, one pattern, and one action you can apply this week to grow your business, reduce manual work, and unlock the potential of automation.
If you’re building a business that runs on smart systems, AI, and no-code tools, this is your playbook for scaling with n8n. Follow The n8n Masterclass and start using automation as your competitive edge.
The n8n Masterclass
How n8n solved Cowork’s Biggest Pain
Use Left/Right to seek, Home/End to jump to start or end. Hold shift to jump forward or backward.
Most people hear about Claude's Cowork features and wonder how it actually fits into a real automation stack. This episode is the answer: a full walkthrough of connecting Claude Cowork to n8n, building a production-ready email classifier from scratch, and the token-saving tricks that make it all sustainable.
Ryan Nolan, who runs a data science YouTube channel and deploys AI automations at his day job, joins the n8n podcast to share his exact playbook for pairing these two tools.
The conversation covers setting up the n8n connector in under 60 seconds, calling external APIs through n8n workflows, building an email classifier with human-in-the-loop approval and error handling, and the new Google sign-in flow that eliminates the painful credential setup process. They also dig into why Claude's computer control is too slow for real scraping, and how n8n workflows are a better fit.
On the enterprise side, Ryan explains why compliance teams need structured execution logs (not just Cowork skill histories), how to roll out AI automation department by department, and the hackathon where a team with zero n8n experience built a driver's license verification workflow in two days.
🎙 Chapters:
00:00 - Introduction and episode overview
02:23 - Connecting n8n to Claude Cowork
04:21 - Calling APIs from Cowork via n8n
10:27 - Building an email classifier workflow
14:51 - Tips for prompting and iterating
13:42 - Compliance and audit logging
24:10 - Saving tokens with n8n workflows
32:31 - Enterprise security and skills vs workflows
36:48 - Reviewing the built workflow
39:41 - Quick Google credential setup
42:10 - Execution history and debugging
44:01 - The hackathon story
46:45 - Advice for getting started
51:43 - Running with David Goggins
Get 30% Off n8n Cloud Starter or Pro Plans!
Want to get started with n8n? Visit n8n.io/pricing and use code 2025-N8N-PODCAST-729C416E at checkout for 30% off your first month or year.
Click on this plus icon over here, then it's gonna say Claude wants access to your NAN instance, choose allow. You see success, open up Claude once again, connect it to NAN. Literally, that took 30 seconds, if not that. In cohort, you can chain together skills, but this is gonna eat up your tokens a lot. If you already have an NAN subscription, go down to NAN workflow. Instead of having all these skills run, all your tokens and hitting those Cloud limits. Why don't you use the executions that NAN gives you? Sign in with Google, choose your account, account connected, five seconds. I remember my first time setting this up. I was, man, there's so many different steps. This is super technical. Now there's like no reason for anyone to watch that YouTube video how to set up Gmail Credentials. We're gonna be learning about how to use Cloud Co-work with NAN. We're gonna go through a real practical workflow, something super basic that anyone can start today. And we're gonna go over 10 to 11 different benefits of utilizing this.
SPEAKER_01You've probably seen Cloud Co-work all over your feed, Anthropics desktop app with skills and connectors. That lets Cloud actually do things on your computer. And the question that every NAN builder is asking is how do I use this in my existing workflow? Ryan Nolan runs a YouTube channel, Ryan and Nolan Data Science and works at Bill, where he's been deploying AI automations across departments. He's the right person to answer this. And today's episode is the playbook. He shows us how to connect cohort and cloud to N8N in less than 60 seconds. Build an entire email classifier with the Gmail human loop node and air handling. The token saving patterns that most people miss, every N8N workflow that you call from Coort doesn't. The new sign-in to Google credentials that turns the hardest part of N8N setup, the Google Cloud documentation slog, into five seconds. Plus the enterprise side. Why compliance teams care about the execution history? Why skills living on an individual computer is a compliance problem? And the hackathon story, where a team that had never touched N8N built a production driver's license workflow in two days. Let's get into it. Ryan, excited for having you on the show, brother. So what are we gonna be learning today?
SPEAKER_00We're gonna be learning about how to use Cloud Cowork with NAN. We're gonna go through a real practical workflow, something super basic that anyone can start today. And we're gonna go over 10 to 11 different benefits of utilizing this. So I'm really, really excited about it.
SPEAKER_01Me too. Uh, this is something that is a very hot topic using cowork and in and together so that you can be more productive. It's something that I'm interested in, and I'm sure a lot of people that are watching this are gonna be interested as well. So feel free to share your screen when you're ready and let's get into it, shall we?
SPEAKER_00Okay. So here I have our Cloud Desktop app. You need to have this installed to be able to use Cloud Cowork correctly. And then I'm here on this center tab. Now there's a lot to the Cloud Cowork app. Obviously, we cannot talk about it all today, but we're gonna take you step by step. The first thing we're gonna do is set up any end directly in over here. So the way to do that is you go over here to this customize icon. Now, fully transparent, cloud changes their icons and locations all the time. So if you don't see this in the future, I promise you it's gonna be pretty easy. So jump into customize. Then what we're gonna do is look for our connectors. And in over here, we're gonna click this plus icon and we're gonna browse different connectors. And connectors are just integrations into other third-party applications so that way you can start sending data that way or grabbing data for any sort of skills. So NAN has a built-in uh connector, which makes it really easy to do. And all we're gonna do is go into the connectors over here and search NAN. Now you can see I don't have this activated right now, but I'll show you how to set this up in literally only 60 seconds. So click on this plus icon over here, then it's gonna say Cloud wants access to your NAN instance. Obviously, choose allow. You see success, you'll be redirected back into the client. Open up Claude once again, connected to NAN. Literally, that took what 30 seconds, if not that. And what's what's really great is you can actually determine if you want full access to NAN or just go through different settings. So you can see, for example, getting execution data, it needs approval. Uh, you can go over here and say always allow, or you can just keep this as new approval, or you can say, hey, I don't want any of this execution data to show up within Cloud Cowork, and you can turn this off. Now, obviously, I'm not going to go through every single one of these settings, but based off of your own security preferences, you can either have these as new needs approval, uh, automatic approval, or completely block it. So, as you see, about a minute to set this up, super easy, but you're like, okay, that's great. How do we actually work with some sort of a workflow here in Cloud Cowork? Again, let's uh start with the basics. So I'm gonna go back over here and we're gonna go straight in this chat panel, and I'm gonna just show you a very quick demo. Uh, one of the things I do for my YouTube channel is I try to get the transcripts from a specific video, and then I'll turn those into timestamps. Now, I'm not gonna show that full workflow today, I'm just gonna show you the very basics of how do we call an external API with the help of NEN. So in NEN, I have this basic workflow, and I would share it, but like it literally takes you two seconds to make, or you can ask Claude Cowork itself to make it. We have a webhook like over here, then we have our HTTP request, and then respond to webhook. Literally, just three nodes to get started with this. Obviously, you can go as complicated as you want, but let's start with a very basic demo. Our webhook is our chat API request, respond back over. So then I'm gonna go back over here and how am I gonna actually call this workflow? So this is called co-ork YouTube transcript, and all I'm gonna say and over here is can you run the the transcripts? Can you run the co-work transcript workflow? And I'm just gonna paste in a YouTube URL. I have a collectibles channel, so I'm gonna actually paste in a video over here that I didn't do timestamps on, and here is this specific video. And if you worked with Clowork for a while, you know that YouTube is blocked directly in over here. So you're gonna have to use some sort of API to analyze a video or get data from the video. Obviously, I want the transcripts, so I'm just gonna run this directly like that.
