How to Build Effective Claude Code Agents in 2026

[00:00] What would you say by the end of this

[00:01] podcast that everyone will have learned

[00:03] from you?

[00:03] >> The main thing I want to talk about

[00:04] today is how we can be the director of

[00:07] our coding agents. Everyone is hearing

[00:08] nowadays how large language models can

[00:11] support up to 1 million tokens in their

[00:13] context. That's like the Harry Potter

[00:14] book five times over. Large language

[00:16] models have what's called the dumb zone.

[00:18] With Opus right now, it's usually around

[00:20] 250,000 tokens and I feel like it gets

[00:22] into the dumb zone.

[00:24] >> It definitely comes with a false sense

[00:25] of security with people now thinking

[00:27] that they have the million. With coding

[00:28] agents, you spend more time planning

[00:30] than you actually do building.

[00:31] >> Without the verification checks, maybe

[00:32] it's 65 or 70, but now you can get

[00:34] something that is 92 on the first pass.

[00:36] >> If you tell it never to to wipe a

[00:38] database, it's still going to do that.

[00:40] If you don't allow it to delete a

[00:42] folder, it can still write a script to

[00:44] do that.

[00:44] >> Recently, something did happen to us.

[00:46] The agent was trying to be proactive and

[00:48] it actually saw something on its task

[00:50] list, but it misinterpreted it and it

[00:51] ended up sending an email to our entire

[00:53] list with a discount code and it was not

[00:56] supposed to go out. If you have the

[00:57] mindset that anything that the agent can

[00:59] read or can touch, you have to assume

[01:02] that it will, even if you never ask it

[01:03] to, that assumption is what's going to

[01:05] save you from having your database

[01:06] deleted.

[01:10] >> All right, Cole, thank you so much for

[01:12] being here today. I'm so excited to dig

[01:13] in.

[01:15] >> I'm excited to be here. Yeah, thanks for

[01:16] bringing me on to your podcast, Nate.

[01:18] I'm looking forward to this.

[01:19] >> Absolutely. Yeah, it's been a long time

[01:20] since we've talked, so I'm excited to

[01:22] hear what you've been up to and to hear

[01:23] kind of like the sauce that you're going

[01:24] to drop on everyone today. So real

[01:26] quick, what would you say by the end of

[01:27] this podcast that everyone will have

[01:29] learned from you?

[01:31] >> Yeah. So the main thing I want to talk

[01:32] about today is how we can really be the

[01:34] director of our coding agents and

[01:37] specifically cloud code because that's

[01:38] what most people use right now. That's

[01:39] what I use. But really, it's creating

[01:41] that system where you have your your way

[01:44] of working with cloud code that evolves

[01:45] itself over time. And we're going to

[01:47] talk about more than just using it to

[01:49] code. Really, I use my cloud code as my

[01:52] second brain. I like to call it. I know

[01:54] Nate kind of calls it as AIOS. Everyone

[01:56] has their term for it, but really like

[01:57] using cloud code as the tool to make

[01:59] your business AI native. We're going to

[02:00] get into all of that and just some

[02:02] highle strategies that honestly you can

[02:04] start applying today.

[02:05] >> I love that. Yeah, I'm I'm super excited

[02:06] to dig in because, you know, I don't

[02:09] come from a formal software engineering

[02:11] background and I think that I would I

[02:13] would guess that the majority of my

[02:14] audience doesn't either, but obviously

[02:16] with the the products being called Cloud

[02:18] Code, I think a lot of people that I

[02:19] bring that up to who aren't super deep

[02:21] in the AI space, they obviously think

[02:22] that it's a tool that is for coders and

[02:24] you need to understand code in order to

[02:26] use it. So, um I love that framing. And

[02:28] real quick before we jump in, you know,

[02:31] me and you have we've known each other

[02:32] for quite a bit. I feel like, you know,

[02:33] right when I kind of quit my job and

[02:35] started on the space, you were one of

[02:36] the main channels that I followed and I

[02:38] still follow to stay up to date and to

[02:40] to learn about how to work with AI in

[02:42] the right way. And um we've kind of just

[02:45] been able to see each other grow and and

[02:47] you know, check in. So, I'm really

[02:48] excited to dive in, but I wanted to make

[02:50] sure you got a chance to real quick give

[02:51] everyone a quick intro if they haven't

[02:53] seen your channel before on what you do

[02:55] and um

[02:56] >> yeah, what you're up to. Yeah, sounds

[02:58] good. You know, before I give an intro

[02:59] though, I kind of want to share

[03:01] something a little bit about what you're

[03:02] talking about. Like when we first met,

[03:03] it's funny because I I actually remember

[03:05] I had um about 50,000 subscribers when

[03:07] Nate first reached out to me and he had

[03:10] like 10,000 and now it's a little bit

[03:12] different. I have like 200,000. You're

[03:14] you're almost 800,000 now, right? Like

[03:16] it's pretty crazy. Um it's been really

[03:17] cool to see you grow, how fast you've

[03:19] grown. But yeah, we were both like

[03:21] smaller channels at the time. Um so

[03:23] yeah, it's it's been a long time. Wild

[03:25] journey. Uh yeah. Anyway, as far as what

[03:27] I actually do, so like Nate said, I come

[03:29] from a software engineering background.

[03:30] So, I've been an engineer my entire

[03:32] life. Ever since I was eight years old,

[03:34] actually, I I started with this language

[03:36] called Scratch. It's developed by MIT.

[03:38] So, I was just like building video games

[03:40] as a kid, like Super Mario Bros. and

[03:42] Pokemon, like really cliche stuff. Um,

[03:45] but that that's what got me into the

[03:46] world of coding. And so I took that

[03:48] through high school, college, got my

[03:50] bachelor's in computer science and um

[03:52] then I had just like a software

[03:54] engineering job in a Fortune 500 company

[03:56] and it was great but I always wanted to

[03:59] be an entrepreneur. And so when

[04:01] generative AI started to really become a

[04:03] big thing at the end of 2022 with the

[04:05] release of chat GPT you know and it took

[04:08] the world by storm that's when I knew

[04:09] like okay this is where I want to go all

[04:11] in cuz there's like a really big

[04:12] opportunity for software engineers

[04:14] specifically to build agentic

[04:16] applications and so I started doing a

[04:17] lot of that like for my company and for

[04:20] friends with their startups pretty much

[04:21] dedicating all day and all night to it

[04:23] for a very long time like over a year

[04:26] and so it got to the point well I know a

[04:28] year might not feel like a long time but

[04:29] in the AI space a year is a long time.

[04:31] So it it got to the point where like

[04:32] okay I got some things to teach people.

[04:34] So that's why I started my YouTube

[04:35] channel.

[04:36] >> So originally it was like really really

[04:39] technical like I was there like writing

[04:40] line by line. I wasn't even using AI

[04:42] coding assistants back then just showing

[04:44] how to build AI agents with like you

[04:46] know lang chain and langraph at the

[04:48] time. And um now that's evolved to a lot

[04:51] of different things like I do a lot of

[04:52] like focusing on AI coding assistance

[04:54] which is why we're talking about that

[04:55] today. Um, and yeah, I quit my my

[04:58] full-time job like three months after

[05:00] starting my YouTube channel, which I

[05:01] think is about the same for you, Nate.

[05:03] Yeah. U because it's crazy like how fast

[05:05] when you when you do it right and and

[05:07] you're teaching people valuable things

[05:08] like how fast a channel can explode. And

[05:10] so now now what I'm up to is I have my

[05:12] AI community um similar to Nate where

[05:14] I've got course content, weekly

[05:16] workshops that I do. I've also been

[05:18] doing some more enterprise level

[05:19] training. So coming into a team and

[05:21] doing like a 4-hour session, helping

[05:23] them adopt a full system for using AI

[05:26] coding assistance so they can really

[05:27] have as like a standard for the team,

[05:29] you know, get away from Vive coding to

[05:31] really have a structured approach and

[05:32] helping them actually bring that into

[05:34] their existing processes and tech stack

[05:36] and things like that. So that's been

[05:38] pretty awesome. And so like really like

[05:39] that and everything I teach in the

[05:41] community, I'm bringing a lot of that

[05:43] here to what we're going to be chatting

[05:45] about today.

[05:45] >> 100%. Real quick, guys, quick break to

[05:47] tell you about today's sponsor, ClickUp.

[05:49] ClickUp is the software to replace all

[05:51] software, which I think is pretty funny,

[05:53] but very true. If you guys have been

[05:54] following me for a while, you know that

[05:55] I've been using ClickUp for a long, long

[05:58] time. Everything that I do with my team

[05:59] lives in ClickUp. All of our

[06:00] communication, all of our project

[06:01] management, all of our chats, and

[06:03] everything I was doing with my clients

[06:04] back when I was running the agency

[06:05] day-to-day, we were also inviting them

[06:07] to a ClickUp. So, it had replaced Slack

[06:09] for us, and it had also replaced our

[06:10] project management tools. So, if you're

[06:12] already using ClickUp, you have to try

[06:13] this new feature called Brain 2. But if

[06:15] you don't use ClickUp already, then

[06:16] Brain 2 is an amazing reason to try out

[06:18] ClickUp. It's kind of like a

[06:19] supercomputer that can do a ton of cool

[06:21] stuff. And I'll talk about in a sec.

[06:23] They have super agents in here. But you

[06:24] can switch between the different chat

[06:25] models that you probably already use and

[06:27] love. Right here, you can see that I've

[06:28] used Brain myself to look through

[06:30] everything that's going on in our

[06:31] projects and then create me a monthly

[06:33] presentation for the team. So, what that

[06:35] could look like is me asking Brain to

[06:36] create an investor presentation pitch

[06:38] deck for our texttospech startup called

[06:40] Glido. And I told it to just use mock

[06:42] data, but make sure that it's

[06:43] professional and engaging. And just like

[06:44] that, we have the deck, which I can open

[06:46] up full screen right here. We've got the

[06:47] voice AI platform that makes every brand

[06:49] sound human. And as I start to navigate

[06:51] through here, you can see that we also

[06:52] have animations in here. So, it's not

[06:54] just a static, you know, slide deck. We

[06:56] get to actually go through and we feel

[06:58] the animations. And think about the fact

[07:00] that this was just a one sentence

[07:01] prompt. If we really started to put more

[07:02] and more data into this thing, it would

[07:04] be really, really solid. And this right

[07:06] here is just one of the many use cases

[07:08] of Brain 2. So, it's not just a chatbot.

[07:10] Like I said, it can do things and you

[07:12] can build your own super agents in here.

[07:13] And what I think is really cool about

[07:14] the super agents is they're 24/7 agents.

