Nate Herk walks Matt Wolfe through three Claude Code builds he runs daily: an editor trained on his own best reels, a debate panel of simulated business icons, and an Instagram account that runs itself.
Posted
today
Duration
Format
Interview
educational
Views
3.2K
227 likes
57 · 43
Big Idea
The argument in one line.
AI workflows get good when you build them backward from proven work: break down examples that already succeeded, turn the patterns into reusable skills, and keep feeding every correction back in.
Who This Is For
Read if. Skip if.
READ IF YOU ARE…
You already use Claude Code and want concrete examples of skills that run real daily work, not toy demos.
You record talking-head or screen-share video and want an AI edit that matches your existing style instead of a generic one.
You make business decisions alone and want a structured way to stress-test them against several opposing viewpoints.
You run, or want to run, a news-style social account and are curious how close to fully automated it can get.
SKIP IF…
You want a click-by-click install tutorial. This is a guided tour; the setup itself lives in a public GitHub repo.
You have never opened Claude Code or a terminal. The demos assume you know what skills, sub-agents and a repo are.
TL;DR
The full version, fast.
The most useful AI workflows start from work that already succeeded. The guest trained a Claude Code editing skill by having it analyze 27 of his best human-edited reels frame by frame, then turned the patterns (scene types, pacing, captions, sound levels) into a skill that now edits raw takes to match. The same build-from-proof idea powers the Roast Room, a set of sub-agents each grounded in a real founder's public work that argue, score and vote on a decision, and an Instagram pipeline that researches, fact-checks, builds and posts AI-news carousels every four hours. The takeaway: save every piece of feedback, bake verification into the loop, and clone the public repo instead of starting from zero.
Free for members
Chat with this breakdown — free.
Sign in and you get 23 free chat messages on us — ask for the hook, quote a framework, find the exact transcript moment, generate a markdown action plan. Bring your own key when you want unlimited.
Series intro and the three builds on the menu: AI editing, the Roast Room panel, and an AI social media manager.
01:03 – 06:33
02 · Teaching AI to edit videos in your style
Why AI edits used to waste time, and the fix: have Claude Code break down 27 proven human-edited reels into a pattern bank, then turn the patterns into a skill.
06:33 – 13:50
03 · How the AI editing workflow works
The stack (Claude Code, HyperFrames, browser capture, AI video gen, Blender), the long-form YouTube variant, screenshot loops, ElevenLabs word timing and waveform-aware cuts. Where to get the skills.
13:50 – 20:37
04 · The Roast Room: build your own AI expert panel
A council of sub-agents modeled on Hormozi, Bezos, Buffett, Gary Vee and others. Each owns one question and has a researched brain folder of rules, frameworks and stories.
20:37 – 26:49
05 · Testing the Roast Room on Matt's newsletter
Live run on whether a 260K-subscriber, sponsor-funded AI newsletter survives agents reading it. Five options, three rounds of debate, a vote, and a PDF verdict.
26:49 – 36:24
06 · Automating Instagram research, content and posting
A 30-day-old AI-news account that is about 99% automated: research, fact-checking, carousel building, comment-to-DM delivery, posting, and a Google Sheet log. Live run from an X post.
36:24 – 38:09
07 · How to try Nate's workflows
Paste the public GitHub repo into your coding agent and ask it to set everything up. Series plug and sign-off.
Atomic Insights
Lines worth screenshotting.
The best starting point for any AI workflow is a golden set of proven examples, the same way production AI gets tested with evals.
Claude Code can't watch video, so the workaround is screenshotting frequently and reading the frames alongside a word-timed transcript.
An editing skill trained on 27 well-performing reels produced cuts that match the human team's fonts, pacing and scene choices.
Word-level timestamps sync graphics, but cutting on the audio waveform is what stops the edit from clipping the last syllable of a word.
Music and sound design are still where human editors clearly beat AI, and they matter more to viewers than most people think.
A useful AI editor flags gaps in the explanation, not just dead air and duplicate takes.
Each Roast Room advisor owns exactly one question, like 'will people pay, how much, and how do we close' for the Hormozi seat.
The Hormozi advisor was built from about 1.5 million words of his own videos, books and posts across 123 sources.
Running the council as sub-agents instead of an agent team cost less and gave nearly the same quality of advice.
A decision council needs explicit options to vote on, so the question has to be framed as a choice, not an open prompt.
The AI-news Instagram account reached almost 2,000 followers in 30 days with about four to five total hours of human time.
Re-checking a post's source right before publishing catches stories that were deleted or edited after the draft was made.
Logging every post to a sheet prevents duplicate topics and sets up a feedback loop where performance data can rewrite the skill.
Comment-to-DM automations that require a follow before delivering the resource turn engagement into audience growth.
Takeaway
Train every AI workflow on proven work
BUILD FROM PROOF
Each of these three systems works because it was built backward from examples that already succeeded, then sharpened with every correction and a verification step before anything ships.
02Teaching AI to edit videos in your style
Collect 20 to 30 of your own best-performing pieces and have the agent break them down before it creates anything new.
Turn the extracted patterns into a saved skill, so pacing, fonts, scene types and sound levels repeat without re-explaining them.
Save every piece of feedback into the skill; the editor only matched the human team after many rounds of corrections.
03How the AI editing workflow works
Give the agent eyes by screenshotting frames and layouts, since coding agents can read images but cannot watch video directly.
Sync graphics to word-level timestamps, then confirm each cut against the audio waveform so words never get clipped.
Ask the editor to flag explanation gaps from the viewer's side, not just to remove dead air and duplicate takes.