SPEAKER_01And for this, grabbing the actual transcripts because it does get blocked, are you using like Appify or some other service to do that?
SPEAKER_00So, yeah, so I'm using rapid API on this side of things. And what you'll notice over here as well, because of our permission settings, it says Claude wants to use the execute workflow from NAN. So it's probably blurred, but it has our workflow ID, it has the type webhook, which I just showed you, and then it also has the body, and all it is requesting is this specific video ID. So Claude is smart enough to take this YouTube URL and then just grab the specific ID that we particularly want. So I'm gonna click allow for this task, and it says Cloud wants to use get execution from NAN. Again, you could always allow these. I'm just doing this for this demo purpose, just to show you guys the first time that you're gonna get these directly in here. I'm gonna click always allow once again.
SPEAKER_01Yeah, and generally speaking, when you first run this and kick this off, right? It's gonna ask you, do you want to allow this? And especially if it's something that you're comfortable with, you do want to read the what are you giving permissions to? But for the most part, if I'm using in it in and I wanted to be able to call it or execute it, just click always allow.
SPEAKER_00Correct. Yeah, and that goes back into that customized section where I showed, you know, they had the hand or the green check mark or block. So you can just change those settings once over there, or you can just change it directly here in this chat. But obviously, you guys are doing this for the first time, so I didn't want to block that or always allow it right away. Anyways, and says the workflow ran successfully. Here's a quick summary was fetched. So this is uh uh again a collectibles video talking about a 1977 Luke Skywalker card that sold for $687,000, which is crazy. The transcript over here is clean and ready. What else would you like to do with it? Blog posts, school posts, YouTube titles, social content, or something else. Let's say, can you build out timestamps? Give me five for this video. And you can kind of stack this up and you can have you know specific skills to build you transcripts. You could have a skill that essentially says run this N-A-N workflow, and then once you have the transcript back over here, turn that into the specific timestamps. And I have that on my other computer. Uh, but obviously for this demo, we'll just do it directly in here. Let's have this conversation.
SPEAKER_01Great. And as you're doing that, I think one thing is important too is sometimes it hallucinates with timestamps. Do you do any like cross-verifications or anything with it to like know that it's not just making things up?
SPEAKER_00I sometimes will check the YouTube video on that. Um, to be honest, I use timestamps a lot more for kind of the keywords on YouTube and kind of ranking. Um, but I'll just quickly double check. Okay, here's the timestamp, what's on the YouTube video? But you can see over here it talks about the sale at Heritage Auctions, comparing the two PSA 10s that sold, other 1977 Luke Skywalker cards, Scanlon Australian cards, and then premium pricing and value comparisons. So I think this is good out of the gate. And this is again something that's kind of blocked in cowork. You can't work with YouTube. And now we used NAN as that bridge where we can call an external API and then send the data back.
SPEAKER_01Got it. And this one currently you're using Rapid API, which is more or less a marketplace for APIs.
SPEAKER_00Correct. And you can see also, just to show you the execution log. So if we go over here to executions, a total of two seconds, it succeeded. And you can see all the green check marks. So if it fails, you can always obviously go directly in N-A-N and change things up. It shouldn't fail being super basic like this. Um, but there's a lot more complicated workflows out there.
SPEAKER_01Of course. Of course. So that makes a lot of sense. And then also in terms of that too, uh I imagine if you're trying to connect to rapid API, you might say, hey, I want to connect to rapid API. Uh, this is maybe some documentation around it or something like that to help you build out that HTTP node that's making that request. It can maybe give you some insights on actually how to connect that up.
SPEAKER_00Yeah, you can actually build an NEN workflow from scratch. So you can write over here and say, hey, I want to connect this API. This is what I want in this specific workflow, and it will build this out for you. So I don't know if anyone remembers the community challenge about two months ago. Uh they had it where you had to classify different emails and then use evaluations. I think it'd be kind of a pretty cool use case if we go over here and just start a very basic build. Obviously, we're not gonna go in full depth and detail of building out this workflow, uh, but maybe we can start with some sort of email classification.
SPEAKER_01Yeah, that makes sense. Yeah, we we do monthly challenges for anybody that doesn't know around like different use cases with NADN. And that was the one that he was talking about from before. So uh if you wanna if you want to try out some uh community challenges, that might be a good place to get started.
SPEAKER_00Yeah, so let's try it. So I'm gonna say, can you create a brand new NAN workflow and call it, I don't know, we'll say NAN community challenge.
SPEAKER_01Since you have NADN already connected up to it, uh now, because it has been connected, we can actually have Claude go ahead and create that workflow for us. So you don't actually have to go into the actual uh workflow space in order to get this built out. You can simply ask it to do it, and it's gonna go ahead and create this for us. And what you're tying right now, I'll just repeat. Can you create a new NATIN workflow? Call it Inadin Community Challenge demo product for podcasts. Essentially, I want you to have a classifier that takes a look at the incoming emails, which we should simulate with a webhook and classify it into five categories IT support, billing, feature requests, and I'm sure there are two more that are coming up here.
SPEAKER_00We'll throw one more over here. Let's see. Let's do um I'll just change it to four and keep it basic over here. And then I'm gonna say after we classify these, and then what I'm also gonna say, and I think this is really powerful within cowork, if you are unsure, ask me any questions. So that's just one way that you can stop hallucinations. And I'm also gonna say, write the initial prompts. I will tweak them later on.
SPEAKER_01All right, and let's give it a shot. So what it looks like you're using uh sonnet and this as well.
SPEAKER_00Do you when you build the workflows, do you typically use Sonnet or do you do Opus or I I use I use I use Opus on those workflows, I just didn't change it on here, which I apologize.
SPEAKER_01Yeah, so it's all good. I just want to make sure just for clarity-wise, I yeah, I try to use I try to use Opus for creating the workflows as well. Um, but any of the low-level, you know, write a prompt or something, I try to switch out the models to save on them the expensive token costs.
SPEAKER_00Oh, 100%. And especially like if you have a subscription to Claude, you know, whether it's a $20 plan or a hundred dollar plan, uh, there's definitely ways to optimize it. And we're actually gonna talk about one of the ways that NAN can really help you out on there. Um, but it'll probably take a few minutes for this to run. You can see right over here, let me pull the S SDK reference and search for all the nodes I need at the same time. And then it says Cloud wants to use getting SDK reference from NAN. So once again, I'm gonna do always allow. We have another one, Cloud Wants to use searching nodes from NAN, always allow.