[07:16] You can tag them in ClickUp. You know,

[07:18] you can at message them and they'll wake

[07:20] up and respond to you and they can

[07:21] search through everything. Which is why,

[07:22] in my opinion, it's a lot cooler that

[07:24] ClickUp is doing this compared to

[07:25] something like chucking an OpenClaw or

[07:27] Hermes agent into ClickUp because these

[07:30] agents already have full context and can

[07:32] search through everything. So, right

[07:33] now, because you're watching this video,

[07:35] you can claim this super awesome offer

[07:36] that is on screen right now by using the

[07:38] link in the description. Now, let's get

[07:40] back to the video. Yeah. Well, I am just

[07:42] I'm so glad that that we both took the

[07:44] leap because it's, you know, it's not an

[07:46] easy decision, but um your brain just

[07:49] gets it. And so, it's been great to see,

[07:51] you know, the consistency and what

[07:52] you've been up to. But I think that if

[07:55] you think back to, I don't know, 5 10

[07:58] years ago when people were going out to

[08:00] get their, you know, CS degrees and

[08:02] stuff, it's like that was such a safe

[08:03] bet at the time, you know, and I don't

[08:05] think a lot of people

[08:07] >> were predicting how much how quick that

[08:09] was going to flip as far as like, you

[08:11] know, that graphic of what is AI being

[08:12] applied to and right now it's just

[08:14] majority is coding and software

[08:15] engineering and obviously everything's

[08:16] going to catch up. But um it's just

[08:19] great that you were able to, you know,

[08:20] make that pivot and be ahead of the

[08:21] curve and now now here we are. So um

[08:24] being able to us have this conversation,

[08:27] one of us coming from like a

[08:28] non-technical background completely and

[08:29] one of us coming from a technical

[08:30] background is going to be really cool.

[08:32] So yeah, let's just jump right in.

[08:33] >> Yeah, sounds good. Cool. So for for what

[08:36] I have prepared for today, um you'll see

[08:39] like

[08:40] >> you'll see it shine through that I come

[08:42] from a technical background, but but

[08:44] really what it comes down to is like I'm

[08:46] going to bring these concepts into using

[08:48] cloud code for far more than just coding

[08:50] like I alluded to at the start. And so I

[08:53] think um you know for me like I I really

[08:56] enjoy leaning on my technical expertise

[08:59] because a lot of the ways that you'll

[09:00] use an AI coding assistant for your ops

[09:03] your AIOS your second brain whatever you

[09:05] want to call it um you are going to be

[09:08] borrowing from software engineering

[09:09] principles whether you realize it or

[09:10] not. So a lot of times just as you learn

[09:13] how to use these tools effectively and

[09:14] you're just learning best practices from

[09:16] Nate's YouTube or Anthropics blog or

[09:18] Boris Journey or whoever like they're

[09:20] bringing software engineering principles

[09:21] and a lot of like product management

[09:23] manager principles as well. And so yeah,

[09:26] like some of the examples that I have

[09:28] here um that will cover like they're a

[09:30] little technical. Um but that's really

[09:32] just like to illustrate how how I

[09:35] started using this tool and then of

[09:36] course I'll like generalize things a lot

[09:38] as well and um give some specific

[09:41] examples too.

[09:42] >> Um so if you if you want Nate, I can

[09:44] just like dive right into the first part

[09:45] that we have here. Okay, cool. Yeah. So,

[09:47] I got like just quick over I mean we'll

[09:49] go pretty quick through this because I I

[09:51] want to keep this pretty casual and I

[09:53] know you you do as well, Nate, but just

[09:54] like a few different pillars here of how

[09:56] we can go from simply using cloud code

[09:58] to what a lot of people call vibe

[10:00] coding, you know, prompting and praying

[10:02] where you're you're pulling that lever

[10:04] like a slot machine, getting to the

[10:06] point where we're really directing it

[10:07] and having that system for reliable and

[10:09] repeatable results. And um it really can

[10:12] be simpler than you would think, right?

[10:15] Like most of what people do that you

[10:17] really shouldn't do is you throw in a

[10:20] request and you don't do much of the

[10:23] planning up front or the validation

[10:25] after. Like those are the two things

[10:27] that I really want to talk about here.

[10:28] And that applies to uh writing any code

[10:31] or any kind of application. It applies

[10:32] to evolving your system like as you're

[10:34] creating skills and integrations for

[10:37] cloud code or even just using it to

[10:39] automate things in your business. Um,

[10:41] and so yeah, the approach is you always

[10:43] want to plan with context, build out

[10:46] that thing that you're looking to do,

[10:47] and then have an approach for verifying

[10:49] like as high level as I can possibly

[10:51] keep it. And then the other like kind of

[10:53] golden nugget here is every time you go

[10:56] through this loop with clawed code, any

[10:58] kind of agentic workflow or thing that

[10:59] you're building, there's always going to

[11:01] be an opportunity at the end to evolve

[11:04] your system. And we'll talk about what

[11:06] that means in a little bit here, but

[11:08] like really that comes down to there's

[11:10] going to be something in the way you

[11:11] work with cloud code that you can

[11:13] improve so that next time it's going to

[11:15] be better.

[11:16] >> And I'm being high level here on purpose

[11:19] cuz I'll get into some more examples.

[11:21] But a lot of people don't think about

[11:22] doing this, right? They kind of like get

[11:24] to the point where it's like, okay, my

[11:25] application works. Like this website

[11:27] looks good or it's now able to automate

[11:30] creating invoices, like whatever it is.

[11:31] And they're like, all right, we're done.

[11:32] like let's next time I want to create an

[11:34] invoice, I'm just going to go through

[11:35] the same process again. But like really

[11:37] there are going to be those problems

[11:38] that come up over time where you can

[11:40] engineer so that they happen less often,

[11:44] right? That that system evolution is

[11:45] kind of what I like to call it.

[11:46] >> So you're having you're having it learn

[11:48] just like you would an employee, right?

[11:50] >> Absolutely.

[11:50] >> Yeah. Like my my second brain, I

[11:52] literally call it my co-founder, right?

[11:54] So I want it to like learn me better

[11:56] over time and how I like to work, how I

[11:58] want it to work as well.

[11:59] >> Mh. Yeah. And I think this four-step

[12:02] kind of framework or whatever you want

[12:03] to call it, it yes, when you kind of

[12:06] maybe look at it like this, it might

[12:07] feel like it's a technical software

[12:09] engineering thing, but if you just

[12:10] relate that back to the same way you

[12:12] would maybe like let's just say build a

[12:13] treehouse, like you would plan that

[12:15] thing out first. You would draw it out.

[12:16] You would understand how much wood you

[12:18] need and where, you would get the right

[12:19] gear, and then once you've built it,

[12:20] you're not just going to put your kids

[12:21] on it. You're going to like test it.

[12:23] You're going to make sure that thing's

[12:24] not going to fall. So,

[12:25] >> um it's just a great way to think about

[12:27] it. And especially if you think about

[12:29] some of the the pitfalls that these

[12:31] models have with like the sick of fancy

[12:33] essentially just being a yes man.

[12:35] >> If you say, "Hey, you know, I want to do

[12:37] this. Does that look good?" And they're

[12:38] just going to say, "Yeah, it does."

[12:39] without really looking over the plan.

[12:41] And then

[12:42] >> on the verification side,

[12:44] >> you know, sometimes they do tell you

[12:45] something's done, but it's not. So

[12:47] having your own method of doing that as

[12:48] well,

[12:49] >> really important.

[12:50] >> By the way, guys, I know we are diving

[12:52] into a ton of information in this

[12:53] episode. So, what I did is I broke all

[12:55] of this down into a free resource guide

[12:57] that you can access for completely free

[12:58] by joining the free school community.

[13:00] The link for that is down in the

[13:01] description. Also, if you want to check

[13:02] out some of the key moments from this

[13:04] episode and all future podcasts on my

[13:06] channel, then go ahead and check out the

[13:08] AI Automation Society YouTube channel

[13:10] where we're going to be posting some of

[13:11] the best moments from the podcast over

[13:13] there. I'll link that YouTube channel in

[13:14] the description of this video as well.

[13:16] Anyways, thanks guys. Let's get back to

[13:17] the podcast.

[13:18] >> Yeah, verification really comes down to

[13:20] prove to me it's actually done and

[13:22] working,

[13:22] >> right? Right. And so like for any kind

[13:24] of coding task that's things like unit

[13:26] tests and linting and like that's where

[13:29] it gets a little bit more technical, but

[13:30] like really you can apply that to

[13:31] anything. Um like I this is an example

[13:33] that I'm going to spoil right now. Um I

[13:36] use claw code to generate this entire

[13:38] diagram. Like I have

[13:39] >> I had a feeling you did. Yeah.

[13:40] >> Yeah. Yeah. Yeah. So I have I have a

[13:42] skill. It's my scaladraw diagram skill.

[13:44] I've covered it on my YouTube channel

[13:46] actually. So I use it to build this

[13:47] whole thing. And um I was going to talk

[13:50] about this example a bit more right here

[13:51] when we really get into like verifying

[13:53] the work. Um but I think it's just such

[13:55] a good like non there's nothing to do

[13:56] with coding here. It's just creating a

[13:58] diagram. But as far as far as

[13:59] verification goes, I actually have it

[14:02] take the Excal diagram and render a PNG.

[14:06] So there's like an integration that I

[14:07] built into the skill for Cloud Code. So

[14:09] it can render it as an image. And as a

[14:11] lot of you know, like Cloud Code is able

[14:13] to understand images incredibly well

[14:15] now. for like the last year, it's been

[14:17] so good at um even viewing like a like

[14:19] if I zoom out here, like there's quite a

[14:21] bit of context, but like it can pick out

[14:23] the tiniest piece of text in a larger

[14:25] image like this. And so I have it look

[14:26] at that

[14:28] >> and then figure out like if there's any

[14:30] kind of like padding or spacing issues,

[14:32] like if there's any sort of overlap and

[14:34] and trust me, there was like it had to

[14:35] iterate a couple times to build

[14:37] something this big. Uh but then the the

[14:39] point is like it is able to iterate by

[14:41] itself. So, we don't really care about

[14:43] the initial mess ups that it has. As

[14:45] long as it like does that by itself, we

[14:47] just care about that that last thing it

[14:48] hands back to us when it says it's done.

[14:50] So, if we have this if we have this step

[14:52] when it says it's done, then like it

[14:54] actually is or at least it's closer. I

[14:55] mean, it's still probably not going to

[14:56] be perfect, but you get the idea. Yeah.

[14:58] >> Yeah. 100%. I've done something pretty

[15:00] similar with my video editing pipeline

[15:02] with the motion graphics it adds and

[15:03] sometimes things would be out of bounds.

[15:05] But like you said, the whole idea is

[15:07] it's almost never going to be 100% on

[15:10] that first pass, but without the

[15:11] verification checks, maybe it's 65 or

[15:13] 70, but now you can get something that

[15:15] is 92 on the first pass.

[15:17] >> Right. Exactly. Yeah. Yeah. It's it's

[15:20] good. So I mean verification,

[15:22] validation, whatever you want to call

[15:23] it, like that is one of the biggest

[15:24] things that I'm focusing on right now

[15:27] for any kind of application or

[15:29] automation that I'm creating. I want

[15:31] some kind of harness for the coding

[15:33] agent to be able to validate its own

[15:35] work for code to validate its own work.

[15:37] And for some things like um website

[15:40] design, it's actually pretty easy.

[15:42] There's a lot of tools out there uh

[15:44] maybe you've heard of Playright or

[15:45] Verscell's agent browser um for it to

[15:48] really just spin up the site, right? It

[15:50] can run the command to start the website

[15:52] and then it can visit it just as a user

[15:54] would take screenshots along the way to

[15:57] prove things to you or even just view

[15:58] the the UI itself. It's pretty easy for

[16:01] other kinds of things that you'll build.