04The Roast Room: build your own AI expert panel
Give each advisor agent one question it owns, so the panel argues from distinct angles instead of repeating the same advice.
Ground persona agents in the person's real public work, organized into rules, frameworks, positions and stories.
Prefer cheaper sub-agents over agent teams unless the extra cost produces clearly better answers.
05Testing the Roast Room on Matt's newsletter
Frame a council question as explicit options, so the advisors have something concrete to debate, score and vote on.
Read the full debate, not just the verdict; the disagreements between seats show which risks are real.
06Automating Instagram research, content and posting
Verify every story before drafting and again right before posting, because sources get deleted or edited.
Log each published post so the system avoids duplicate topics and can later learn from performance data.
Gate comment-to-DM giveaways behind a follow to turn engagement into lasting audience growth.
07How to try Nate's workflows
Start from a public repo of working skills and ask your agent to install and adapt it instead of building from zero.
Glossary
Terms worth knowing.
Claude Code
Anthropic's command-line coding agent. It reads and writes files, runs commands and can be extended with skills and sub-agents to automate multi-step work.
Skill
A saved folder of instructions, reference files and scripts that an AI agent loads when a task matches, so it repeats a workflow the same way every time.
Sub-agent
A separate AI worker with its own instructions that a main agent can call for a focused job, then collect the answer from.
Agent team
A setup where several agents run together and talk to each other directly, instead of reporting back to one coordinating agent. Usually more expensive to run.
Golden data set
A collection of known-good examples used as the standard that an AI system's outputs are measured against.
Evals
Repeatable tests that score an AI system's outputs against expected results, used to tell whether a change made it better or worse.
LLM as a judge
Using a language model to grade the output of another model or workflow against a rubric, so quality checks can run automatically.
HyperFrames
A code-driven video composition tool an agent can use to build motion graphics and scenes without a traditional editing timeline.
Word-level timestamps
Transcription output that marks the exact start and end time of every spoken word, which lets software sync captions and graphics precisely.
Resources
Things they pointed at.
06:31toolClaude Code
06:31toolHyperFrames
06:40toolKIE.ai
06:40toolHiggsfield
07:08toolBlender
12:04toolElevenLabs speech-to-text API
12:04toolWhisper
13:18linkNate Herk's public skills GitHub repo
19:27toolGPT Image
34:13toolBoteto (multi-account posting and DM automation by Sabrina Romanoff; spelling as heard)
“It's made me a lot more productive, but it's also made me a lot lazier.”
honest tension most AI users feel→ IG reel cold open↗ Tweet quote
09:51
“It's an investment. Every time you give it feedback, it gets better.”
short, quotable principle for skills→ newsletter pull-quote↗ Tweet quote
29:53
“In total, the past 30 days, how many total hours have I spent on this? I would probably tell you four to five.”
hard number on automation payoff→ TikTok hook↗ Tweet quote
The Script
Word for word.
Read-along
Don't just watch it. Burn it in.
See every word as it's spoken — crank it to 2× and still catch all of it. The same dual-channel trick behind Amazon's Kindle + Audible.
17px
metaphoranalogy
This channel is all about finding you the coolest AI tech, tools, models, and perhaps my favorite thing, which is workflows. This video is the second in a new series that I like to call Show Me Your Workflow, where I bring guests and friends onto the channel and then I mercilessly squeeze every last drop of value that I can from them.
And by squeeze, I mean I get on a Zoom call and politely ask them questions about the cool stuff they built. And today I'm talking with Nate Hurk, one of my all -time favorite builders of cool stuff. He's going to walk you through three of his favorite AI builds that he uses every single day.
His automated AI editing workflow, his AI expert panel called the Roast Room, and his AI social media manager. And the best thing is by the end of this video, you'll be able to do all of this stuff on your own too. So Nate Hurk, show me your workflow.
Let's optimize that workflow. So it sounds like the first one we're going to get into is like the AI editing workflow, which is this is something I've been hearing a lot about from a lot of people. And I'm really, really excited to hear your take on this because I've tried to do some just like let the AI edit for me.
And I don't know, I always find that like I'm spending more time when I let it do it for me because I'm going back. And sort of fixing a lot of stuff. So I'm really, really excited to hear your editing workflow here.
Yeah, this has been something that I've been very, very surprised by in a good way, because I think when all this started, I agree with what you just said. It was just like it was frustrating because it would take more time because the rendering would take a while and then you would make a change and then it would have to re -render everything.
But once I really started to. changed the way I thought about how I was doing these editing workflows, as well as, of course, saving all of the knowledge and the feedback and building skills around it, then this has truly made me so much more productive. Like, it's pretty nuts.
Like, just this morning, for example, I had worked this in combination with some other skills that I'll talk about in a bit. but was able to just bang out like 20 reels. It did all the ideation, all the scripting.
And then I just threw it on my teleprompter, read off. The cool thing is like it grabs all the B -roll and it makes all the AI generated videos that go into it. So it's really a cool pipeline.
But I wanted to start off here before maybe we look at like some examples and stuff about how it was built. And this is kind of a wordy doc, but I just wanted to talk about. the way I think about not only this workflow, but in general, the way that I build skills and workflows that I think is really a game changer.
So it's kind of timely with the whole, you know, reverse engineer, anything repo that dropped and just went insanely viral. Oh yeah. The whole idea is that I've been trying to build skills around editing short form content for a while.
And it just was never really there. It just always felt a little cheap and AI on its own. It's not very great at thinking outside the box.