SPEAKER_01Yeah, I do appreciate it uh describing what is the issues and what are you approving as you go through it. And I think one of the benefits of using NADN with this type of systems is that we generally want to get a result. We want to get some sort of output from when anytime we're making an automation workflow, we want a result, but there's kind of a trust but verify going on right now. So you want to you want to trust the system, but the power of using inAdin with these types of systems is it allows you to really verify. You can go into the back end of the system and know for certain by looking at the execution history and all of that data, say, oh, this is clearly doing what I want to do as intended. Uh, versus sometimes if you just do it straight with cowork, you may not always know. And it might be doing things where you're trying to figure out why is this happening. So I do like that use case where you have this do the heavy lifting, but you can kind of you can be the ultimate verifier.
SPEAKER_00Yeah, and like especially in other industries too. Um, I'm not sure about the medical industry, but I work in compliance. Like you need to log every sort of interaction that you have with AI. So um just having a specific skill in over here and asking it to do something might not be adequate enough uh for regulators.
SPEAKER_01That's a bit, yeah, especially in the health space, uh removing, you know, PII or HIPAA compliance or any of those types of things. Or it's it's very good to have a digital paper trail. We'll we'll say that.
SPEAKER_00Yes. And you guys have the guardrails node, which can help a lot on there too.
SPEAKER_01For sure, for sure. Yeah, that's important with these things. Um, so yeah, I see it being built out right now. And so talk to me just a little bit about these patterns that you're seeing there. Can you talk to me as this thing's getting built out right now? Maybe a bit of the pattern. So let's just say you have a goal with building out some sort of automation, whether it's for yourself or for a client, right? And you want to use co-work and NADN together. Like, what's your typical patterns for kind of getting started? How do you ideate? How do you get started? Talk to me a little bit about your process.
SPEAKER_00Yeah, so I think kind of my process on it, if I'm gonna build out a workflow. First, like in the past, before I think co-work and Claude got really good at building out workflows, I was very stubborn. I always built them out by hand. I was I'd figure out some sort of flow and I'd go into NEN. Okay, this node we should use here, this node we should use over here. But now I kind of look over here and I say, what's the general idea of this workflow? Give some context over here. And obviously, in a world scenario, I'd throw in a lot more context. Um, just being on the podcast, we're gonna keep it pretty short. But you throw in as much information as you want in the beginning and then just clean up the mess. I think one of the things that no matter what you're gonna have to do is rewrite prompts, you're gonna have to change some of the inputs and change some of the directions of the nodes, that's given. But I think it could save you hours just starting out. And I think it's I think it's also really helpful for people that just haven't spent a ton of time in NEN yet. If you want to get your feet wet and you maybe you don't want to look at a template and want to start from something yourself, which I would still recommend starting with a template, you can go and co-work, give it an idea, and then just see what it built and then start taking a look at all the nodes. Um, again, very important that you have an understanding of how NAN works. You just don't go over here and you start doing AI slot. Uh, it's very important to know this is the node, this is what this node does, this is how you put this in order. This is how nodes specifically execute because I know for the first time when I was in NAN, I didn't understand that. And I built some uh janky workflows, but uh yeah, pick that up.
SPEAKER_01Janky is the word for it for sure.
SPEAKER_00Yes. The the loop over items. I had no idea how it worked at first. I come from a coding background, so I just like, oh, we have to always do it for everything. I didn't realize um nodes went one at a time, so that was pretty fun. Yeah, and that's why you guys talk about it in the documentation. You might not need uh the loop over item node.
SPEAKER_01Yeah, and as uh as you go through this, it it's getting me thinking about like as these things are a multiplier, right? So depending on your net depth of knowledge, there's a lot of things that happens with these AIs that you just trust it. And the thing is, with any of these LLMs, they say it with a lot of confidence. And unless you truly know how to cook in your kitchen with this type of stuff, you're just gonna agree with it. But sometimes it says things, and you're and if you actually know the back end of the system, like in it in, you can say, hey, um, why are we doing it this way? Can't we do it this other way? You know, uh instead of a code node, could we new use a data set node or another node? And it goes, oh, you're right, good catch. And then usually good catch is like, oops, sorry, I've messed up. Uh, let me do it another way. So it is, it is, it is good to do it not only as a time-saving tool, um, but if you do have depth of knowledge and this can teach you a bit as it builds, uh, I think uh it's very helpful to to know the systems well.
SPEAKER_00And I think it can also help you with debugging and some aspects. Like imagine you built out a workflow two or three months ago, you don't remember all the nuances, and now you have some sort of bug. You can go back and forth and try to figure out like what is wrong, maybe take a look at the execution history, grab some of the inputs over here and use it for testing, especially if you have some sort of a webhook as the introduction to that workflow, or you could just add in a webhook and uh go back and forth.
SPEAKER_01That's great. Yeah, and I know so you're connecting with the uh the official uh N8N MCP, is that correct?
SPEAKER_00Yes, what whatever you guys have on the customized tab.
SPEAKER_01Cool. Yeah, and I just recently uh met with the uh one of the team members who actually created the N8N MCP. And I actually found this out just earlier today, is that you can actually use it to create data tables and and actually go through the process. Yeah, I just found that out too. And I was like, oh wow, so I can actually make internal data tables and populate it with data. I was like, that's incredibly useful for me because there's a a lot of people use Google spreadsheets as a way to, as a kind of a, I would call it a ghetto uh data table, uh database, you know. Uh but some limitations with credentials, or if you make it as a template, or if you're if you're trying to like share that template with someone else, now they need to hook up Google credentials. But if you're using data tables, you don't need to.
SPEAKER_00Yeah, and that uh especially that happens in the enterprise side of things. Like you're not gonna be able to get to log into Google quite easily. One of the workarounds I do is I just have the form uploader and then I'll just upload a spreadsheet and go through.
SPEAKER_01Oh, that works too. That works too. It's a good move. Yeah, yeah. These are all these little little tips and tricks. And that's the thing about these spaces is that I think all of us tend to build with what we know. And then you in there's so many things happening so quickly in the space across all of the AI platforms and everything else that like even someone like me and you are both like, oh, you can make data tables with this. I'm like, I didn't know that either. Like, and so this is how the point of this podcast is to share these insights and best practices so people can get up and and iterate with this.
SPEAKER_00No, and I I will say that's one of the things I like with my full-time job. So I work at a company called Bill, and every Friday they have different people that are building out AI workflows in NAN. They kind of share what they built for the week and kind of their key findings. So there's probably like, I don't know, 50 people on these type of calls, and they get to learn every single week someone else's viewpoint of building out an automation.
SPEAKER_01Amazing. And that's like that's the power of the community, man. Everyone's just learning and growing together and sharing insights and knowledge. Try not to get stuck in those uh private dev holes, you know, where you just you don't realize that someone else has got a solution. All right.