[16:03] U it can be kind of hard to have the

[16:06] agent really verify its own work

[16:07] effectively. one like really simple

[16:09] example kind of silly example. Um I in

[16:12] my spare time like I' I've always loved

[16:14] like video games as a kid. I mean like I

[16:16] talked about with Scratch. I mean I was

[16:17] building like Pokemon and and uh Mario

[16:20] Bros and stuff. And so like I've

[16:21] actually like been doing a little bit of

[16:23] just trying to I mean I hate to admit it

[16:24] but Vibe Code video games, right? It's

[16:26] just a hobby. I'm not trying to like do

[16:28] something too crazy and it's more just

[16:29] like having it run in the background for

[16:31] fun. But like one of the things I had to

[16:32] think about is like how do I build a

[16:34] harness for the coding agent to be able

[16:36] to actually play the video game. It's a

[16:38] bit trickier because they can't like

[16:40] coding agents they need time to think,

[16:42] right? So if you have a game that's

[16:43] running at 60 frames per second, it's

[16:45] not really going to be able to react to

[16:47] things the way that a human would. So

[16:49] thinking about a system where it can

[16:50] basically like slow down the frame rate.

[16:52] I know it's kind of like a silly

[16:53] example, but it's just like that's one

[16:54] of the biggest things you have to

[16:55] engineer for for anything is like how

[16:58] would the agent actually verify that as

[17:00] a user would because just like looking

[17:02] at the code it creates or the skill it

[17:03] builds for you like that's not enough

[17:05] for it to just do that sort of like

[17:07] review highle review which is good but

[17:09] like you need to wait for it to really

[17:11] like use the application or whatever

[17:13] you're making as you would.

[17:15] >> Yeah, absolutely. And real quick, for

[17:16] anyone that might not have heard the

[17:18] term harness before, what is your kind

[17:20] of quick definition of that?

[17:22] >> Yeah. No, that's good. I know it gets it

[17:24] gets technical,

[17:26] >> right? Yeah. So, um, usually when people

[17:29] talk about harnesses, they're talking

[17:31] about something more like what I was

[17:32] going to talk about a bit here at the

[17:34] end. Um, so what I'm talking about as

[17:37] far as like validation is more like

[17:40] I mean it's it's kind of I I have to

[17:43] think about like how to actually explain

[17:45] what a harness is really. It's it's the

[17:47] wrapper around the large language model,

[17:49] the tools and context that it has access

[17:52] to. So it knows what it's working on and

[17:55] how to work on it effectively. So if we

[17:58] think of like a harness for AI coding,

[18:00] cloud code is actually a harness, right?

[18:02] like it when you download Claude code

[18:04] and you run it, it loads a system prompt

[18:06] on top of Claude as a large language

[18:08] model. It gives it the tools so it can

[18:10] run commands and create files on your

[18:13] computer. Um, that's what really makes

[18:15] it a harness. And and then when I was

[18:17] giving the example of like a harness for

[18:19] testing, it's more like u giving it a

[18:22] system where it's like, okay, these are

[18:23] the commands I can run to start the game

[18:25] and then like slow down the frame rate

[18:27] so that I can interact with it frame by

[18:28] frame and like really stop and analyze

[18:31] and think before I take another action.

[18:33] So it you can think of it kind of like a

[18:35] so I mean maybe I will just jump ahead

[18:37] here. You can think of the harness as

[18:38] the thing that just wraps the model. And

[18:40] then there's also that that component of

[18:42] the harness that you get to build

[18:44] yourself. I call it the AI layer. And so

[18:46] for cloud code, that's like your

[18:47] claw.mmd and your skills and your hooks

[18:50] and any kind of MCP servers that you're

[18:51] bringing in to connect it to your other

[18:53] platforms like your CRM or your task

[18:56] management software, right? That's

[18:57] that's building on top of the harness.

[18:59] So it's kind of like the large language

[19:01] model is the reasoning. It's it's the

[19:02] brain at the center and then you pick

[19:04] the tool like cloud code or codeex or

[19:07] whatever and then you can sort of like

[19:09] build the context and integrations on

[19:12] top.

[19:12] >> Absolutely. I love it. Yeah, well said.

[19:14] I think something something fun anyone

[19:16] listening should try real quick is if

[19:18] you go to an AI model and ask it to

[19:19] explain an AI harness or an agent

[19:21] harness. I would be willing to bet it

[19:23] does the whole car analogy where the

[19:25] engine is the AI model and the car is

[19:27] the harness. So let me know if you guys

[19:29] run that and and see if that's what you

[19:31] get.

[19:32] >> Sounds good. I mean we could we could

[19:33] test it right now.

[19:36] >> No, we won't we don't need to do it

[19:37] right now. But yeah, that's that's your

[19:38] homework for today.

[19:39] >> Yeah.

[19:40] >> Yeah. Yeah. Cool. Um Yeah. Yeah. So, I

[19:44] mean, we've talked about like validation

[19:46] a lot. Um, planning is the other thing

[19:48] that I really want to hit on cuz most

[19:50] people don't do enough of it.

[19:52] >> And it takes it takes patience. And this

[19:54] is like one of those um software

[19:56] engineering disciplines that I like to

[19:58] bring into um even when I'm talking to

[20:00] someone who's not writing code or who

[20:01] isn't technical is you have to spend I

[20:04] mean with coding agents you spend more

[20:06] time planning than you actually do

[20:07] building because you you really put a

[20:10] lot of your effort up front into the

[20:12] plan and then you use that to delegate

[20:14] as much of the coding as you possibly

[20:16] can or for a lot of us all of the coding

[20:18] to the AI coding assistant. And so its

[20:21] success is really just dependent on how

[20:22] good is your plan. Usually you have some

[20:24] kind of like a lot of people like using

[20:26] markdown, right? I use markdown a lot.

[20:27] So I'll have like a single markdown

[20:29] document that outlines um you know like

[20:32] the goal. What are we building here?

[20:33] What is success actually look like? And

[20:35] like of course with that comes the

[20:36] validation strategy um that we've

[20:38] already talked about. So how does it

[20:40] know that uh the work is done and

[20:42] working well? And then um not to get

[20:45] like too technical here, but especially

[20:47] more for any kind of like coding task,

[20:49] you're going to have like the

[20:50] integration points, right? Like if

[20:51] you're building on top of an existing

[20:53] automation or application or website,

[20:55] whatever, like what are the parts of the

[20:56] codebase that we actually have to touch?

[20:58] And so if you are more technical, you

[21:01] can sort of evaluate like make sure it's

[21:03] understanding it's correct of like,

[21:04] okay, what files are we really going to

[21:06] create and edit here? Not that you need

[21:08] that. Um, and then once you have that

[21:12] plan, then this is kind of what my

[21:14] workflow looks like. And then this is

[21:16] for anything. So you do some kind of

[21:17] like context loading up front, any sorts

[21:19] of like documents that your agent needs

[21:22] related to the task at hand. And then

[21:24] I'll typically have it do some kind of

[21:26] research, usually using sub agents for

[21:28] that. So if I'm building a new

[21:30] application, maybe I'll have one sub

[21:31] agent research what's a good tech stack

[21:33] for this. What's a good like approach if

[21:36] there are people that have built similar

[21:37] applications, right? So like especially

[21:40] if you're not as technical, that can be

[21:41] really useful for it to just gather a

[21:43] lot of information and then propose a

[21:45] plan to you. And so that's when you you

[21:47] create the plan with the coding agent.

[21:49] This is also where usually you want to

[21:51] have the coding agent ask you a lot of

[21:53] questions. Like I know Nate, you just

[21:54] put out a video today on uh Matt Poc's

[21:56] grill me skill, which is really good.

[21:59] Like you need to make sure that you that

[22:01] the coding agent is not assuming a ton

[22:03] of things about what you want it to do,

[22:05] like the workflow you want to build, the

[22:06] skill you want to build, whatever. And

[22:08] so having it ask you a lot of questions,

[22:10] clarify those things is good. So that

[22:12] way you can be confident that once you

[22:14] have that final plan like this is about

[22:16] this is what we're going to go and do

[22:18] now that both you and the coding agent

[22:20] are aligned on what's actually going to

[22:22] be done and and how you're going to

[22:23] validate it.

[22:25] >> Absolutely. Yeah. I love it. When you do

[22:27] that, are you typically using in cloud

[22:29] code plan mode or are you kind of

[22:30] planning but not in plan mode?

[22:33] >> Yeah, usually I don't use plan mode.

[22:35] Okay. It's It's good, but plan mode like

[22:38] puts Claude code into a bit of a

[22:39] different behavior that I'd rather be

[22:40] able to control my control more myself.

[22:43] So, my skill for planning is like

[22:46] instructions for how I want it to ask me

[22:48] questions and then just like generally

[22:49] how I want to go about researching and

[22:52] organizing things into a plan.

[22:54] >> Yeah.

[22:54] >> And so, like I want to define the

[22:56] sections. If you don't, then you're just

[22:58] using Cloud Codes plan mode. Like it'll

[23:00] build something actually pretty much

[23:02] like this. But I just like having that

[23:05] more um that that higher level of

[23:07] control. I think that's a theme that you

[23:09] get a lot through my content in general

[23:11] is that I I like to have control and

[23:13] customizability cuz in the end that's

[23:15] how you get the best results. It's just

[23:16] it's kind of like that learning curve to

[23:18] get to the point. Um like for example, I

[23:20] I don't use OpenClaw or Hermes. I have

[23:23] my own second brain that literally is

[23:24] just built directly on top of Clawed

[23:26] Code. And I'm a big proponent of that

[23:28] even though those other open source

[23:30] tools are very powerful because you're

[23:32] running something that you don't

[23:33] understand and it's harder for you to

[23:35] like really take as your own and it's

[23:37] not like a foundational component that

[23:39] you can create your own system on top

[23:41] of. So you're more like adopting someone

[23:43] else's system. And these tools have done

[23:45] a really really good job making it easy

[23:47] to extend and and really make your own.

[23:50] But like in the end building something

[23:51] from the ground up is always going to

[23:53] give you the most control even though

[23:54] that can be pretty daunting. Yeah, I

[23:57] hear you. Yeah, that's interesting. I

[23:58] mean, it it really does make sense. I

[24:00] always love, you know, that's something

[24:02] I just say a lot, which is a very simple

[24:04] theory is just to be genuinely curious

[24:07] to understand what's going on,

[24:08] especially when I don't understand what

[24:12] these lines of Python code that it that

[24:13] just got written mean, you know, and the

[24:15] whole idea of dark code.

[24:18] >> And I guess what do you think about that

[24:20] whole idea because I know you talk a lot

[24:21] about vibe coding and and preaching

[24:23] understanding things at their core. So

[24:25] when someone is generating automations

[24:28] or code that they don't

[24:31] understand how to read,

[24:33] >> yeah,

[24:33] >> how do they actually feel secure and

[24:35] safe about that?

[24:37] >> Yeah, that's a really good question. So

[24:39] >> pretty loaded, too.