I mean, if you really think back to how it was actually like what it does, under the hood like it just predicts the next word right like at the most fundamental highest level which means that it's going off of like what most people would assume or like what makes sense so what i started to do was you know i had all of these reels that were proven now i can take this raw input where i'm speaking right like i'm just able to record even if i have mistakes in there i'm just speaking and then what i have right here side by side is the manual versus the skill now so this is like a human editor had built this and you can see this the styling is very consistent the font the way the motion come in, the shimmers, the sound effects and the music are pretty similar too.
And that is one of the areas where AI, I think still has a lot of work to do. Music and sound design. I think music and sound design is super, super underrated in the experience for a viewer.
And right now, like a human is just going to do that a lot better, but it is getting there. And I'm starting to get to this point now where my Herc edit kit is what I call it. It's saved a bunch of the sound effects I really like.
sounds that i like like music trending audios and i'm just constantly feeding in like when i would want it to use this one you know what i mean so it's definitely getting better but the point i was trying to make here is you can kind of see there's like three main scenes right there's me on the bottom with b -roll up top there is b -roll full screen and then there's me full screen and Basically, the way I was able to get to somewhere where I really liked this is I had it go do what was proven.
And so before I continue scrolling down here, I think that's just a really, really important mindset to have when you're working with AI is when you're trying to have it help you with something. The best inspiration is proven work. So like if you think about when you're deploying AI in production, what do you do is you run evals.
And your evals test against the golden data set. So essentially like, why would you not start with that kind of golden data set in mind when you're building? Because then you know what you're building towards.
So whether it be an editing flow or whether it be even just like a business decision, if you go look at an example of someone who's done exactly what you want to do successfully and has proven it, then break down how it works. how they got there. And I think that just if you zoom out and think about life in that way, like it's changed the way that I make decisions.
But so real quick, back up on the one that you were you were showing there, you've got the two videos side by side, and it looked like it was finding pretty much the same B -roll, right? Like it's the same video of Karpathy there. So the human one found the same B -roll as the skill, or did you tell the skill which B -roll to use?
Well, in this case, what happened is, you know, the human one was already made. It was already posted. It got a lot of views.
So I'm assuming that the skill here just took this clip because it knew this was like a good one. But it's more like going through and saving the principles, you know, the theories of what makes this, you know, successful, quote unquote. So I see.
OK, gotcha. In this example, it analyzed 27 of our reels that had done really well. All of these were human edited and it pretty much just watched them through like frame by frame.
Here, it's just kind of breaking down the way that it's able to look every couple seconds and understand like how often things change and how the viewer feels when you switch between this sort of B -roll. You've got like the shimmering effects and it really, it even got this granular. It started to break down when my voice and the music.
and sound effects and the difference in the audio levels. And it really, really just broke it down as granularly as it could. And it built me a bank of patterns.
And then we took those patterns, turned it into a skill and kept building on that and replicating it. So that is one example, right? So now I can drop in these raw videos and I'm able to get outputs that look like they were edited by my human team, right?
They've got the same fonts, same vibe, same pacing. my style pretty much. And obviously it's saved all this kind of stuff.
Now this is using, you're using cloud code to do this. Correct. Yeah.
Cloud code. It's using hyperframes as well on the backend. And then it will use the browser.
So it will go grab any B roll. It needs to screen record, click on things, screenshots. And then of course it will generate any AI videos it needs to with like, you know, key .ai or Higgs field or something like that.
Yeah. And I'm starting to hear more and more as well that you don't even need like. DaVinci Resolve or Premiere Pro or anything like that.
It's just does this just kind of do it all autonomously without pulling it into an editor like that? Totally. Yeah.
I've also been starting to work in. blender into some of this stuff too so now it's able to create some really cool 3d scenes for me as well with just essentially the similar idea i've never opened blender once i don't even know what the ui looks like but i just know it creates 3d scenes and then i just connect cloud code to it and then it just does it all it's it's really really absurd i've never learned blender in my life and i'm pretty much the same i've made more stuff in blender in the last three months that i ever have in my entire life that's so funny yeah it's really interesting though because you know at least me, it's made me a lot more productive, but it's also made me a lot lazier.
You know, like I no longer want to go do these manual things that I used to just be able to do just fine in a couple of minutes. But now it's like, oh, I don't want to do that. And I don't know if that's a good thing or a bad thing.
I think you could argue for both sides. But yeah, I mean, I guess, you know, the argument is maybe you're your sort of mental capacity has moved up the value chain a little bit, right? Like you are actually now more of the orchestrator thinking through the bigger picture, the bigger problems.
Yeah, I agree with that. Then I started to do another one here for YouTube videos, pretty much from when I started doing YouTube up until now. Every one of my tutorials I've just edited myself, but I figured that it would be worth a shot, right?
And for a while, one of the things I didn't like about when I would have AI edit my videos was, you know, sometimes it would leave in two takes of something or just not catch some of the things that I catch. Like sometimes when I'm recording or editing a video. I'll be like, hmm, I didn't really explain that sentence very well.
Let me actually just rerecord this real quick. I'll have the technical understanding of what's going on in order to make sure that the video makes sense. But now I've been able to work in some of that into the skill because now I make sure that it's not only transcribing things and cutting it up, but it's also thinking about the viewer's perspective and where there might be gaps.
And it's surfacing some of that stuff to me, which is pretty cool. But the main thing I wanted to focus on here was pretty much the exact same. framework, right?