SPEAKER_00So I think this is done. So you can see over here the workflow created despite 500 errors, the API timed out for some reason, probably not a big deal. Uh, here's the structure that was built. So we have an email webhook, an email classifier. It says basic LM chain plus structured output parser. So interesting enough, it didn't use the text classifier node, um, which is interesting. Uh, maybe we'll ask it to change that because again, we talked about how you can go back and forth. We have a route by category, which uses a switch, which sounds correct. We have the the four different ones over here, policy Google Docs, which obviously we have no Google Docs, but you could have a hypothetical Google Doc and probably just send it over here and say attach it. Uh draft email responses with an AI agent. What I like also, it says before you can run it, you need to fill in three things open AI credentials, which is interesting. It used OpenAI in comparison to the cloud models. Weird, right? Uh Google Docs, OAuth credentials, and then Google Doc URLs. So paste each policy URL into the respective node to simulate the email testing, post it over here with a body like this, the classifier prompt. So now I'm gonna load up this in NAN and actually see what happened.
SPEAKER_01All right, let's load this up. Yeah, I saw someone too, as you're getting that ready. Uh someone else was building with our own internal um in it in prompt system uh that we have inside of the AI workflow builder. Oh, let's see what you got here.
SPEAKER_00Look at that. Out of the gate. I mean, sure, I could build this out relatively fast, but I mean, think about the time that it's saved. You could be doing some other task and you already know you're starting with a webhook. I would change this over here um right now, and I know you guys just did new uh UI design, but I would change this to the is this actually text classifier? No, it's not. That's a basic LM chain. Apologies, I'll say it one more time. Three, two, one. I'd change this out to a text classifier, which maybe we can ask it to do. So we route by our category, we have the docs, and then we have our draft response. So I'm actually kind of curious what the prompts that it gave us. So it didn't really give us a lot of context. I think this is not the best prompt, which is expected. And then Draft email response. You can see it's passing in all the JSON, which you know for a lot of people that takes quite a lot of time at first until you realize how it all works. Yeah, so let's actually go back. Let's imagine, hey, we don't want this over here, basic LLM chain. This is bad. We should have used a text classifier. So I'm just gonna ask that.
SPEAKER_01And as you type that in, that's the point of like if you know in it in well, and you're just like, okay, this is not the best use case, or they're not the best node for this use case. Let's switch this out to something else that you know is a is a bit more, I would say, um focuses on proper design parameters, right? How do we do that?
SPEAKER_00And I'm gonna say also there is no error handling, which obviously real world scenario, you'd want an error handling. Most tutorials aren't gonna show you error handling because it takes extra time. But we're gonna say we should throw in some sort of error handling.
SPEAKER_01Yeah, that's an important use case. Yeah, one of the good features with N8N is that you can have these universal error handlers. So if something happens, notify me, either Slack or email or text message or whatnot, so that you know, because sometimes with automations, when it airs out and you don't know, when errors happen in automations, they they usually happen at scale. You know, so it's not just one error. You might send in. I I built a node or a workflow uh for somebody a little while ago, and I sent it through and it aired out and ended up sending like 36 emails. Um, and I was like, I was like, oh, that's not just filled up the whole system. I was like, oh, that's that's automation messing up at scale.
SPEAKER_00That sounds terrible. I added in actually one other thing as well, which we'll see if it picks it up because it's a little bit more advanced use case. I'm saying, can we also add in a node to send in an email and wait for a response 24 hours with the human in the loop within Gmail? Like this is a specialized node within Gmail. Uh and we'll see if it picks it up or not. And again, I'm using Sonnet. I should have used Opus, so it's not the smartest, but that's okay.
SPEAKER_01Oh, we're already saving tokens.
SPEAKER_00Yes. Well, we'll talk about actually. Do you want to talk about saving tokens now?
SPEAKER_01Yeah, let's talk about it.
SPEAKER_00Yeah, so as this is getting fixed, you know, one of the benefits I also see of using NAN workflows is token savings. People, I mean build out skills, they have a lot of different connectors, four or five. And obviously, in co-work, you can chain together skills. So, like when one skill finishes, you can start a second skill or the third skill. But this is going to eat up your tokens a lot. And if you already have an NAN subscription, whether at work or a personal $20 plan or $50 plan, you can just build out an NAN workflow and kind of do what I had over here. Hey, start this NAN workflow. So instead of having all these skills run, all your tokens and hitting those cloud limits, why don't you use the executions that NAN gives you, whether it's like 2500 or 10,000 and uh run it on that platform?
SPEAKER_01Yeah, yeah, yeah, yeah. Leverage them if you're smart with how to use your your tokens and leveraging systems that already exist, especially like if there's templates that are already out there that exist, and I think we have uh 7,000, 9,000 templates in the template gallery. Yeah, you can say, hey, let's start with a with a with a good template as a base uh that someone's already solved this problem, and then it merely can iterate on that versus trying to create from the ground up.
SPEAKER_00And you can just iterate in here. So you can see, like I'm asking it to fix this workflow. So maybe you go on to NEN's website, you find a template that you want to solve a situation. So instead of building out a skill, you have a skill that just says call this any end workflow, and then you can process those results back over here. And I find that to be pretty good because you have one skill, calls any end workflow, the data comes back over here with respond to webhook, and then maybe you want to take a look at something else. You have another skill that just analyzes whatever you have in here.
SPEAKER_01For sure, for sure. Nice. And have you seen any good skills that that work well with NITN and co-work together?
SPEAKER_00Yeah, I on my other computer, unfortunately, I have built some pretty cool skills, at least for my YouTube channel, because I always get super lazy with writing descriptions, timestamps, the keywords, and everything like that. So whenever I upload a new YouTube video, I just say I uploaded a new YouTube video, paste that in, and then it'll run an NATN workflow, builds out everything that needs, sends it back over here, and has it all formatted ready to go. And I could take it to another level and have it just log into my account and uh populate everything if I wanted to. I'm kind of just lazy over there. Sounds bad to say on a podcast, but I shouldn't take that extra step.
SPEAKER_01Now, automators are inherently aggressive, aggressively lazy people. And what I mean by that is that you're like, you're like, look, I understand that I could do this and it would take me about 30 seconds each time, but I would rather spend 30 minutes so that I never have this problem ever again. And so there's like that aggressive to happen. Yeah, yeah. Like, how do I solve this problem so I never probably have this problem again for sure.
SPEAKER_00Now, now what I haven't looked at too much, and I think it would be actually quite interesting, is cloud can control your computer. So different use cases of you know, controls your computer first, grabs whatever you need, and then starting any and workflows. I think that would be a pretty killer response. So if anyone has any pretty cool automations, like leave a comment on there. Um, but if you didn't know, cowork can control your computer, it can also control your browser. But as I mentioned with the NAN workflows, it is significantly better to just use some sort of scraper. Now, if you're using like a popular social media site, whether it's like a LinkedIn or Instagram, thousands of scrapers, Apple Fi or other websites, as we mentioned a little bit earlier. If it's something custom, maybe you build out a Python scraper.