[24:40] >> No, I'm No, that's that's good. I I

[24:42] welcome it. So I I'll answer in two

[24:44] ways. I'll answer first by saying that

[24:47] like maybe not everyone loves to hear

[24:49] this but like if you are using an AI

[24:51] coding assistant to write code cuz

[24:53] you're building your second brain you're

[24:55] creating automations whatever it is I

[24:57] would recommend at least trying to get

[25:01] to the point where you can understand

[25:02] the code and really at first that can be

[25:04] as simple as just asking cloud code or

[25:07] whatever coding agent to explain what it

[25:09] just wrote because code can look pretty

[25:12] intimidating but when you get over that

[25:15] like initial hump like it kind of reads

[25:18] like English and maybe that's just me

[25:20] being extremely ignorant because I've

[25:21] lived and breathed it since I was eight

[25:23] years old but it starts like as long as

[25:25] you understand the core primitives of

[25:26] like this is a class this is a while

[25:28] loop this is a if statement like it

[25:30] starts to read like English you're like

[25:31] okay I understand when this part of the

[25:33] code is going to execute now just asking

[25:36] your coding agent constantly and so um I

[25:39] mean like in cloud code there's the

[25:40] slashby the way feature so like you can

[25:43] always just kind of a sidecar

[25:44] conversation where it's like, "Hey, help

[25:46] me understand like what the heck is

[25:47] going on right here." And then it

[25:48] doesn't have to to dilute your main

[25:50] context and just kind of like keep

[25:53] throwing context at at Claw Co. Like you

[25:55] can have that separate conversation for

[25:56] your own understanding and then go back

[25:58] to the main task at hand without it

[26:00] being affected. So I would recommend

[26:02] that. And then you know if someone is

[26:04] really not inclined to learn how to code

[26:07] like that's just not your goal. You want

[26:09] to use cloud code to automate things and

[26:11] not have to like engineer applications.

[26:13] I totally get that as well. Really comes

[26:15] down to your validation strategy is

[26:18] what's going to dictate how confident

[26:19] you can really be and what is created.

[26:21] So if you're spending a lot of time in

[26:23] this is why I say like whenever you're

[26:24] building something with cloud code, the

[26:26] way that you don't vibe code is that you

[26:28] sandwich the delegation of the coding

[26:32] between the planning and the validation

[26:34] process that you're heavily involved

[26:36] with. Right? Like the only reason I'm

[26:39] ever going to say, "All right, Claude,

[26:40] go rip through this." is because I made

[26:42] sure I created a really detailed spec

[26:44] and I've defined like this is how you're

[26:46] going to tell me that you're done and

[26:48] how you can be confident that you

[26:50] actually are.

[26:52] >> I love it. Very well said. Nothing to

[26:54] nothing to add there.

[26:55] >> Cool. All right. Sounds good. Yeah. Um

[26:58] Yeah. And as far as like creating that

[27:00] plan with the coding agent, the most

[27:03] important thing is to manage the context

[27:06] like what your coding agent is going to

[27:08] really be paying attention to at the

[27:11] start of any kind of planning session.

[27:13] So the the thing here is that attention

[27:15] is scarce. And so there's a big

[27:18] misconception right now for a lot of

[27:20] people where they think that like it

[27:22] doesn't really matter how much you throw

[27:23] at a coding agent because everyone is

[27:25] hearing nowadays how like large language

[27:27] models can support up to 1 million

[27:29] tokens in their context when they're

[27:31] like oh that that's like the Harry

[27:33] Potter book five times over I forget the

[27:35] exact but people like always throw like

[27:38] some some analogy where it just like

[27:40] makes it pretty obvious where it's like

[27:41] 1 million tokens is an insane amount of

[27:43] information and it actually is but

[27:46] there's two massive caveats here. The

[27:48] first one is that that context will go

[27:50] way faster than you think because if

[27:52] it's reading through um a bunch of

[27:55] skills that you set up for it or a bunch

[27:56] of code that can be tens of hundreds of

[27:59] thousands of tokens very quickly and

[28:01] then the other thing is uh large

[28:04] language models have what's called the

[28:05] dumb zone. And so you have the the

[28:09] little bit of context up front. Maybe I

[28:10] can just draw like a quick little

[28:12] analogy here. So if like this is Oh,

[28:14] that is a fat marker. Um, hold on. Okay,

[28:18] I I give up already. I'm not going to

[28:20] try that. Okay, so you you have to

[28:22] imagine this with me here, but imagine

[28:23] you have a box that represents the the

[28:26] LLM's context window. You have that

[28:28] initial part at the start of the

[28:31] conversation up to the first, you know,

[28:32] 100 or 200,000 tokens where the large

[28:34] language model feels very sharp or at

[28:36] least it feels like it's at its best.

[28:39] Once the conversation surpasses that

[28:41] first 100 200,000 tokens, obviously it

[28:44] uh depends on the model when you reach

[28:46] the dumb zone, you get to the point

[28:47] where it just feels like it's overloaded

[28:50] with information and it starts missing

[28:51] things and making mistakes that seem so

[28:54] obvious to you or like the kind of thing

[28:56] where you're like, if I had had a fresh

[28:58] context here, like there's no way it

[29:00] would have made that mistake. Like it

[29:01] writes a really bad line of code or it

[29:04] uh doesn't use a skill that you thought

[29:07] it should have known to use. right? Like

[29:09] that kind of thing if it's in the middle

[29:10] of a larger workflow.

[29:12] >> And so that that's why I say attention

[29:14] is scarce. Like don't don't get under

[29:16] that false notion that you don't really

[29:18] have to care about how much you give it.

[29:20] Like if you're trying to have it handle

[29:22] a larger workflow, you still have to you

[29:25] have to be very careful like what you

[29:26] give it up front versus what you allow

[29:28] it to discover when it actually needs.

[29:30] And like that's one of the most

[29:31] important things with skills with Claude

[29:33] is you're giving it procedures and best

[29:35] practices, but it gets to decide like,

[29:37] okay, now I need to rely on this process

[29:40] or this information. So you're not just

[29:42] dumping a bunch of things up front. A

[29:44] lot of people do that. Like even with

[29:46] MCP servers back in the day, they would

[29:48] they would connect their like 20 MCP

[29:51] servers to cloud code and each one of

[29:52] them was was uh filling the context with

[29:55] like 20,000 tokens up front of

[29:58] information because it has like all the

[30:00] tool calls or the tools that come with

[30:02] the MCP server. And so their large

[30:04] language model would always act super

[30:06] dumb. And so they're like, I'm using the

[30:08] latest opus. Like why am I getting

[30:10] terrible results? And it's really it

[30:11] comes down to just how much of the

[30:14] context is filled right away. Yeah. Oh

[30:16] my gosh. It drives me nuts. It It truly

[30:18] drives me crazy when you hear people

[30:21] blaming the model when it really is kind

[30:23] of a skills problem. And we see this at,

[30:28] you know, when you look at these studies

[30:30] and surveys too about business adoption

[30:32] >> where it really is these people either

[30:35] have not yet felt the ROI because they

[30:38] can't they don't know enough about how

[30:40] to use it truly,

[30:42] >> right? And also people claiming that

[30:44] they have the skills to, but they're

[30:46] just not doing it. And like the adoption

[30:48] is then another problem. But I mean,

[30:50] obviously I'm not doing heavy heavy

[30:53] coding, building software and and apps.

[30:56] But, you know, we're doing some pretty

[30:57] cool things and I've seen some people do

[30:58] some really awesome things and it's just

[31:00] >> yeah,

[31:00] >> there's a lot of things like you know,

[31:02] if you kind of think about your your

[31:03] diagram that you had, you got the model

[31:05] in the middle, you got the agent

[31:06] hardness around that and then obviously

[31:08] a huge layer is what you put in there as

[31:10] well and the way that you manage your

[31:12] stuff. And I think that the 1 million

[31:14] context window specifically for you know

[31:16] like let's just say Opus 4.8 at the

[31:17] moment. Obviously, it's great, but it

[31:19] definitely comes with a false sense of

[31:21] security with people now thinking that

[31:23] they have the million, but when, and I

[31:27] know this might be outdated by next

[31:29] month or two months away, but let's say

[31:31] right now when you're in cloud code,

[31:32] >> when do you typically

[31:34] >> do your compact or a session handoff and

[31:37] clear and when do you get out of there?

[31:40] Yeah. So, with Opus right now, it's

[31:43] usually around 250,000 tokens, and I

[31:46] feel like it gets into the dump.

[31:47] >> That's my exact number, too.

[31:48] >> Oh, really? Okay. Yeah. Yeah. Good.

[31:50] Cool. So, and that, by the way, is like

[31:51] really subjective. Like, I'm not going

[31:53] to um bet million dollars on on like the

[31:58] on Boris Churnney or someone saying

[31:59] like, "Yeah, it's also 250,000." Like,

[32:01] >> quarter million is just clean, right?

[32:03] >> Yeah. It just it sounds good and it is

[32:05] like pretty accurate. I would say like

[32:06] Opus 4.7 was around like 200,000 and

[32:10] then like Sonnet 4.6 is like honestly

[32:13] probably only like 100 125,000. Um like

[32:16] it as you go to these smaller models

[32:19] like the dumb zone becomes a pretty

[32:21] small amount of context relative to like

[32:23] what it theoretically can handle. You

[32:25] just never want to get to that point. So

[32:27] then with the dumb zone thing, I've also

[32:29] heard stuff about the model being really

[32:31] good at remembering things that are at

[32:33] the front and the very end and the

[32:34] middle is where it loses. So where does

[32:36] that play into the whole dumb zone

[32:37] conversation?

[32:39] >> Yeah. So basically that issue is just

[32:42] amplified the more you get into the dumb

[32:44] zone. Yeah. And um yeah, as far as like

[32:46] I mean we don't have to get into like

[32:47] the super technical details for how the

[32:49] attention mechanism works for LMS, but

[32:51] yeah, you can think of I mean like the

[32:52] analogy I always like to use is the

[32:54] needle in the hay stack problem. Yeah,

[32:55] >> like if you have that like little piece

[32:57] of information that you want the agent

[32:59] to remember in the middle of a massive

[33:01] conversation, it's like trying to find a

[33:03] needle in the hay stack. Like you can't

[33:04] expect the model to just because of the

[33:06] way that large language models are

[33:08] engineered. Um you can't expect it to

[33:10] like always be able to pick out that

[33:11] little piece of information.

[33:13] >> 100%. Yeah.

[33:15] >> Yeah. I wish you could. That would be

[33:17] nice if there wasn't a such thing as a

[33:18] dumb zone. It would make it much more

[33:21] convenient for us to hand it massive

[33:23] tasks and let it just rip through

[33:24] things. But a lot of the reason we have

[33:26] to create a harness and like a lot of

[33:28] the things I'm focusing on right now on

[33:30] my channel and just like generally what

[33:32] I'm building is creating harnesses that

[33:35] build a workflow that can bind multiple

[33:38] coding agent sessions together. And so

[33:40] basically it's like one model does the

[33:42] planning and then my orchestrator will

[33:44] like automatically take that handoff

[33:47] document like the plan and then feed it

[33:49] into another agent for implementation.

[33:51] And then when the implementation is

[33:52] done, it'll create like an execution

[33:54] report and then it'll hand that off to

[33:56] the next agent to validate things and do

[33:58] a code review. And it might sound like

[34:00] like that's a lot of engineering and it

[34:02] is, but it's very necessary right now

[34:04] because if you're trying to do any kind

[34:06] of like real work for like production

[34:08] grade software or building an automation

[34:10] that's like critical for your business,

[34:11] you can't just throw the whole thing at

[34:13] a single cloud code session unless you

[34:16] can like confidently build it in that um

[34:18] that zone that you have before you get

[34:20] to the dumb zone. And most of the time

[34:21] you just can't do that or at least you

[34:23] can't really trust that's going to be

[34:24] the case because you never know how much

[34:25] it's going to have to iterate on

[34:27] something. And

[34:27] >> so that's why I'm really like I guess

[34:30] you could say bullish right now on um

[34:32] harness engineering which is like

[34:34] building a the workflow that uh

[34:37] orchestrates many coding agent sessions

[34:39] to handle a larger task. And like a

[34:42] really basic example of that kind of

[34:44] harness is the Ralph loop. It went like

[34:46] super viral at the start of this year.