Like I took multiple videos that I edited myself and now I can give cloud code my face cam recording as well as the screen recording and it will place it in this, the scene for me. And I pretty much have two scenes when I make a YouTube long form. It's this scene where you can see like my face cam.
screen and then kind of this background or just like my full screen face cam so it also understands okay when has the screen not moved for a little bit you know nate's mouse has been still and maybe nate's going on a rant or he's talking about something and that indicates for me to go to the full screen rather than just keeping you know this this view there and then of course what's really nice is it will do certain zoom ins that i wouldn't have done myself And even something as little as this, right?
Like just a little zoom in that I wouldn't want to do myself. It has the visual understanding to know that a viewer is probably going to enjoy this better because now they can read the text a little bit more. So it's not just going through and very simply cutting out mistakes or cutting out the dead space, but it's also really thinking about the experience of the viewer too.
And I think that's one of the tougher things to work into these skills. It's an investment. Every time you give it feedback, it gets better.
And then also I'm able to work in essentially sort of like LLM as a judge so that I can build up a better judge over time so that the skill does keep improving. So cloud code, obviously it's not capable really of watching videos, right? So how is it when you feed it a whole bunch of your old videos, how is it figuring out what you're doing in those old videos?
Is it just like taking screenshots at certain intervals and looking at those to figure it out? Because I think as far as I know, like Gemini is really one of the only ones that can actually watch videos right now. Yeah, that's exactly what I think as well.
I did see there's like this repo that maybe lets Cloud Code do it. But I mean, ultimately, the way I think about it is, yeah, just like. Let it screenshot basically every frame.
For YouTube videos, I didn't really make it do that. For these short form ones, I certainly did. I think the first time that I really started to do this whole screenshot loop was when I was doing a lot of web design with Cloud Code.
You know, I would give it a reference example or I would, you know, there was lots of things that were out of bounds and I would just bake in. You have to screenshot every single element. Like you scroll down, you screenshot everything and then you look at it and make sure that things are in bounds.
And then from there, I basically just. baked in screenshotting into like everything that i do whenever it's anything that you know takes a little bit of visual skill from the agent so yeah gotcha and then i'm imagining it's also using some sort of transcription api or mcp or something in the background that transcribes it so it knows where to put each animation and that sort of thing yes 100 let me actually pull this up real quick so what i just pulled up right here is i just asked it the other day to make me a video about how it edits some of my videos.
Because at the end of the day, I'm just telling it all the stuff I want. And sometimes it's like, I don't know exactly how you did that, but I like it. And it broke down.
I've got tons of different editing skills. I've got raw reels, which is more of like this style where I've got my, I just whip out my Osmo and I just record my screen, right? Or I flip it around and record me talking.
I do like motion show reels. I've got the YouTube shorts, the Instagram reels, curriculum videos. So anyways, it's just really, really cool what we're able to push out with all these skills.
You were asking about the transcription and everything like that. And this is one of the big pieces of it that I had to work in. So obviously it would listen, right?
So it would transcribe the audio. I use Eleven Labs API to do it just because it's really quick. It's super cheap too.
I mean, you could also do something free like the whisper and it's local, but it just, it's slower. So I use the Eleven Labs API and it gets the words. And what it does is it will tell you, you know, like this word played from, or you spoke this word from 0 .09 to 0 .17.
And that way you can actually sync. the motion graphics to come in exactly when the words come in. So that's very important, but then it would still sometimes clip words off like halfway through the end of like, I would say videos.
And then it would just come out as like video, like it would just cut me off. So rather than also just listening and syncing to the words, it would also look at the, I don't know what you call this, like a waveform. What is this?
Whatever this is called waveform. Yeah. And it would make sure to do it when the word's actually over by looking at when this hits like flat.
So it used to just kind of cut here, but now I made sure the skill cuts here instead. It understands pointing, right? Like it understands that if I point here to make the Claude logo go there.
And if I pointed there earlier in this video and the Grokbot logo goes there. So it's just really, really intelligent with that sort of stuff. This is awesome.
So one. Final question on this one, and then we can sort of move on to the next workflow. But if somebody wanted to sort of follow this, is there any place where they can find maybe your skills that you've already created?
Or how would somebody go and replicate what we're talking about here themselves? So I've made a few videos on my YouTube channel about all of this stuff, but I've also got a GitHub repo, which is public, and it has pretty much all of these skills inside. So you could clone that in and then just ask about...
which skills would fit your workflow and you should be able to, you know, be in a pretty nice spot with it. All right. So I know not everyone has a need for editing videos, although with it being that easy these days, I don't know why most people wouldn't start adding videos to the mix.
However, this next thing we're going to talk about is something that I think everyone can use because sometimes maybe you have an idea that you don't know if you should pursue or not. Well, this next workflow that Nate's going to show me. is called the roast room and it puts a panel of the smartest people in the world in front of you to debate about your idea all right check this out so this one is called the roast room And then I was building off these different councils and things like that.
But this is just a visual interface on top of what actually happens inside of Cloud Code. So really the idea here is that we have a council of different agents. And you're able to ask for advice on some sort of, whether it be personal or a business decision.
Most of these people are going to be giving you more business -focused advice. You pretty much just shoot in a prompt. They will all take an opening position.
They will then start to argue with each other and we can see all that happening. And then they'll vote and they'll give you basically a final option with a rundown. And then, of course, you can look through the actual debate itself and you can dig in a little deeper and maybe even do another round.
It really helps you look at it from different lenses. And especially if you start to mix and match, because I've also got some people in this roast room that aren't currently on this council and I'm adding more people to it. And then you can see there's a skill in here called.
I think it's called New Roaster. And so if you want to add your own roaster or council member, you just run this skill and then say who you want and it will create them inside of this as well. So it's going to go and like research them and figure out sort of what they're known for, what the their sort of philosophies on things are, stuff like that, and pull it in as context.