SPEAKER_01Yeah, and that's the thing, it's like it can take over your uh system, it can use the browser, but it's really slow.
SPEAKER_00Like the it's terribly slow, it eats through tokens, and uh yeah, better off to build out it some sort of any n workflow that can hook up to Appy for it.
SPEAKER_01Yeah, exactly. And then you might want to do that as like a proof of concept or something that, oh, can you go in and do something on the the Chrome browser or something? But but in in yeah, because we always go with, okay, it might be out of the way, it might be like a big bloated system that takes a long time, but it's too long, especially like let's just say speed delete, right? If you're gonna have Claude all of a sudden uh go to a website, look up the information, grab the information, extract the information from a website, it's gonna be a lot slower than if you were to uh use some sort of scraping services that you could plug into that's a dedicated, code-focused, out the gate, solves a very niche problem, it's gonna be a lot faster. So there's kind of like a trade-off between kind of, you know, uh can do anything but slow versus I've got a specific task, it can go fast.
SPEAKER_00Or imagine if you have a thousand pages that you want to scrape all like different directories, how long would that take with uh Claude right now versus that you either build out something custom in Python or you find something that's already online and you kind of hook everything together?
SPEAKER_01Yeah, yeah, exactly. Yeah. So so leverage the power of in it in and scrapers, if you really want to build something that's kind of that's speed and reliable. Let's talk about testing. Yeah, trust, verify. I feel like that's that the the name of the game when it comes to this, these AI systems is like you want to trust it, but you also want to verify it. And I think that's what the case is. Like you feel really powerful when these AIs can do so much for you uh until you get burnt by it. And then you kind of learn to be a bit more wise with the verifying things work repeatedly. Uh otherwise uh they will pop off and you least expect it. I was I was building something that would like it would look at what my things were to do for the day, and then it would start to break my thing into like chunks of time, five minute chunks, and put in my calendar. And I wasn't paying attention, and then all of a sudden my entire calendar got filled up with like five-minute slots of things to do. And I was just like, I had to go through and just delete them all. And I was like, oh man. So you you you know, at the right place at the right time.
SPEAKER_00Yep. And obviously, like with any end being structured, you know, you have the same exact workflow that should happen time after time. Obviously, you can split your workflow and go to multiple paths, but you have some sort of input, you have some sort of output. And if there's anything that you want to change, it's pretty visual. You know exactly where you want to change something out. You can obviously go in over here and prompt it as I'm showing you guys right now. Um, but skills, not always the case. Obviously, you can change up skills, you can add to skills, you can remove skills. There's a lot of things that are really cool within cowork, but if you want something that is structured, guaranteed to work every time, throw that any end workflow and just call it from cowork. And then kind of on the testing side too. I know obviously we're building this out right now uh with this Gmail classifier gonna have a response back. You know, we can build out test data in cowork as well. We can say, hey, can we do five test runs in our any end workflow? And it'll essentially create a Gmail, it'll send it over as the webhook and it'll go through that full workflow. Now, I think this workflow will fail because we don't have any Google Docs attached to it. So I would hope that there's errors and it would tell us this directly in here. But I would love to test it once this is ready.
SPEAKER_01Sure. And while this thing is being loaded up here, I got a question in terms of uh multitasking inside of here, do you ever spin up uh multiple agents, uh different threads inside of cowork while you're working inside of NADN, dude? And like if you do, like how do you break up those tasks so they don't step on each other's toes?
SPEAKER_00I have, yeah. So um, for example, I on my other YouTube channel, I do a monthly sales series of like top non-sports cards, and probably most people watching have no idea or really care. But imagine I scrape eBay every single month and I talk about the top sales for a specific category. Well, I used to make these PowerPoints by scratch. I would have to grab the images, download the images, write some descriptions and everything like that. So that process now I just fully automated it with cowork and any n. I just say here, I want to grab the last month's data. I already have a scraper already built out, and then it'll go out there, it'll scrape everything for specific keywords, it'll go through, filter out the top 25. I have a human and loop aspect where I just do a quick review of the spreadsheet that's generated, give it a check mark, good to go. Then it'll actually build out a full slide deck for me. I mean, this process used to take me three to five hours, and now it's done within probably 20 or 30 minutes of my time, which is really cool. But at the same time I'm doing that, I can build out another NEN workflow or I could have a conversation in here because cowork kind of acts like a chat GPT. You can just ask random questions to an LLM and gives you the results responses for it. So I think of it kind of like as you guys had for Chat Hub for a while back, where you could essentially write to an LM and work with any and workflows. I just think this is the next level of chat hub.
SPEAKER_01Yeah, I can see that because the chat hub makes it a simple interface that everybody understands, chat. And then it goes into the back of automations, which not everybody understands. So being able to have a simple front end that makes a complex back end is is awesome.
SPEAKER_00And and to add on to that, right? Let's imagine you're in a corporate environment. You don't want to have everyone have access to your NAN workflows. So you could just essentially have your NAN workflows and have multiple people call into it based off of your settings that you set up and uh specifically customize. The issue with skills is skills live individually, I believe, on every single person's computer. Obviously, it's not audible and everything like that. But I think from like more of a security side of things and just getting accurate results every time, better just to call an NAN workflow and then go back into cloud core. In addition, one thing I I think is worth noting, I think there's a lot of people that believe that anyone can use cloud code or can load up a terminal and understand things. They have not worked in a corporate environment. There's people at every single company that are brilliant people but struggle with technology, whether it's like on a Zoom call or using spreadsheets, but they know so much about their domain and they expect people just to jump into cloud code and get started right away. I don't believe that. But what I think using NAN and cowork, like cowork is a chat interface, someone can understand that. Like, okay, I'm just talking in kind of like a chat GPT. NAN is the same thing for people that want to know how to code. Oh, okay, I have to use this node and it performs this action with an AI agent, and you structure it. So working in parallel, I think these are both ways for really non-technical people to get their feet wet and maybe one day they um go into cloud code, but they don't necessarily have to.
SPEAKER_01Yeah, it limits the barrier for getting up and getting started. And that's a hard thing. When a lot of people want to start to automate things, there's this like frustration in the beginning that like you want to get started, but then the the challenge is you hit these roadblocks and you're like, oh God, I don't understand it. But if you have a front-end interface like this and you can you can ask, well, why did this happen? What was the cause? What's this, you know, you can you can learn about these things, they can help solve those problems that you can learn from the systems without getting that typical thing where you just you just want to build, you just want you want a result and you want a quick win. And they have these front-end interfaces, you can you can get those results so much faster.