[34:48] Um so I feel I feel like even if you

[34:50] haven't heard too much about harness

[34:51] engineering you probably have at least

[34:52] heard of the Ralph loop. And that's like

[34:54] really like the foundation of that kind

[34:56] of harness, right? Like the Ralph loop

[34:58] is stringing together multiple coding

[35:00] agent sessions. I I wish I had uh one of

[35:02] my diagrams up for this right now. I'll

[35:04] just have to explain it verbally but

[35:06] like you know basically you have the

[35:07] first cloud code session read in your

[35:10] larger spec for like a bigger automation

[35:12] you want to build and then um it'll

[35:15] define like the the task list like first

[35:18] phase is this second phase is this and

[35:20] then it'll have many coding agents

[35:22] handle one phase at a time but it'll

[35:24] like do it all automatically in a loop.

[35:26] That's why it's called a Ralph loop cuz

[35:28] like agent one will do phase one and

[35:29] then it'll write up its little report

[35:31] like its handoff to the second agent

[35:32] that'll continue the work. And like the

[35:35] main reason the Ralph loop matters is

[35:37] because it you can't have one agent

[35:40] handle that larger task without it

[35:42] getting into the dumb zone and like you

[35:44] know halfway through phase two, right?

[35:46] Like you have to break things up.

[35:47] >> Yeah. So it sounds like from like a a

[35:50] high level view the idea or kind of the

[35:53] mindset that you've got like this

[35:55] assembly line and you have an agent

[35:58] doing something. Each agent kind of does

[35:59] one thing really well and hands over

[36:02] their input to the next agent in a way

[36:04] where

[36:05] >> the agent has enough context to

[36:06] understand what has been done and what

[36:08] is left to do and what its current job

[36:10] is.

[36:12] >> Yeah, exactly. Yeah, assembly line is a

[36:14] a really good analogy and um I mean that

[36:17] that applies to a lot more than than

[36:20] just writing code. Um like like one

[36:22] example that comes to mind when I think

[36:24] about like cuz I I know that I've been

[36:26] talking about like coding as an example

[36:28] for a lot of things, but um I I work

[36:30] with a lot of companies that are in sort

[36:32] of like the like B2B side of things. And

[36:36] when you're B2B, like you do a lot of um

[36:40] creating quotes, like estimates, right?

[36:42] like you have um construction company or

[36:45] uh like I've worked with companies in

[36:47] the print industry where like they'll

[36:48] have like a request for like all right

[36:50] make me like 100,000 flyers or whatever

[36:52] and like for those companies one of the

[36:54] biggest opportunities for them to use AI

[36:56] is to use something like Claude to help

[36:59] them take in a request and automatically

[37:02] create an estimate like a quote for how

[37:05] much that uh job's going to cost

[37:07] >> cuz that's like a really really

[37:09] laborious job like more than you would

[37:11] think Like when I when I've talked to

[37:12] these companies, like it's crazy how

[37:14] much work goes into that because they

[37:16] have to like take the request and they

[37:18] have to understand like how much labor

[37:20] goes into you know parts obviously like

[37:21] depending on the industry and then they

[37:23] have to do research on like the latest

[37:24] prices for things and making sure

[37:26] they're getting it from the right

[37:27] vendor. Like there is so much that goes

[37:28] into that and so like that kind of thing

[37:31] u is it's like a really good example

[37:33] like nothing to do with creating code

[37:35] still using something like cloud code.

[37:37] You can use coding agents for this to go

[37:39] through that larger workflow of like

[37:41] looking at their inventory, looking at

[37:43] prices, comparing vendors, um, all based

[37:46] on what's going to be needed to

[37:47] accomplish that task like that remodel

[37:50] that the 100,000 flyers for whatever

[37:52] that request is from the other company

[37:55] and then creating that estimate and then

[37:57] understanding how the company works like

[37:59] what kind of padding they want on top of

[38:01] u based on the the labor and the cost

[38:03] for the parts or whatever. Like there's

[38:05] a lot that goes into that. And so like

[38:07] that's the kind of thing where like

[38:08] you'd build a workflow where you have

[38:10] one agent that's going to research

[38:12] inventory, one agent that's going to

[38:14] look at prices and and compare prices

[38:16] for parts, and then one agent that's

[38:18] going to draft the PDF, and then maybe

[38:20] another one that's going to make it look

[38:21] good. I mean, I'm kind of stretching the

[38:22] example here, but you get the idea of

[38:24] like you you actually don't have just

[38:25] one agent handle the entire thing for

[38:27] something that big. And you are going to

[38:29] be doing a lot of planning, right? like

[38:31] you're going to plan, you're going to

[38:33] have a validation at the end like what

[38:35] kind of calculations can I do at the end

[38:36] to make sure that like this job uh has

[38:38] the the margin that we want on it for

[38:40] example.

[38:41] >> Yeah. Yeah. And I think I think back to

[38:45] one of our biggest failures back when I

[38:48] was still kind of in the day-to-day of

[38:49] running an agency was that exact use

[38:52] case was having to look through tons and

[38:55] tons of examples, past quotes, past

[38:57] client work, past proposals, and and

[39:00] needing to generate these quotes with so

[39:02] many different factors that go into it.

[39:04] And that was one of our biggest failures

[39:06] because me personally, I underscoped

[39:08] that build. And we went into it not

[39:10] realizing how much actually is necessary

[39:13] to get to an accurate quote. So that was

[39:15] a great lesson for me to learn not only

[39:18] about the importance of asking enough

[39:20] questions and scoping, but just

[39:22] >> in the way that you split up the work.

[39:25] And I think, you know, obviously Cole

[39:26] mentioned he's he's talked a lot of

[39:28] these examples have been kind of around

[39:29] coding, but I don't really do much

[39:32] coding. I mean, at the end of the day,

[39:33] these automations are code. So yes, it's

[39:34] coding. Yeah. But

[39:36] >> I'm not doing like

[39:37] >> software. I'm not building products, but

[39:39] every one of these theories that we

[39:41] talked about in these mindsets and

[39:42] frameworks has, you know, directly

[39:44] applies to the knowledge work is kind of

[39:45] what I like to call it of of what I do

[39:47] on the day-to-day and what probably most

[39:48] of you guys need to do. That gives you

[39:50] an insane amount of leverage right away

[39:53] in cloud code. And I think that

[39:55] >> when you think about your job or you

[39:58] think about some of your

[39:59] responsibilities, it's not just one

[40:01] responsibility. it is. You can drill

[40:04] that down into so many little subtasks

[40:05] like Cole just said like one agent does

[40:07] the research, one agent does the PDF

[40:09] generation, all these little strings of

[40:12] subtasks that flow up together to

[40:14] actually make the overall responsibility

[40:16] which might be 10 little tasks that get

[40:19] strung together. So when you can

[40:21] actually break down a process by just

[40:23] writing it down or or you know flowing

[40:26] it out on on a piece of paper,

[40:28] >> it makes things a lot more clear,

[40:30] >> right? Yeah. Yeah. And one thing I want

[40:33] to say here is that a lot of people they

[40:34] want to simplify it down to just using

[40:36] sub aents. So like for this this larger

[40:39] workflow, what if I just have my main

[40:41] cloud code dish out a bunch of tasks to

[40:44] sub aents? Like that can work for some

[40:46] things. I do love using sub aents

[40:48] especially when I'm initially planning

[40:50] any kind of automation or or uh

[40:53] application,

[40:54] but it's hard to really make those

[40:56] communicate well with each other. Like

[40:58] we've talked a lot about handoffs here.

[41:00] A lot of times one agent when it's

[41:02] taking that next step in a workflow it

[41:04] has to understand the work that was done

[41:05] with the by the previous one whether

[41:07] that's work you know actually writing

[41:09] code or if it's just doing research or

[41:11] if it's pulling information from your

[41:13] CRM for example like it has to have that

[41:15] kind of handoff document and it's really

[41:17] difficult to um do that well with sub

[41:20] agents claude has tried their hand at

[41:24] doing something with agent teams so they

[41:26] they that's kind of like the step above

[41:27] sub aents where they can really

[41:29] communicate with each other but uh that

[41:31] is like really unrefined. It's a really

[41:32] good idea but it's really unrefined and

[41:34] it's very expensive like tokenheavy.

[41:36] >> Yeah.

[41:36] >> And so yeah like and that's actually

[41:38] what I'm working on. So there's a open-

[41:40] source project that I'm working on

[41:41] called archon and that's really the

[41:43] problem it's solving is how can we more

[41:45] like the word I use is deterministic

[41:47] like how can we build the AI model like

[41:51] build cloud code into a system instead

[41:53] of having cloud code trying to

[41:55] orchestrate everything because that's

[41:56] when it becomes difficult for

[41:58] communication and everything becomes

[42:00] very tokenheavy right so like the way

[42:02] that I like to put it is we want to um

[42:05] pick when the AI model works in a

[42:08] workflow instead of having it drive the

[42:10] whole thing.

[42:11] >> Mhm. Yeah. Yeah. How do you make such an

[42:16] autonomous non-deterministic system as

[42:18] deterministic as possible?

[42:20] >> Pretty much. Yep. Yep. As deterministic

[42:21] as possible. I wish I could say make it

[42:23] deterministic, but that is never going

[42:24] to happen. Unfortunately, that is

[42:26] fundamentally impossible.

[42:28] >> Yeah.

[42:28] >> I love it. Yeah. Completely agree with

[42:29] you there.

[42:31] >> Cool. Yeah. Um, so I mean really we

[42:34] we've talked about most of the other

[42:35] things I have in the diagram here. Like

[42:37] we've talked about verification, making

[42:39] sure that it's able to check its own

[42:42] work and um yeah, I mean like the the

[42:45] main thing here is we don't really care

[42:46] about what it does it f on its first

[42:49] pass. If we build a system where it's

[42:50] able to iterate, that's all we really

[42:52] care about as long as it doesn't take

[42:53] billions of tokens to get to that final

[42:55] stage. But like when I'm whenever I'm

[42:58] using cloud code for something, I'm

[43:01] never optimizing for speed. I mean, at

[43:04] least like I don't want it to be

[43:05] unrealistically slow, but any kind of

[43:07] task I have for it, I don't really care

[43:09] if it's something that I have to uh have

[43:11] it work through for a half hour or an

[43:13] hour and a half. Like, I'll send off

[43:14] that request and then I'll just go to

[43:16] another Cloud Code session for whatever

[43:18] else I have to work on or I'll do

[43:20] something, believe it or not, without an

[43:21] agent for a little bit, like if I have

[43:22] to uh record a video. Um, well, I mean,

[43:26] maybe I'm using an agent in the video,

[43:27] but you get the point. But anyway, like

[43:28] the the point is that I don't really

[43:30] care how long it takes because I just

[43:32] care getting the best results possible.