Absolutely. Yeah. And maybe before we run a demo, I can show you like what actually is inside this, because I think it's kind of cool to see like like Alex Ramosi, like what even is that?
What is he in this context? So let me pull that up. We can quickly walk through that and then we'll run an example of the roast room.
OK, so this is, again, just a GitHub repo that anyone can grab. But you can see that we've also got down here, we've got Naval, Cody Sanchez, Layla Hermosi, Sarah Blakely. And I'm probably just going to keep adding more people.
I'm surprised I don't have Elon Musk on here. Should probably have him. Should probably have like...
Elon Musk is just in there to troll everybody. You can see in here, if I go to the dot cloud, we have these different agents. So if I open up the agents, this is basically what they are.
They're sub agents and they get triggered. Now, one of the questions I get about this is... Why not an agent team?
And I actually used to run this as an agent team. The roast skill used to be an agent team, but I ended up basically finding that it was costing me more for minimal gain in the actual values providing. So I switched it back to sub -agents.
But you certainly could set this up as agent teams if you want. But anyways, let's just real quick open up Hermosi, for example. This is his markdown file, which is just a very simple subagent, right?
We can see that you hold offers, pricing, and sales. So each of the council members basically have one question that they have to weigh against, which in this case for Alex is, will people pay? How much?
And how do we close? So very, very Hermosi coded. But anyways, you can see that we have a brain, which I'll look at in a sec.
We have his lens. So the way he thinks, what he looks at, how he talks, how he debates, and things that he never does, essentially. So each of these council members is just their own agent .md file, a sub -agent file.
And they're all running the same model? They are, yes. They all run the same model and you could customize that if you want, but it just runs the default.
So if I go to the skills and we open up the roast room, you can see that there's brains, references, and scripts. Really the brains is the main one that we want to pay attention to here. So each of the agents has their own brain.
So here you can see for, who is this open? Gary V. His brain lives right here inside of the skills, inside of his Gary brain.
So I'll open up his, for example. Each of these people's brains has these different Markdown files. We have hot, which is basically his hot seat.
So the question he owns, his worldview in three sentences, and then they all basically have eight rules they decide by. So this is all pulled from real sources. So for Hermosi, for example, is one of the only ones I really remember off the top of my head.
We looked through like 123 different videos and book frameworks, articles, X posts, LinkedIn posts. And it was over like 1 .5 million words that came straight from Hermosi. And then we build all these themes.
And there's also like specific quotes. So we have this hot, we have books. So this will go through the books and different frameworks and thesis from each one.
We have frameworks, we have positions. So yeah, I think you understand the point here. It just does a bunch of research and then it organizes it in this nice way where we can look at these main concepts and even like stories.
So it'll pull in specific stories that they use. And there's a lot of data here. This is all the context.
So when you ask a question to the panel that you're asking to roast you, when they each individually respond, this is their sort of worldview, right? This is the context they have with how they're going to respond to the questions. Exactly.
Yep. They pretty much will look through all these. and apply this on top of the question that you asked.
So yeah, a hundred percent. Gotcha. Very cool.
Yeah. And then we've got the, obviously the new roaster skill right here, which basically just helps you turn any person that you want to into one of these council members. So it'll create even like the little, like the cartoon image of them.
So yeah, that's a little, a little peek under the hood of what this actually is. So I think that helps kind of, you know, before we, we jump into an example. Now with the actual visuals of this.
did cloud code code up all the visuals? Like are those graphics? Obviously cloud code doesn't have an image generator, but how was that, that created?
Yeah. So it, I'm pretty sure it used GPT image too. It's shot a request off, but obviously it used like their references.
And, um, originally some of these people did not look like how they really look at all, but now they all have the same sort of like cartoon look and you can see Hermosi's got like the classic acquisition cap and yeah. So that's all baked into the skill. And now you can add.
different council members. And it should also ask us based on the question. It should recommend like, hey, maybe these five would be best or maybe, you know, these eight.
So, Matt, I guess I'd love to put you on the spot here. What do you want to ask the roaster? Is being a YouTuber a good business model?
Yeah, I mean, we certainly can throw that out there. We have to just do one thing, though. We have to give options.
So they will actually vote on different options that we present. So just like if you have one idea, if you've got two different options you're thinking about or maybe five options you're thinking about, just kind of throwing out at least some context of what you're thinking. One thing that's been an interesting discussion internally with me and my team lately has been.
our newsletter is going to continue to be worth it in the future. So I'm trying to think of like what sort of options to give, but that is, that has been a constant narrative that's been going on internally. Cause we've got a very large newsletter.
We've got 260 ,000 subscribers for like, you know, AI news. I am a little concerned that over time, AI agents are just going to be the ones reading newsletters. There's not going to actually be human eyeballs on there.
So that's something I've been thinking about a lot lately. I'm just trying to think of what the sort of options to give would be. We could shoot off this context, right?
So Matt has an AI newsletter. It's got 260 ,000 subscribers. He is concerned about agents reading these instead of humans.
How is your newsletter being monetized? I guess that piece of context might be helpful as well. So right now it's monetized through purely sponsorships.
Okay. Well, they might be able to also create options for us and then vote on them. So I'm just going to say like, here's some context about a situation that Matt is thinking about with his team.
Could you just like turn this into a roast room prompt for us and then kick it off? So let's try that. Maybe it'll just throw together some stuff for us.
We'll see if it wants to change up the council members, but yeah, it's going to write that prompt, run the council, and then we'll get to see it in real time. It looks like they actually shut this off. And you can see that they gave us five options here.