SPEAKER_00Yeah, you can build your first AI agent in NAN within 20 minutes. Now, are you gonna understand all the nuances of NAN workflows? Are you gonna understand proper prompting techniques? You know, no, that's not the case. But you know, you can get someone super excited that they learned about AI automation, whether it's like someone pretty old that doesn't understand everything or someone that's a little bit younger. And I I really like it for that aspect. I just wanted to call out if you take a look at my screen right now, it says Cloud wants to use updating workflow from NAN. This is something that you might want to choose, only allow for this task because if you always allow this, it might make changes to your NAN workflows that are already working perfectly. So a good call out of something that you just want for this task and just to manually review it. Now, obviously, I don't really care because this is a demo. So I'm just gonna click allow for this task, but really see what they mentioned because you can see 14 nodes over here. They're talking about some specific changes. We're gonna fly through that and say, hopefully it's correct.
SPEAKER_01Hopefully that's correct. Yeah, that's the that's the trusting part that and I had that before because I had to build out a bunch of workflows and I was telling it to fix some things and change some things, and I allowed always allow, but then it would it would change my working workflows into broken workflows just because it was trying to fix another problem.
SPEAKER_00What's also interesting, I think it's actually giving us a description for this workflow also, which is obviously best use case if you're setting up some sort of MCP connection. You should have a clear label for that workflow and a clear description. I think it's actually building out a description there too, uh based off of these notes, but I'm not 100% sure. Um, regardless, what I do really like, take a look at this. What's changed? I remove the basic LM change, the structure output parser and switch node. Added a text classifier node, added error handling on five nodes over here, each error wired to a shared send error alert Gmail node, added Gmail, send and await with a 24 hour timeout, approve and decline buttons, added was approved branch, send a customer true, notify, draft decline, added spam, notify spam received gmail so the team knows when spam is filtered. And then take a look at this because we we talked about hey, give us other suggestions. It said a confidence threshold, a one Google Doc credential. You have four separate credential placeholders for Google Docs. Yeah, we'll we'll ignore that for now. Uh, we'll actually talk about quick credentials in a second, which is gonna be really awesome. Uh, you can see structured draft output and then cleanup. You still have two duplicate workflows uh left from the creation retries worth deleting those from your NAN canvas. So let's actually load up this workflow and see what happened.
SPEAKER_01Great. Some good, some good recommendations there. Yeah, we definitely want to after this, we'll talk about the credentials connections because that's one thing that a lot of people get stuck on, especially if you're self-hosting a lot of times, because you have to go into say Google Cloud platform, you got to make a lot of connections.
SPEAKER_00So take a look at this. Now, this is something that you know going back three to six months ago when people were saying, well, LMs can build out uh workflows in any end. I would get stuff like this. I'd be like, not quite. Um, you might get this the first time you're like, what the heck is happening? And honestly, taking a look at this, I kind of get a little bit of that mess. Now, Opus probably does a way better job. Again, I'm gonna throw that out over there. But this is an example you have to know the basics of any end. So you're like, okay, this has our model, which I'm actually curious about model. It's using GPT-4.0 mini. Yikes. All right, no mo no worries. So we have this over here. Let's clean this up. And I know there's uh the button to clean things up also. Where would we have this? Right over here. Tidy up. If you guys don't know, click tidy up. Let's see what happens. A little bit cleaner. All right, so I deleted that over here. Obviously, you can choose your own error handling as you specifically want. Um, I know I was a little disappointed that there wasn't error handling after the webhook because after you have some sort of webhook, you want to authenticate the webhook. And maybe if it's in the incorrect format, you would want to have some sort of error handling. So I was really hoping that that was the case. Obviously, we can go back to cowork and prompt it to save you guys times. I'm not going to do that. Uh, we have our new text classifier over here, which I would assume the prompts aren't the best. But what's really nice is it grabs the from, the subject, the body, has the category with the descriptions. Again, really like that. And if you're not sure, just click this over here and you can see a little bit more. World scenario, you'd write way more thorough, but we're not worried about that today. We have our different documents over here. We have this draft email response. Uh, we have a review email response. So this should be the wait and respond ac and you can take a look, send and wait response. It says two placeholder value, which is funny. Obviously, we could just change this super fast. It says review draft. A customer support email is waiting for your review. And we have this over here. Now you can use this in way more services than just Gmail. I think probably the most popular one is Slack. I could be wrong, or Telegram. And then you can see response type approval, approve or disapprove. So, and we talked about 24 hours, it built that out. So, again, think of the time saver. Like, oh, I have to build this out, I have to build this out. Like we just had this running in the background as we were chatting. And then we have this was approved. Notify draft decline and then send to customer again with all the JSON and ISM already being in over here, which sometimes can be a pain for people, although it's super easy to drag and drop. Um, done. So obviously things I would tweak for a production build, but I think for a demo purpose, hopefully you guys get the point of that.
SPEAKER_01Yeah, yeah, yeah. It got most of the way there, which is pretty slick. And again, we're not using the most frontier model. It's okay. So we know things could get improved with that as well. Uh, this is this is great. So let's talk about these quick connections and how to connect credentials quickly.
SPEAKER_00Absolutely. So in the past, and we're gonna use Google as an example, you'd have to go and go through a bunch of different documentation. You have to go to Google Cloud, you'd have to figure out everything. You're like, man, this is such a pain. In fact, funny, going back to my YouTube channel, some of the highest viewed N-E-N videos are just credential setups, whether it's like Gmail or Google Sheets or Slack. But you guys just built out something that I think is really, really cool because it's simplified. If we go over here, choose credential. Let's imagine we want to create a new credential. You can see that you have a sign in with Google. So you can just go over here, sign in with Google, choose your account. I'll just choose this one. The others are blurred, and that's for my Ryan Nolan data account. I'm gonna click continue. Well, I should say I want to allow. Make sure you don't skip that step, otherwise, you're gonna have a little bit of issues. Click continue and take a look. Account connected.
SPEAKER_01Yep.
SPEAKER_00Five seconds. I remember my first time setting this up. I was like, man, there's so many different steps. This is super technical, and I'm a technical person. Um, I was like, ah, this is a lot. And honestly, anytime I'd have to set these up, I'd just have to remember the steps. Like I used to have a Google Doc. Okay, step one, step two, step three, or rewatch my old YouTube video. Now there's like no reason for anyone to watch that YouTube video, how to set up Gmail credentials or any Google because it takes two seconds.
SPEAKER_01Yeah, yeah, it's it's amazing. Credentials are the biggest pain. So once you got that sorted, then you should be able to fly right through, especially if you just go through and figure out any of the credentials you need to have set up, whether it's Google or you know, name name the platform, and then you're you're good to go. Because then from then on, you just simply open up the nodes, select the credentials you want, carry on with your day.
SPEAKER_00Yep. And you can see the credentials are already set up across the board. Like I didn't even have to tell cowork, hey, set up these credentials. By default, NAN, when you throw that node in, we'll set up that uh default credential, whatever you have in here over here.
SPEAKER_01Uh so you know, we talked a little bit about this. Um, are there any other ways that people can save on tokens?