[43:35] >> Um, and so yeah, that's why like I I

[43:37] spend a lot of time engineering systems

[43:40] for coding agents to check their own

[43:42] work, whether it's browser automation

[43:43] for a website or they silly example I

[43:46] gave earlier, like a way for it to sort

[43:47] of like play a video game as a human

[43:49] would. And that's like a really

[43:51] fascinating problem for me to solve

[43:52] right now. It's just like that

[43:53] verification layer at the end for a

[43:55] coding agent, which um also extends to

[43:57] things like security as well. And so

[44:00] like that's not something as interesting

[44:01] to talk about right now, but like

[44:02] security is pretty important to me. It's

[44:04] something that um vibe coders get very

[44:06] burned for. I mean, you hear those

[44:07] horror stories like at least once a

[44:09] month

[44:09] >> of uh you know like their superb base

[44:12] private or secret key getting leaked in

[44:14] their uh JavaScript files and things

[44:16] like that because they're just

[44:17] completely vive coding. Like I mean

[44:19] that's like the simplest example but

[44:21] yeah like that kind of part of

[44:22] verification is really important as

[44:24] well.

[44:25] >> Yeah. And on that whole element of

[44:28] security and

[44:30] >> what could go wrong when you think about

[44:32] sort of like the permission layer that

[44:34] you're putting around your agents. I see

[44:36] a lot of false sense of security once

[44:39] again where people think that their

[44:42] prompts

[44:44] are a good enough permission layer when

[44:46] really that permission layer needs to be

[44:48] >> scoped keys or you actually can't touch

[44:51] this at all because I think I was

[44:53] talking to my team and

[44:54] >> we kind of got to this conclusion of

[44:56] >> if you have the mindset that

[44:58] >> anything that the agent can read or can

[45:01] touch it will like you have to assume

[45:03] that it will even if you never ask it to

[45:05] That assumption is what's going to save

[45:07] you from having your database deleted.

[45:10] >> Yes. And that's funny you bring up that

[45:12] example specifically because I was just

[45:14] about to say like if you tell it never

[45:16] to to wipe a database, it's still going

[45:18] to do that.

[45:19] >> Mhm.

[45:19] >> Like there was a story that went viral

[45:21] um like a month or two ago was someone

[45:24] like really high up at Meta that had

[45:26] their database. I'm still not convinced

[45:28] that's real. I feel like they might have

[45:29] been I don't know cuz people get so much

[45:31] attention when they have stupid stories

[45:33] like that. But but anyway,

[45:34] >> conspiracy theories with Cole,

[45:36] >> right? Yeah. But like it is it is

[45:39] definitely possible and I do know some

[45:40] stories of that actually happening just

[45:42] to a smaller extent.

[45:43] >> It just feels so weird that or it sounds

[45:45] so stupid that it's like their actual

[45:47] production database was wiped. But I

[45:48] mean even if you have a test database

[45:50] wiped, it can still be a bummer if that

[45:51] slows you down a lot. And so so yeah, it

[45:54] is super important. You never want to

[45:56] assume that just because you tell an

[45:58] agent to not do something, it never

[46:00] will. I mean it's the same thing like if

[46:02] you tell a kid to not do something they

[46:05] just might not listen. I mean even even

[46:07] adults

[46:07] >> there actually recently something did

[46:09] happen to us which is kind of why we

[46:10] started talking about this.

[46:12] >> Okay.

[46:12] >> We had this this incident where the

[46:15] agent had the right intentions. It was

[46:17] trying to be proactive and it actually

[46:18] saw something on its task list but it

[46:21] misinterpreted it

[46:22] >> and it ended up sending an email to our

[46:24] entire list

[46:25] >> with a discount code and it was like not

[46:28] supposed to go out. So, we had to like

[46:31] change the code, update the page, we

[46:33] emailed out an apology. So, if you guys

[46:35] are on the email list and you got that,

[46:36] that's what happened. But it's just

[46:38] like, you know, I wasn't mad at the

[46:40] person who was kind of responsible for

[46:41] the agent. It was just a really good

[46:42] opportunity for us to think about, okay,

[46:44] why did this happen?

[46:45] >> And, you know, she wrote up a case

[46:46] study. We sent it to the whole team and

[46:48] everyone was like, okay, that's a

[46:49] really, really good reminder of how

[46:51] careful you have to be. Because, you

[46:53] know, if you connect to an MCP server

[46:54] and you don't limit the permissions, it

[46:56] has everything, you know. Yeah. Yep. Now

[46:59] that's good. Yeah. The main way that I

[47:01] restrict actions from my coding agent is

[47:04] with hooks.

[47:05] >> So like cloud code hooks is a really

[47:06] good way because um basically a hook and

[47:09] cloud code is a little piece of code

[47:12] that you can run whenever a certain

[47:14] event happens in the tool. So whenever

[47:17] you start a session, whenever you end a

[47:19] session, right before cloud code uses a

[47:21] tool, you can run some kind of code that

[47:24] does a security check. I mean there's a

[47:26] lot of other things but like I love

[47:27] using hooks for security. And so what

[47:29] you can do in cloud is every time it's

[47:31] about to invoke a tool like it wants to

[47:34] write out to a file or make some

[47:36] requests to the web, you can uh check

[47:39] against that command to make sure it's

[47:40] not trying to mess with a folder you

[47:43] don't want it to touch or run some kind

[47:45] of command you don't want it to run. And

[47:46] there's a lot of different ways you can

[47:47] check for that that we don't have to get

[47:48] into right now. Um, but that's like one

[47:50] of my favorite ways to make sure it's

[47:52] like not reading my environment

[47:53] variables or it's not running a a delete

[47:56] command for a database.

[47:58] >> Um, and it it it's really hard to make

[48:00] sure you're you're covering all the

[48:02] loopholes cuz there's a lot of things

[48:04] that coding agents can do.

[48:06] >> Yeah.

[48:07] >> To get around those kind of checks as

[48:08] well. A lot of people have false false

[48:10] sense of security around that as well.

[48:12] So, you kind of have that like first

[48:14] false sense of security where it's like,

[48:15] well, I told it to never delete my

[48:17] database. And then you have the second

[48:18] level where it's like I block all delete

[48:20] SQL statements. But then there's that

[48:22] third level that you have to like make

[48:24] sure you're engineering for um like for

[48:26] example a coding agent. If you if you

[48:29] don't allow it to call the like delete

[48:32] like remove command to delete a folder,

[48:34] it can still write a script to do that.

[48:36] So it just has to do twostep like write

[48:38] the script and then run the script and

[48:40] then it's still able to remove a file or

[48:41] folder on your computer. So it's I mean

[48:44] they're less likely to do that. So, it's

[48:45] still like you're getting there if you

[48:48] are at least have like that that second

[48:50] false sense of security, but like you

[48:52] got to be really safe. You got to it's

[48:53] it's actually a tough problem to solve.

[48:55] >> Yeah, man. AGI is it's it's scary.

[48:58] >> Yeah.

[48:59] >> But I would love to see and maybe you've

[49:01] already got one out, but I would love to

[49:02] see a a Cole Hooks master class because

[49:05] I actually just recorded one

[49:07] >> and I don't use hooks that much to be

[49:10] honest. Like I really don't. I think my

[49:11] my main hook that I have is just to give

[49:13] me a noise notification when it's done

[49:15] or when it needs me. But yeah, like I

[49:17] have underutilized hooks for sure. And

[49:20] I'm not sure if that's because they're

[49:22] mainly valuable when you're doing heavy

[49:24] coding but

[49:26] >> I would assume that there's a lot of

[49:27] things that I could be doing in my

[49:28] day-to-day where hooks would be really

[49:30] good and I need to definitely look into

[49:33] a little bit more how I can be utilizing

[49:35] them. But anyways,

[49:37] >> yeah. Yeah, I I definitely should do a

[49:39] master class on hooks because there's a

[49:41] lot of ways that I use them. Um, yeah,

[49:44] since we're on the topic, like one of

[49:45] the really interesting way to use hooks

[49:47] is you can use them to automatically

[49:50] suggest like you can have cloud code

[49:52] like automatically suggest ways to uh

[49:55] improve your AI layer, like make your

[49:57] rules better, make your skills better.

[50:00] And a lot a lot of tools like Hermes and

[50:02] OpenClaw, they kind of do this. I don't

[50:04] think they like explicitly use hooks,

[50:06] but like OpenClaw for example, every

[50:08] like 10 20 turns, I think it's

[50:10] configurable. It will like kind of

[50:13] compact your conversation and store it

[50:15] as a memory, right? So that you have

[50:17] like the whole like daily log thing with

[50:19] the uh memory MD file. Like all of that

[50:22] comes from what's essentially a cloud

[50:23] code hook. Like so with the way I use

[50:25] cla code with my second brain

[50:27] >> is uh every time I have a memory

[50:29] compaction, which I try to avoid those I

[50:31] don't want to get that far into

[50:33] conversation. um or I end a session, it

[50:36] automatically creates a summary of the

[50:37] conversation, puts that in a daily log,

[50:39] and then I have a process every day.

[50:41] It's basically like cloud code dreaming

[50:43] where it's going to look at the daily

[50:44] log and then extract any like really

[50:46] important things to store and sort of

[50:48] like promote to my primary memory file.

[50:51] Like here are the decisions that I've

[50:52] made recently or like the things that

[50:53] I'm actively working on and where I'm at

[50:55] with them.

[50:56] >> So like hook hooks actually drives a

[50:57] whole thing like this terminal that that

[50:59] this is like the second time it's popped

[51:01] up. Um, that's actually a hook that just

[51:03] fired there. So, I'm just like testing

[51:05] some other things. I forgot to turn it

[51:07] off, which is unfortunate, but actually

[51:08] now it made for good illustration. I had

[51:10] I had a hook run as I'm talking about

[51:12] it. I'm just testing something else

[51:14] right now.

[51:15] >> Yeah. Just just yet another way to make

[51:17] these non-deterministic things as

[51:19] deterministic as possible. So, what do

[51:21] we have next after this verify the work

[51:24] section?

[51:24] >> Yeah. Yeah. So, really, this is the last

[51:26] thing. So, we've already talked about

[51:27] the the harness, but the the last and

[51:30] honestly probably the most important

[51:32] thing is the system evolution that I

[51:33] talked about just a little bit earlier.

[51:36] And and really the the mindset here is

[51:39] what like I this is out of everything

[51:42] that makes it so you're really directing

[51:43] cloud code instead of just being a user

[51:45] of it, the building the system is the

[51:47] most important thing. So anytime there's

[51:50] an issue that comes up, instead of just

[51:52] fixing the issue and moving on, it's an

[51:54] opportunity for you to with the help of

[51:56] the coding agent, with the help of cloud

[51:58] code, figuring out like what could we

[51:59] make better so that this doesn't happen

[52:01] again. Like maybe there's a new rule

[52:03] that we can add in our claw.md or

[52:05] there's a new document that we can give

[52:08] it when we're in our planning process or

[52:10] there's maybe an update to our skill

[52:13] that we could make. And I'm being kind

[52:14] of general on purpose here because

[52:16] there's a million different ways that we

[52:17] can improve our system. And so this is

[52:19] kind of like the example that you gave,

[52:21] Nate, where you had the email go out or

[52:23] at least it went out to way more people

[52:25] than it should have. And so you wrote up

[52:27] that report of like here's what

[52:28] happened. Here's what we can do better.

[52:30] And so it's kind of doing that but like

[52:32] for the agent so that going forward it

[52:35] has that rule so it it doesn't do that

[52:36] thing anymore. Like maybe it uh didn't

[52:38] run all the validation you wanted it to.