Keep doing what works now. Rebuild for humans. Resell sponsorships on outcomes.
Design for agents. Sell agent reach. And shift effort to other channels.
So what's happening now is they're all going to go through and make their opening positions. Oh, you can also see here, it decided to take out Dan Martell and Gino and it added in Naval. Oh, interesting.
Dan surprises me a little bit. Yeah, I guess his main question here is, who does this and what does it cost the founder's calendar? That's the one that he looks to protect.
Naval is, does this build leverage and equity you own or does it just rent out your time? Yeah. Okay.
Yeah. That makes sense then. So this one, like I said, round one, they'll take their positions.
And then round two is when we actually see them like pick out who they want to. like debate with or poke holes in their plan or whatever it may be now is there actually audio on this when they speak it out or is it all just text there's not there's not someone said that i should add that and try to get their voices like a love and labs or something and have them speak that'd be pretty funny but no there is not audio it's just a weird little bobblehead looking mouth movement so but now you can see that they made their initial initial picks right so we can see that rebuild for humans is one of the main is the winner i don't exactly know what that means but i guess we'll find out but now they're going to go through and we'll see them kind of decide who they want to chat with and so will they bring in different people or is it it stays the same panel at this point at this point it'll stay these same six council members gotcha and we'll just see them sort of make connections but of course
If this local host wasn't open, this would just be running right here. You know, like obviously it'd be doing the exact same thing. It would create the same deliverables, same sort of vibe.
But this is just way more fun. Yeah, yeah. So everything's happening basically in the sort of AI chat.
The visual is just to make it a little bit more interesting and entertaining to watch. 100%. Yep.
There we go. So now we can see that Gary Vee was going after Hermosi a little bit. When they do stuff like this, if I scroll down here, we can actually watch like their opening positions.
We can watch the key points. We can see the debate. So Gary Vee versus Hermosi.
He said that he disagrees with Hermosi saying the readers are fine and the broken part is a sponsor offer price on opens. I concede here. Here are some other things.
Here's my scoring. And so we can go ahead and read all of the actual like debates and discussions that are going on. But now I just wanted to scroll back up so we can see, you know, like Paul Graham also disagreed with Hermosi.
And it looks like Bezos disagreed with. So once they feel good about this debate, they'll kind of like reset once again, and then we'll see them actually do the vote. And then maybe these scores will have changed a little bit.
Maybe they won't have changed that much, but that's what you can see next to their names. So you can actually see that everyone voted B except for Warren and Alex. They both voted C.
So are the, are multiple debates happening at the same time? Cause you're seeing all those lines between different people. So those that like they're happening, happening simultaneously.
They pretty much are just happening one after one at a time. Because then the council can look at what these other two people discussed. OK, gotcha.
So now we're going through round three. We're going to see them actually like vote, vote, vote, vote, vote. And then we'll have a little PDF that we can look at, which is a very, very high level snapshot.
But then, of course, if we wanted to dig deeper, ask more questions, run it again, even we have everything saved, obviously, in the logs. So what does the amend mean over their faces right now? It's basically just when they come through and they have voted, there's basically like one proposal.
And then they're either going to agree with that or they're going to push back. So it looks like they're all starting to come to a place of agreement. And now they're writing the verdict here.
But yeah, if we wanted to really get in here and look at every single round of debate or discussion, then it can get pretty granular in here. Nice. And how brutal are they to each other?
It looks like it's pretty cordial. Yeah, that's why we got to get Elon in the mix, right? There we go.
So we have go with B and run C beside it, which is interesting. So a summary passes along facts, not Matt's judgment. B is the only option that tests whether readers want Matt.
Pricing on opens prices on the number against agents eat. About 78K a year is at risk on assumed numbers and click terms protected at no cash cost. So we can actually open up this PDF real quick.
And that will just, like I said, it will give you the super, however, overview. So this is what that looks like. It's pretty much the exact same thing.
It'll show you the scoring, the final call. It'll show you how they got here and like a finished round scoring of all of these different options with their weights and things to watch out for. And then it kind of gives you like an action plan.
So yeah, just a super simple breakdown of what was actually discussed on the council. and then you know the probably the easiest way to set something like this up would be to go into like your cloud code point it at the github repo that you know nate made available for everybody and just say install this for me right like that's almost the easiest way to do any of this kind of stuff these days yeah literally just drop in the url set this up and then you're you should be good to go Yeah.
Awesome. We're not even done yet. Nate is a master at finding killer ways to use AI.
So I wanted to squeeze just one more idea out of him. So this time we're going to tackle social media. In fact, we're going to put Instagram on complete autopilot.
This next workflow shows you exactly how Nate is putting out high quality content on Instagram using AI and is practically hands -off technique. Check this out. So what we're looking at here is a very humble Instagram account.
I'd say this has been going for about a month. At this point, 99 % automated, maybe 98. The goal is to get this 100 % automated and then be able to monetize through sponsorships and things like that.
But really, just to have a nice automated Instagram account that's dropping news. So before I get into the workflow, we'll just give a quick overview of what actually happens here because there are some things in here that are pretty cool. So some of these obviously are just grabbing a cool video that may be trending on X.
And just kind of throwing it in here, right? We're crediting the original person and then we're just kind of ending with like a, hey, AI moves fast, so go ahead and follow, right? Like nothing too complicated.
Obviously, we had to build a skill around this so that we have a few different scenes and that everything is very branded. But what else is cool is if we look at a different one like this one, for example, the opening carousel was an AI generated image. We've got an image of Dario crying with a bunch of money.