SPEAKER_00Yeah, I mean, I think the the biggest one for most people that are in the NAN ecosystem and then also use Cloud Cowork is to definitely have these NAN workflows, especially as you know, if you're working during business hours, your tokens uh get burned through really fast. And I assume a lot of these automations are gonna be run during those business hours. So set up with some sort of skill, have that run a NAN workflow for whatever you want and go back and forth. Obviously, there's a lot of different ways that you can save tokens within Cloud Cowork. Um, but I think this is one that's really slept on in this industry for some reason.
SPEAKER_01Got it. I it's great. Um, and then we talked about, I think we're gonna talk about a little bit about how execution histories are stored and logging.
SPEAKER_00So, yeah, I think it's really important to take a look at these executions because maybe you have some sort of error and you need to uh deal with it, or you just need to see how often this is running. So you can just go over here to the executions. You can see this is run quite a bit. Um, one thing I think is really helpful if you have an error. I always just click over here to copy to editor, and boom, we have those results. I think this helps with errors, or if you're getting some sort of hallucination, you want to see, hey, what data came in our webhook? Why do we have a hallucination a little bit later with a specific AI agent? Well, you can uh really see those specific details, and you can see our data is pinned over here in this webhook, and then you can see the green check mark. Uh, we have the results over here that essentially pulled from that specific API. The other side of it, again, we talked a little bit about you know compliance or HIPAA. You need to log your data. Um, at least like if you're working with some sort of regulators, they need to see like, what are you sending to an AI agent? What is the AI agent's response? Are you guys utilizing any sort of human in the loop? If you're doing skills directly within Cloud Cowork, that's not always going to happen. Whereas you build out an NEN workflow, you can literally point it in the workflow. You're like, yeah, this sends data into my database and it is stored directly here. This is the input to that specific AI agent. This is the output, and it's all visual. You can explain every single node, every single action. Obviously, in cowork, you can explain, yeah, this is a skill, this is a prompt that is used every single time, but it's not structured. Whereas this over here, and again, we were just using a uh three-node example, the basic as basic as it gets, um, you see exactly what's happening.
SPEAKER_01Yeah, that's a bit it's the visualness of the platform that you can see what's going on and understand why the errors are happening. It's amazing. So you had a hackathon at your office, and so what were the results of the hackathon?
SPEAKER_00Yeah, so previously before I worked at Bill, I worked at a company called Stacks, and uh there's a lot of AI frenzy last year, and one of the one of That was pretty cool is they actually hosted a hackathon with some of our customers that processed with us. We had different companies that came in, and the goal of the hackathon was to solve some sort of problem. One company had a problem with underwriting. Um, if you don't know, if you're doing any sort of payments, typically a company will have underwriting to either approve or reject applications. So they had issues with their customers uh not going through the full underwriting process. And one of the things they they figured out is hey, our IDs that we're getting from our customers, they just aren't in the correct format. And we would pen an application and send it back to them. So in this hackathon, this group of people never used NAN before. They saw my YouTube channel and kind of coached them through NAN for two days. At the end of the second day, they were able to build out a pretty awesome workflow that they were able to apply to their business. So essentially what they did is they would take an input in for a webhook. They would have the input of a uh driver's license ID, and then it would go to a visual model. Okay, is our driver's license not blurry? Okay, good. Is the driver's license in color? Good, because you would get penned if it is in black and white. Um, and then it would use an OCR model to actually extract elements from over here. Okay, does the pattern match to the specific state? Correct. Okay. Is the driver's license not expired? Correct. Okay, great. Does the name match the application? Great. And there's a bunch of different data points that they would take a look at. I'm not gonna bore you guys with that. Um, but that was literally their first two days ever getting exposed to NAN and they're able to build out something that they're gonna put back into their business. And I really think that shows the power of NAN.
SPEAKER_01Yeah. That's and that thing is the beautiful thing about this is the ability to connect the people that maybe aren't as technical to the problems that they're trying to solve. Because ultimately, at the end of the day, we're trying to solve problems. And so if you can say, hey, you don't need to be incredibly technical. If you're using co-work plus NAN together, you can figure out and you're bringing someone who their job is to solve a problem. Maybe they are verifying IDs. They can very quickly build a system, a solution, an automation that solves that problem because they're gonna know that problem intimately versus a hyper-technical person, they're gonna know the technical back end of systems, but they're not gonna be as connected to the problem. So I like that closing the gap between the person who has a problem and the solution that's created. And whenever you can do that, it there's so much more value because it's a it's a real world problem versus just making up uh solutions that don't actually have any problems.
SPEAKER_00Yeah, and you know, the sad thing is like people make fun of people if they can't get their Zoom camera correct or they have an issue with the spreadsheet. But sometimes you have so much domain knowledge, and if they could apply it to an automation, like they would save a ton of hours. I think between that gap of cowork and NAN that can help solve that issue.
SPEAKER_01So, what, you know, coming towards the end of the podcast here, what advice would you give to uh, let's just say a company that wants to use this type of technology? What would you tell them to get up and start it and and and really get value from this?
SPEAKER_00Yeah. So I guess my first question is, you know, how much experience do they have with automations? Do they already have any end workflows? Do they not have any end workflows? Are they just starting from scratch, like, hey, we want to build out our first AI agent today? Do they already have like, how far along is this company?
SPEAKER_01So yeah, so let's just say they have limited, they probably have let's say one or two people at part of the company that knows a lot about it. And a lot of these other people are just people that work in different departments. Some work in accounting, some work in sales, some work in different places, but you want them to all have the power of AI and automation. They just, they just they're eager, but they just don't have the technical chops.
SPEAKER_00Sure, absolutely. So, what I would do with that two-person team is I would start in one uh department. Let's just for technical sakes or for simplistic sakes, we're gonna say they're gonna go to the accounting department. First, I would kind of just kind of track what that accounting department is doing on a day-to-day basis. Because I think if you watch an employee or you know, a coworker, what they do, you might come up with ideas like, oh, we can automate this, we can save you you know five hours a week doing this. Um, so I'd first observe anything before taking any action. I know a lot of people are so gun ho, they're like, all right, we're gonna automate everything, but until you understand the context of why people do certain things, you're gonna mess up in the automation and someone's gonna say, well, AI sucks. Well, it's really the person that implemented it. So I would first observe what they're doing, and then after maybe a day or two, come up to them with some specific ideas like, Hey, I think I can automate this. Let's work on this together. And maybe that's where you kind of hold their hand and show them the process. Maybe you want to start with this connection with NAN and co-work and say, okay, can you describe what you're doing? Write this out, and you start seeing the NAN workflow getting built on the side. Obviously, you have to figure out your credentials, you're gonna have to figure out some additional changes as you saw with the workflow that we built over here today. Um, but it kind of showed them in real time, like, oh wow, this process took me five hours and we just automated it really fast. Again, with world scenarios, you have to do a ton of testing. You're not gonna just build a workflow in an hour and wipe your hands and say, Man, that's done. I just saved five hours a week. You have to throw an error handling. You should go through at least 50, 100, 200 runs of a workflow, obviously, depending on what it's used for, uh, to really confirm it. Um, but I would start with that and just kind of work department over department. Um, maybe your executive team can tell you or point you in the right direction what departments have a lot of manual processes and you start over there.