[52:41] So now you just like make sure that like

[52:42] that's a part of the rule where it's

[52:43] like this you make sure you don't forget

[52:45] this validation kind of as a silly

[52:47] example but that way every bug becomes a

[52:50] permanent upgrade. So once you have this

[52:52] kind of system in place you actually

[52:54] almost welcome bugs like I want

[52:56] something to go wrong because then I can

[52:57] make sure it never happens again

[52:59] >> right like I almost have I almost feel

[53:01] kind of nervous when everything's going

[53:02] too well cuz then it's like oh shoot I

[53:03] have no way to like make my agent better

[53:05] right now. So it's it can kind of become

[53:07] nice.

[53:07] >> Yeah. Absolutely.

[53:09] >> Yeah. Just get better over time. I've

[53:10] got an interesting question for you. So,

[53:12] >> I completely agree. Every single time

[53:14] that you have a failure, you should look

[53:16] at that as data and an opportunity to

[53:17] improve the system.

[53:19] >> Now, what what about before you get

[53:21] those failures? How do you think about

[53:24] to your best to the best of your ability

[53:27] finding those edge cases or predicting

[53:29] what edge cases might happen and trying

[53:31] to build in guardrails before

[53:33] >> the whole testing part?

[53:35] Well, it can never be perfect, which is

[53:37] why I lean on this so much. But

[53:39] generally, when you're looking out for

[53:40] edge cases,

[53:42] um, I mean, cloud code is actually

[53:44] pretty good at it.

[53:46] >> It's not going to cover like nearly all

[53:47] the edge cases, but even just asking it

[53:49] like how could this go wrong is a

[53:51] question that sometimes people are

[53:52] honestly like nervous to even ask, but

[53:55] it's a really good question once you're

[53:56] done with the implementation. And like

[53:58] this is a part of like my code review

[54:00] skill that I have built in where it's

[54:02] like ask yourself what could go wrong

[54:04] here and then try to engineer a scenario

[54:07] where you're really testing that. Like

[54:09] if I'm building an automation where I

[54:11] think there might be an edge case where

[54:12] it doesn't handle this kind of input

[54:14] correctly, I'm going to as a part of my

[54:15] agent's code review have it like create

[54:18] that like it'll invoke the application

[54:20] with that input like a web hook or

[54:23] whatever and try to break it and see

[54:24] what happens. And then if it does break

[54:26] then I mean that's obviously going to be

[54:28] like going back here a part of our

[54:30] verification where um it'll then uh

[54:34] address that thing and then do the tests

[54:36] again right like iterate like you find a

[54:37] problem fix it and then also retest

[54:39] right don't forget to retest because

[54:41] maybe you're fixant to actually address

[54:42] the problem.

[54:43] >> Mhm. Yeah. Well, I think, you know,

[54:45] something that I've realized after

[54:48] responding to YouTube comments, Q&As's

[54:50] in the community, chatting to you, and

[54:52] and just seeing what's going on when

[54:54] people are learning these kinds of tools

[54:55] is that you really at, you know, the

[54:58] simplest way to describe it, you just

[55:00] have to treat it like your best friend

[55:03] who is the smartest person in the world.

[55:06] Meaning, you know, treat it like a

[55:07] mentor. It's not going to laugh at you

[55:09] if you ask it something stupid. You just

[55:11] need to be curious and you need to ask

[55:13] >> ask the questions that you are wondering

[55:15] in your head. And I think when you kind

[55:16] of get over that idea that it can teach

[55:18] you anything and it can for the most

[55:20] part, especially if you ask it right, it

[55:22] can help you figure out the majority of

[55:24] your problems when you have, you know,

[55:26] that that sort of uneasiness because

[55:28] maybe you don't understand what it did.

[55:30] So that's like a huge mindset shift for

[55:33] anyone I've talked to that is like

[55:35] trying to get into it and doesn't

[55:36] understand it. if they, you know, maybe

[55:38] they text me a question or they drop a

[55:39] question. It's just like the response

[55:41] can a lot of times be, "Have you asked

[55:43] Claude code that?"

[55:44] >> I know. Yeah. I feel bad saying that,

[55:46] but like, yeah, it comes, it comes to

[55:48] that a lot. Um, yeah. Where it's like,

[55:50] no, you should have just usually how I

[55:53] can be more helpful is like telling them

[55:54] what to ask exactly, like give it give

[55:57] it this link, give it that thing, and

[55:58] then here's how I'd ask it. But yeah, a

[56:00] lot of times it does come down to that.

[56:02] And I mean, you can't you can't just ask

[56:04] Claude for everything because of like

[56:06] the psychic fancy you mentioned earlier.

[56:08] Sometimes if you're asking it for its

[56:09] opinion like asking a large language

[56:12] model for its opinion is a really

[56:14] slippery slope.

[56:15] >> Yeah.

[56:15] >> But but what you can what we can ask it

[56:18] for is to like understand how something

[56:21] works. Like that's when it can do a

[56:22] really good job. So, like going back to

[56:23] the example earlier, if you're not

[56:24] technical, but you want to try to

[56:26] actually be able to understand the

[56:28] automations and things that it's

[56:29] building for you, like that's a really

[56:31] good thing to ask it because it's not

[56:33] going to like there's no sick fancy

[56:34] there, right? It's not just trying to

[56:35] appease you. It's it's just helping you

[56:37] understand. The way to appease you is to

[56:39] explain the thing, right?

[56:41] >> Um, so like that that's a really good

[56:43] case just trying to understand anything.

[56:45] And then like what we were talking about

[56:46] just here with verification like trying

[56:48] to find edge cases. If there's anything

[56:49] where there's like actual empirical data

[56:51] like there is a way to verify that like

[56:53] this this automation doesn't handle this

[56:55] input well. I mean there's no room for

[56:57] sickop fancy there. It's like it it

[56:58] either works or it doesn't and there's

[57:00] not really like any kind of gray area or

[57:02] opinion.

[57:03] >> So if you think there might be an edge

[57:04] case or it thinks there might be it can

[57:06] test it and then it's it's black or

[57:08] white.

[57:09] >> Right.

[57:10] >> So I want to hear what you think about

[57:13] this because You briefly mentioned the

[57:16] agent teams earlier and

[57:18] >> I actually find myself using them quite

[57:20] a bit for mainly one specific use case

[57:22] and I want to hear what you think about

[57:24] it. So really the time when I reach for

[57:27] agent teams is when

[57:29] >> I am trying to help you know I'm trying

[57:31] to decide something but I don't want to

[57:33] just ask for cloud code's opinion like

[57:35] you just said.

[57:36] >> Yeah.

[57:36] >> And so what I'll do a lot is I'll spin

[57:38] up like a debate panel or like a war

[57:40] room.

[57:41] >> Nice. And I will say, you know, like one

[57:43] of you guys is a CEO, one is a beginner,

[57:45] one is a college student, and just like

[57:46] a bunch of different personas, sometimes

[57:48] even like seven. And I will just have

[57:50] them all do independent research, form

[57:52] their own opinions, and then I'll have

[57:53] them debate.

[57:54] >> And then I'll just be able to read the

[57:56] debate, and I'll be able to sometimes

[57:58] I'll say like, "Keep debating until you

[58:00] all come to some sort of consensus."

[58:02] >> But I do that quite a bit. And that

[58:03] doesn't mean whatever the agent team

[58:05] spits out, I do.

[58:07] >> But sometimes it's just really great for

[58:08] me to read through all those opinions.

[58:10] But I want to see do you do you like

[58:12] that? Do you think that's a major flaw?

[58:14] Like what thoughts do you have about

[58:15] that?

[58:16] >> I do actually like that. Uh I've I've

[58:18] never done that before.

[58:19] >> You've never done that? You should

[58:20] definitely No. Yeah. I feel like tonight

[58:21] I literally got to try that. It's really

[58:23] fun.

[58:23] >> Yeah. I like that idea a lot cuz some

[58:25] something that I have done

[58:26] experimentation with that's sort of

[58:28] similar. I call it adversarial

[58:30] development where basically after a

[58:33] cloud code finishes building something,

[58:36] I'll have a separate cloud code session

[58:38] u where I prompt it specifically to play

[58:40] the devil's advocate. Like I want you to

[58:42] be mean to the other CL code session to

[58:45] like really make sure that it's not just

[58:47] being happy golucky when there are

[58:48] actually some some problems that need to

[58:50] be surfaced

[58:51] >> and like that works really well. So just

[58:54] generally like pitting large language

[58:55] models against each other is a good

[58:57] idea. Um, I wish I had tried that

[59:00] before. So, yeah, I'll I'll give that a

[59:01] shot. I think that that's that's a

[59:02] really good use for Asian teams because

[59:04] at that point at that point, it's like

[59:06] you're not relying on it to getting the

[59:08] perfect answer. Like they it's very

[59:11] tokenheavy and the communication is

[59:12] never really perfect. So, that's why I

[59:14] don't really recommend agent teams when

[59:15] you're trying to do like deep

[59:16] development or like building any kinds

[59:17] of like complex automations. But, when

[59:19] it's more like research and just like

[59:21] forming a consensus, I I think that it

[59:23] does really it would do really well for

[59:24] that. I'll try it out.

[59:26] >> Cool. Yeah. Let me know if you try it

[59:28] out and what you think. But I've never

[59:30] >> really talked about that or made a video

[59:31] because I know people would go do it and

[59:33] then be like, "You just killed my 5 hour

[59:35] limit."

[59:36] >> Right. Yeah. Fortunately.

[59:38] >> So, um,

[59:38] >> how much of your limit does it use when

[59:40] you typically do it?

[59:41] >> I mean, on the 200 buck 200 bucks a

[59:44] month plan anywhere from, you know, 4%

[59:47] to to 10 sometimes. Like, you know,

[59:48] >> it's not too bad.

[59:49] >> It's not too bad. But, you know, if you

[59:51] if you say something like a

[59:53] >> don't stop until everyone agrees and

[59:54] they just keep going, then you could you

[59:56] could run into some some trouble. But

[59:59] >> to close us off here, I have to ask,

[1:00:02] >> I just did a video about my favorite

[1:00:05] features in Cloud Code. And I prefaced

[1:00:07] that whole video and basically said this

[1:00:10] is not a list of the best features or,

[1:00:12] you know, the most used or the the most

[1:00:14] useful. These are basically the way that

[1:00:16] I use Cloud Code on my day-to-day, the

[1:00:18] ones that I like the most. And I I had

[1:00:19] like a numbered list of 12 at the top.

[1:00:22] But I would love to hear from you to put

[1:00:24] you on the spot. If you had like a top

[1:00:25] three based on because I'm I'm assuming

[1:00:27] we use very differently.

[1:00:28] >> What would you say are like your top

[1:00:30] three favorites?

[1:00:32] >> Yeah. So, uh, Hooks is definitely maybe

[1:00:35] not like my favorite favorite, but

[1:00:37] probably the one that like most people

[1:00:38] wouldn't put in their top three.

[1:00:40] >> And that's because of what I've been

[1:00:41] doing with it for security and then the

[1:00:43] whole um integration with the second

[1:00:45] brain. So, it's able to basically like

[1:00:46] extract summaries and like remember

[1:00:48] things over time.

[1:00:49] >> We definitely need a hooks coal video.

[1:00:51] Yeah, I honestly I should just do that

[1:00:53] next week.

[1:00:53] >> Yeah, we definitely need it.