And the idea is that I'm able to either drop in an X post that I find, right? I can just literally send Claude the link. And then it just makes a post.
So that means that it goes and it does research. It'll go to a thread. It will pull off different reactions.
It will also go like read articles and it will either create B -roll or it will go to the article. It even found this clip, right? It found a clip of Dario, threw it in here with audio.
So it's more than just making a carousel. It's automated like the backend research and thought that goes into making the carousel as well. And I'll just go through one more thing that this does.
So this one, for example, did really well. And you'll notice that it has 559 comments. And this is obviously using an automation, right?
Like a many chat type of automation, but I've automated that too. So we're giving away a resource guide and we could link people back to our community if we wanted to. I haven't done that yet here, just giving away the stuff.
But not only are they commenting for it, which helps like boost engagement and things like that, but in the DMs with these people, we're making them follow first to get the automation or to get the prompt. So they're commenting and then it says, hey, if you drop us a follow, we'll send it over. And then we shoot it over.
And so all of that's automated. And now, like I said, it's 99 % because. Every four hours it goes through, it finds a few posts and it makes some carousels and posts them.
But then I'm also still, if I see something, I'm still dropping it in and I am, you know, maybe sometimes still iterating on the prompts a little bit. Sometimes I'll see a post that I didn't like, I'll delete it, I'll shoot it back and say, hey, you know, I didn't like this piece of it, do it again, blah, blah, blah. But yeah, I mean, this really will get to a point where it is 100 % automated.
You know, this previously would have probably been a full -time role for someone to manage and run this Instagram account. And once we do get to monetize it, I will 100 % have agents that are managing the sponsorship inbox, automatically taking payments, automatically creating those posts, scheduling them out, communications.
That is going to be super, super cool. And, you know, I think that just goes to show 30 days. Almost 2K followers.
2K is not that impressive, but I think it's a lot more realistic of what is possible as long as you're iterating on the product. I'd say 2K is pretty impressive for 30 days, honestly. I mean, you know, if you told me you've been working on this for nine months and you're at 2K, that'd be one story.
But 30 days in, I think that's great for 30 days. Yeah, no, I'm pretty happy with it. Especially if you really think about, like in total, the past 30 days, how many total hours have I spent on this?
I would probably tell you four to five. Yeah, I'm pretty happy with it. Now, what I thought would be...
we could do real quick to end this episode or to end this demo would be I could go grab a quick X post and just shoot it in and we could see it run. So I guess you can see this. Here's an example I just found.
I could become self -aware. We've got a video here. And what I can do is bring this over to Claude.
And so what I always do here is, you know, you can see that I got out a different one. Now I just post it and it posted it. But then what I always do is I keep this on remote control.
and then i keep my computer awake so that if i'm like at the gym or on a walk and i see an x post i can just shoot it off but also i have this connected to like a vps version of cloud code so i can do it there as well but i basically would just say make a carousel for this shoot the link off and then when i run that it goes there it's going to read the replies it's going to you know download the video slice it up and it will pretty much just make the whole research post it might decide that there's a good resource to have people dm for it might not but obviously we can enforce that you know if we wanted that to happen every time we could enforce things like that but yes it's just pretty cool like automated pipeline now of creating these social media posts and you've got a whole skill built so when you say make a carousel for this it just goes and knows what skill to grab Yep.
And that skill has things like our brand guidelines. It has things like the way that we talk. It has assets it will save.
So sometimes if it's creating generated videos or images, it will save them too in case we want to reuse them later. And this one, it's going to, it took the clip already. You can see it's going to transcribe it.
My guess would be that it's going to cut that up and have a few like 20 second clips in the carousel of like important things that this person said in the clip. But we will see what it actually does. Here's another example of like, obviously it's taking screenshots and stuff, right?
Because when it does things like this, where it's putting this little thing behind Dario, it has to like cut out Dario, put that in there and then layer it back. And it has to make sure that it's not going to cover up his face or anything like that. And sometimes it'll just play a video here too.
it will make sure that it's spacing everything out right, that it actually makes sense. How long does this typically take to run? So once you feed it a video and say, hey, make this carousel, what would you say like the average amount of time it takes to do it is?
I would say it's probably about five minutes. Maybe this wasn't the best example because whenever it's a video, it obviously takes a little bit longer, but it doesn't take too long. And then you can also just like, I've come into a thread before and just dropped in like 10 posts that I found that I liked.
And then it will just bang all of them out. And also the desktop app. It does this cool thing now where it will suggest to open up another thread and then it will just like slot in a thread below this one.
And they're all linked. And then you can have this one main thread manage all the other ones. I don't know if you've played around with that yet, but it's pretty slick.
When you shoot off a ton of work to one thread, it'll be like, hey, you know, these are all kind of separate tasks. Let me shoot these off in like their own like parent or child sessions or something. Yeah, yeah.
That's kind of like the new projects feature in Cloud. Yes, yes. That's what it is.
Yeah. super it is pretty nice and also that's another piece that it does is it confirms everything oh nice so it makes sure that everything is real because sometimes on x there's a lot of like fake news right and then the other thing it will do is if i'm manually asking it to make a carousel when i say post it before it actually does it it will go make sure everything is still true because sometimes i've had it happen where i have it generate a carousel and then i ask it to post it And then the old post actually got deleted or edited or something else has changed.
So it does like one more sweep through, which is nice. Instagram's API is kind of rough, right? So I'm imagining it's actually opening the browser in Cloud and you're already logged into Instagram.
So it posts inside of the Cloud browser that's already logged in. Is that what's happening? Or is it going directly through the API?