SPEAKER_01Makes sense. Yeah. So figure out what you're doing before you go anywhere. And then once you start to, once you start to identify those core problems, go okay, what is the one, two, three top priority problems to try to solve that kind of is that it's kind of the the intersection between complex and value driven, right? You don't want something super value driven that's super complex, but you also don't want to automate something that's not going to serve any purpose. So, how do we find something that's fairly easy to automate that that also ideally solves a core problem? And if you can find that and then work with some technical people on the other side. So if you do get stuck, you can kind of hit the panic button where somebody can come in and help you out. It makes sense that would get them up and running pretty easily without those technical barriers.
SPEAKER_00Yeah, and that kind of goes back to the hackathon, right? That one customer had issues with their applications getting pended. One of the biggest reasons was those specific IDs. Well, what was the reason? The IDs were in the incorrect format. So why don't we just build out a NAN workflow that confirms the format of the ID? If there's any issues, it spits it back and says we will not accept that specific ID. So now on their website, they just have a form, someone submits the ID, it sorts out that any end workflow, and then it can say your ID has been approved or your ID has been rejected. Think about that. In a day, you saved one of their biggest issues, which probably costs them tens of thousands of dollars.
SPEAKER_01Absolutely. And that's the thing, you just got to find those use cases and integrate them into every piece of the business. Same thing with AI, I would say, is that you know, everybody wants this all-knowing AI that knows everything about you and your business, and we have automations that solve every single problem, but that's not how it works. So you get one small problem fix at a time, you start to build out a bunch of different workflows, and then it stacks together, then it feels like magic when you start having flows through the entire business. But that's that's how you need to do it. Just kind of one piece at a time until it builds into a beautiful orchestration system.
SPEAKER_00Yep. And I would also say don't always chase the newest technology. Like new technologies can get adopted really fast and also dropped really fast. I think we saw it with what, ClaudeBot. Um, it got really hyped right away. And then, oh man, we have a ton of security concerns. We're not going to use this anymore. And no one's really talking about it anymore. I could be wrong. But uh, regardless, if you can figure out an AI automation and it works correctly, you don't always have to change things. If something works, perfect.
SPEAKER_01Exactly. Yeah, yeah. Just wanted to solve the problem. Beautiful. Uh Ryan, is there anything else you'd like to let us know before you tell people how to get a hold of you?
SPEAKER_00No, unless you want to hear about that Goggins story we kind of talked about.
SPEAKER_01Oh, yeah, yeah. Well, just real quick though, yeah, because uh you have a bit of a background with uh with uh running quite a bit. As as we've we've connected before, you've always been on a treadmill having conversations with me. Uh talk to me just a little bit about Goggins.
SPEAKER_00Yeah, so funny enough, my first marathon, I actually ran with David Goggins, which is so bizarre to say. I was running the Las Vegas marathon, and for some reason I had the dumb idea of, hey, maybe I can BQ my first time BQ being a Boston qualifying time. At the time, it was a three-hour marathon that you had to get. First half of the race, fantastic. I think I did like a 128. Second half, I started getting really bad cramps. I don't know if it was like being in the desert or I just didn't drink enough uh liquid IV or whatever the case may be. I was cramping really, really bad. And kind of towards like the second half, towards the end, I think it was like mile 19 or 20, see this guy running past me. I'm like, that kind of looks like David Goggins. And someone points at him who's gonna carry the boats, and he's like nodding, and yeah. And I'm like, oh my god, David Goggins just ran past me. I found out he was pacing his wife or girlfriend, and this was a week after he ran a race called Moab 240, which if you don't know that race, 240 miles across Moab in Utah. Now, a week after that, he's already running a marathon. Incredible. Anyways, I got to run with him for a few miles, and he he said, This isn't my race, I can't finish it, I'm gone, or whatever the case may be. And he left. And I'm like, no one is ever gonna believe my first marathon I ran with David Goggins. I finished the race and I'm walking and I hear someone yelling at me saying, Hey, I paced you those last few miles. Goggins literally waited at the end of the finish line. He's like, Good work, you know. I'm trying to link up with everyone else that ran with us. Like, he could have easily said, Man, I got spotted, I'm gonna dip. He literally waited and tried to talk to every single person that ran with him for a few miles. Um, ton of respect from him on that side of things, especially a week after running a 240 miler. When I ran my first 100 miler, I was like completely gone for a week and a half. I was, oh man, that was terrible. My feet were throbbing, I was so sore. And I even did a 75 miler two weeks ago, and I've already lost two toenails, or not two weeks ago, two months ago. I already lost two toenails and uh took a while to recover. I can't imagine 240 miles running a marathon next week.
SPEAKER_01And then also just to tie it back, uh, is you had uh someone part of your community actually made a a Goggins-inspired workflow.
SPEAKER_00Yes, but yeah, so I'm always on a treadmill on my calls. This is actually a rare occurrence. I'm not on a treadmill, funny enough. But uh, because of that, he made a joke. Hey, you're like David Goggins, and I obviously told him that type of story. He's like, I have inspiration. This guy in our community, Ken Rogers, I actually know him from the card space, and now he's in AI space also. Uh, he built out a full David Goggins workflow on there. I'm gonna ask him to actually upload it to the N-AN website so then people can download it over there. I think that's a good call to action over there on that side of things. Uh, but he built it being inspired. It's like a telegram workflow. So every morning it gives him inspiration, like, hey, make sure to get in your run or make sure to get in your workout. And it says it in David Goggins' tone. And that was one of his first workflows.
SPEAKER_01Awesome. Yeah, you can use it for inspiration as well. It's incredible. Uh, Ryan, this has been awesome. If people want to find your channel and find you, how do they do that?
SPEAKER_00Absolutely. You can check out my channel on YouTube. It's Ryan and Matt Data Science. Obviously, as the name states, start as a data science channel, uh, kind of just as a way to build a portfolio over there. And it's kind of drifted into more NAN and AI over the last few years. I really appreciate it if you checked it out. We actually have a full 17-hour NAN course. I think the longest one here on YouTube, and I think over 100 NAN videos. So if you're not sure what a specific node does, obviously you can ask inside cowork, or you can watch probably a 20 or 30 minute video learning the nuances of that particular node and kind of the use cases for it. Um, you guys can also join our free school group. We have a call every single Wednesday. You can join in, you can walk on your treadmill, talk about NAN, AI, freelancing, does not matter. Uh free group. A lot of people will charge you hundreds of dollars. It's free. Come join us.
SPEAKER_01Incredible. Uh Ryan, it's been an honor and pleasure, my friend. Much love, and I will see you on the other side.
SPEAKER_00Really appreciate it. Thank you again for having me on. Take care. Bye now.
SPEAKER_01Bye.
.jpg)