[1:00:54] >> Yeah. Okay. Yeah, thanks Nate. Yeah, so

[1:00:57] yeah, hooks. Hooks is definitely number

[1:00:58] one.

[1:00:59] >> Okay.

[1:00:59] >> And then uh here because I I mentioned

[1:01:02] some of the things here like I mean

[1:01:03] really when I there's kind of two

[1:01:05] different sorts of cloud code features.

[1:01:07] you have like the components of the AI

[1:01:09] layer like rule, skills, hooks and then

[1:01:10] you just have like general capabilities

[1:01:12] of the harness like um agent teams and

[1:01:16] slash by the way and and um dispatch

[1:01:19] like dynamic workflows things like that

[1:01:21] right it's either like it's something

[1:01:22] that you use or it's something that you

[1:01:24] build on top of

[1:01:26] um sub aents would be probably like

[1:01:28] number two um just because like I said

[1:01:32] there's dangers to using sub aents but

[1:01:34] just using them to like sprawl out and

[1:01:37] research a ton of different things. I

[1:01:38] use it for that all of the time and

[1:01:40] especially when I'm working on more

[1:01:41] complex code bases or building out

[1:01:43] larger automations. I'm using sub aents

[1:01:46] to basically like extract context from

[1:01:49] certain parts of my system, right? Like

[1:01:52] you're responsible for getting a

[1:01:53] grounding here of like how are we going

[1:01:54] to have to mess with the front end in

[1:01:56] this application? How are we going to

[1:01:57] have to mess with the back end? Um and

[1:01:59] then honestly probably like my number of

[1:02:02] one. So I guess like hooks would be two

[1:02:04] and sub agents would be three. Probably

[1:02:06] my my number one is skills. Even though

[1:02:08] that's like super super cliche like

[1:02:11] Yeah. It's got to be skills.

[1:02:13] >> It's just the best. Yeah.

[1:02:14] >> Yeah. Like skills. Skills dictate

[1:02:15] everything. Skill. I have a skill for

[1:02:17] making this diagram. I have a skill for

[1:02:19] scripting my YouTube videos. I have a

[1:02:20] skill for building PowerPoints.

[1:02:22] >> I have a skill for

[1:02:25] >> um I mean you could literally make

[1:02:26] >> so versatile. Yeah.

[1:02:28] >> Yeah. It's just any kind of reusable

[1:02:30] prompt. You just make it as a skill.

[1:02:32] >> Mhm. And cloud code has done a really

[1:02:34] good job continuing to evolve just like

[1:02:35] the way you can parameterize things like

[1:02:37] they have like um path scope skills now

[1:02:40] and you can like set if this one is to

[1:02:41] be invoked only by you or if the agent

[1:02:43] can decide to do it as well. Um and then

[1:02:46] like talking about like verification

[1:02:49] like getting back to here like having

[1:02:51] that browser automation skill so it

[1:02:53] knows how to use a CLI. Um, like that's

[1:02:55] a whole another thing is like the the

[1:02:56] skill plus CLI combination is just

[1:02:58] really really powerful because basically

[1:03:00] any platform or tool you want your

[1:03:02] coding agent to be able to use. It's

[1:03:04] either going to be an MCP server and

[1:03:06] like those are still good but honestly

[1:03:09] what I think is even better like more

[1:03:10] token efficient is having a CLI so it

[1:03:13] has access to your CRM or GitHub or

[1:03:16] whatever through the CLI and then the

[1:03:17] skill it tells it how to use that CLI

[1:03:20] and then more it more specifically like

[1:03:22] how you want it to use that like how do

[1:03:25] you want to this CLI to be integrated in

[1:03:27] your workflow. So like that combination

[1:03:29] I'm leaning on that for everything like

[1:03:30] my AR archon tool I was talking about

[1:03:32] earlier like it is a CLI that has a

[1:03:35] skill that comes with it. So like if you

[1:03:36] want those more deterministic workflows

[1:03:39] where you get to pick like when do we

[1:03:41] have the LLM? When are we just running

[1:03:42] code then like you build that as a

[1:03:44] workflow and then now archon with its

[1:03:47] skill and its CLI becomes a tool that my

[1:03:49] second brain can call upon whenever it

[1:03:51] wants to dispatch one of those workflows

[1:03:52] to go handle a GitHub issue or run this

[1:03:55] automation whatever it is. Very cool. I

[1:03:58] love it. Yeah, I love the list.

[1:03:59] >> My top three

[1:04:01] >> were skills was number one.

[1:04:03] >> Okay.

[1:04:03] >> Number two, I had status line.

[1:04:06] >> Oh, nice.

[1:04:07] >> I love just a quality of life thing, you

[1:04:08] know, just seeing the model, the effort,

[1:04:11] the window. I love that. And then my

[1:04:13] number three was routines.

[1:04:15] >> I love the uh the cloud routines. I I I

[1:04:18] just think it's so cool that,

[1:04:19] >> you know, I know I know we've got the

[1:04:20] SDK and whatnot, but it's just nice to

[1:04:22] be able to schedule something that

[1:04:24] >> is just my cloud code going. And

[1:04:26] >> yeah, I think those were my top three

[1:04:27] and I'm sure they'll they'll move

[1:04:28] around. But yeah, I appreciate you

[1:04:30] sharing yours. It was interesting to

[1:04:31] hear. I'm glad that Hooks made the list,

[1:04:32] so I'll definitely be keeping my eye out

[1:04:34] for that video, though.

[1:04:34] >> Sounds good. Yeah. All right. What do

[1:04:36] you use uh routines for?

[1:04:38] >> Um well, I've got one going now that is

[1:04:40] a a trading bot.

[1:04:42] >> I had that originally going with an open

[1:04:43] call agent, but I switched it over to

[1:04:45] routines just to see how

[1:04:46] >> how it would do there. Um but then other

[1:04:48] things just like it's actually doing

[1:04:50] worse there.

[1:04:52] Yeah, it's doing worse there right now,

[1:04:53] but I don't know if it's I mean the

[1:04:54] market and everything as well, but

[1:04:56] >> I think OpenClaw had just out of the box

[1:05:00] it had better

[1:05:02] memory capabilities for that sort of

[1:05:04] thing. So,

[1:05:04] >> yeah, makes sense.

[1:05:06] >> Um, but then, you know, just your other

[1:05:08] standard stuff like checking in on the

[1:05:11] team and giving me updates throughout

[1:05:12] the week and um end of week reports,

[1:05:14] just very very simple things, but

[1:05:16] >> nice to throw the routines in there. So

[1:05:19] yeah, I really appreciate you walking us

[1:05:21] through all this stuff today. Is there

[1:05:23] anything else that you want to leave

[1:05:25] everyone with?

[1:05:27] >> Uh, that's a good question. Yeah, I I I

[1:05:29] would say that no matter how technical

[1:05:31] you are, really what it comes down to is

[1:05:33] you could think of yourself like the

[1:05:35] product manager for cloud code. So you

[1:05:38] don't necessarily have to describe how

[1:05:40] to build something, but it's important

[1:05:42] for you to shape the vision, right? Like

[1:05:43] what are we going to build? And then a

[1:05:46] lot of people are calling this intent

[1:05:48] engineering now. I just kind of another

[1:05:49] buzz word of basically like you want you

[1:05:51] want to give like the why like cloud

[1:05:53] code this is why we're building this

[1:05:54] thing because that really actually it

[1:05:55] ends up shaping the how quite well. So

[1:05:57] like that's a big part of your planning

[1:05:58] process

[1:05:59] >> that's going to take you far and like it

[1:06:02] it it seems kind of silly cuz you really

[1:06:04] start to get into sort of like the

[1:06:05] personification of claude code when

[1:06:08] you're you're telling it why you're

[1:06:09] doing things but like it actually makes

[1:06:10] a difference. you kind of have to like

[1:06:12] get over yourself and be like it's kind

[1:06:14] of cringe to treat it like a person, but

[1:06:16] like that actually is how you get the

[1:06:17] best results.

[1:06:18] >> So just just do it. It actually helps a

[1:06:20] lot and good plans and good specs going

[1:06:22] into whatever you're building with

[1:06:23] claude or automating.

[1:06:25] >> Great tip. Great tip. I actually did

[1:06:27] just yesterday read in

[1:06:29] >> the Claude docs on how to prompt 4.8

[1:06:31] that it said that it said to give it the

[1:06:33] context for why you're doing something

[1:06:35] and it will probably do a better job. So

[1:06:38] >> that's awesome. Cole, where can people

[1:06:40] find you if they want to watch more of

[1:06:42] your stuff or get in touch?

[1:06:44] >> Yeah, so YouTube channel is the main

[1:06:46] place for me to put all my content. So,

[1:06:48] you can just search my name, Cole

[1:06:50] Medine. Uh, it is not spelled as you'd

[1:06:52] think. It's me d i n. Sounds like medin.

[1:06:55] Everyone says it wrong. But yeah, that's

[1:06:57] that's my YouTube channel. And then uh

[1:06:58] also doing a lot of posting on LinkedIn

[1:07:00] as well.

[1:07:02] >> Same name obviously.

[1:07:03] >> There we go. Oh yeah, I think for the

[1:07:05] first multiple months I knew you, I

[1:07:06] thought it was Cole Meen and I was

[1:07:07] saying I was saying Meden all the time,

[1:07:09] but nice.

[1:07:10] >> Good to know everyone cleared up. It's

[1:07:12] Cole Medine.

[1:07:13] >> That's right. Yeah, it's a Swedish last

[1:07:14] name. And uh yeah, Nate, there's there's

[1:07:16] people that have said it way worse than

[1:07:17] you. Like someone called me Melden uh

[1:07:20] live on stage at a chess tournament in

[1:07:22] high school. Like it's it's been worse.

[1:07:24] >> Oh man. Yeah. I don't know. A lot of

[1:07:25] people have hallucinated the L in there.

[1:07:27] I've noticed that. I'm not sure why.

[1:07:29] >> Oh, really?

[1:07:29] >> Yeah. I've had a lot of people spell it

[1:07:31] to me as Meldon or Medlin.

[1:07:34] >> Oh wow. Okay. Cuz I that was actually a

[1:07:35] onetime thing for me. That's

[1:07:36] >> I've gotten that a lot for some reason.

[1:07:37] But

[1:07:38] >> Wow.

[1:07:38] >> Anyways, yeah, thank you so much for

[1:07:40] hopping on, Cole. Um I was here to not

[1:07:44] only chat with you, but I also learned a

[1:07:46] lot as well. So, thank you so much as

[1:07:48] always. It's a pleasure to get to speak

[1:07:50] with you and hopefully we can do it

[1:07:51] again soon.

[1:07:52] >> Yeah, sounds good. I appreciate it. And

[1:07:54] thank you as well, Nate. This was

[1:07:55] awesome.

[1:07:55] >> Absolutely. I love chatting with you.

[1:07:57] >> Awesome. There we go. All right. Take it

[1:07:59] easy Cole.

[1:08:00] >> Yep.

[1:08:00] >> Have a good one.

[1:08:00] >> Thanks so much for watching today's

[1:08:02] episode. I hope that you guys enjoyed.

[1:08:03] Don't forget that I broke all of this

[1:08:05] down into a free resource guide that you

[1:08:06] can access for completely free using the

[1:08:08] link in the description to join our free

[1:08:09] school community. I'll see you guys in

[1:08:11] there. Thanks so much.