Actually, this one is using for everything. I'm not familiar with that one. It's the tool that Sabrina Romanoff created, if you're familiar with Sabrina.
But I've heard her name before. Yeah. So it's a tool that she created and it allows you to have multiple accounts.
So like I told you earlier, I've got a few other things that are auto posting on X and LinkedIn and Instagram, TikTok, a bunch of different accounts. And Boteto can just manage all those accounts. And then it also she just pretty much worked in the DM automation functionality.
And that's when I was like, you know what, I'm going to I'm going to test this out on this account. So the DM automation stuff isn't actually through mini chat. It's through what do you call it?
Boteto or? Boteto. Boteto.
OK. It's the ManyChat style, but yeah, it's not through ManyChat. It's using Potato.
So you can see this one finished up. It took, I think it said a little over five minutes, like five or six. And what it does is it gives you this video so you can actually just like preview the entire carousel.
We've got the opening slide and it chose to do this tweet style. So it played a lot of the video in just one slide. So I think this is a two slide carousel and it just ended it with that.
So it was looking through to see what would be a good frame for the last picture. But yeah, then it just basically put this with these, with this caption, these systems might acquire some feeling of self -awareness. You can see, oh wait, there are three video tweet, 36 seconds.
And then another one's 36 seconds. Oh, okay. So halfway through the text switches to, we're made of the same carbon matter with our squishy brains.
And then you can see here, it's already recommending to post it. So I would just hit tab, hit enter. And you know what, I might as well just go ahead and post it.
But then it'll do a quick refresh and make sure everything's still good. And then it will just pop up on my Instagram and say that it's live. And it also logs everything on a Google Sheet.
So I can go see every single post. And that way, the reason I'm having it log everything is just so that it makes sure that it's not duplicating a topic. So I've also got that going on too.
What would be cool, and this is just thinking out loud, is if periodically it pulled in stats of how they're performing into the Google Sheet. And then it can go look back at what stuff performed and almost have like its own internal reinforcement learning of how to get better and better because it's watching the stats of what performed.
Yes, you are. You are 100 percent right. And I forget if that is automated or not, but.
Here, I'll actually just show you real quick. Okay, so I haven't set that up yet. But yeah, I've prepped it to do that so that over here you can see.
It will go through and it will start to come back and understand the stats on it. I guess it did it a weekly for some of these, but not all of them. But yeah, I do need to set up that element.
And then that'll be really cool to see how it's able to do like a weekly analytics and see if it updates its own skills a little bit based on the data it's finding. So 100%, yeah. Yeah, sort of self -improving loop.
That'd be super cool. All right, that's what we got for you today. three workflows that you can go and implement right now.
And just as a reminder, like the easiest way to go and implement these is go to the GitHub page where Nate made all of this stuff available, copy in the link to that GitHub page to your cloud code or your codex or your grokbot or whatever app you're using and say, go build this out for me. And it will just. build everything for you.
But once again, I want to thank Nate Hurk so much for jumping on with me and breaking down his workflows and going into so much detail so that I can share them with you. And you have some really cool practical use cases for AI. This is a series that I'm going to be doing more of.
This is my show me your workflow series. The last one with Bilal Sadu showed off his God's eye view. And now we got three more workflows from Nate.
If you like these types of videos, let me know in the comments and I'll make more of these show me your workflow videos. And if you haven't already, maybe consider liking this video and subscribing to this channel because that will make sure that when future versions of this pop up, they'll show up in your YouTube feed.
And if you're brand new to this channel. I also try to keep everybody super looped in with all of the AI news. Every Friday, I make a breakdown of all of the AI news that happened throughout the week so that if you don't want to have to drink from the fire hose all week and be overwhelmed by all the AI news, well, I make one video that you can check into once a week and get fully looped in for the week.
So if that's something that interests you as well. definitely subscribe to this channel and I'll make sure those show up in your YouTube feed. Thank you so much for hanging out with us today and nerding out with us.
This was a blast to do and hopefully I'll see you in the next one. Thanks so much. Bye -bye.
The Hook
The bait, then the rug-pull.
The title's claim is real and it shows up two minutes in: the guest says his pipeline ideated, scripted and edited about 20 reels that morning. The rest of the episode explains why it works, and it isn't a better prompt. It's training every skill on work that already proved itself.
Frameworks
Named ideas worth stealing.
04:15concept
Build from proven work (golden data set)
Before asking AI to do something, collect examples that already succeeded, have it break down how they work, then build the skill toward that target. Mirrors how production AI is tested against evals.
Steal forany new skill or automation: start with 10-30 winning examples, not a blank prompt
05:40list
Reel editing pattern bank
Three scenes: face-cam bottom with B-roll top, full-screen B-roll, full-screen face-cam
Consistent fonts, motion and shimmer effects
Voice vs music vs sound-effect level ratios
Change frequency every couple of seconds
The patterns extracted from 27 well-performing human-edited reels, then turned into an editing skill.
Steal forcodifying a house editing style so an agent can reproduce it
12:04list
Precision sync stack
Word-level timestamps from a transcription API
Waveform check so cuts land after a word fully ends
Pointing awareness so graphics appear where the speaker gestures
Frequent screenshots so the agent can see layout and bounds
The four mechanics that make AI motion graphics land on the exact word without clipping speech.
Steal forany caption or motion-graphics automation
Lens: how they think, talk, debate, and what they never do
Each council member is a simple sub-agent file plus a researched brain built from the person's public work.
Steal forbuilding any persona-based advisor or reviewer agent
21:50list
Council decision flow
Frame the decision as explicit options
Pick the best-fit council for the question
Round 1: opening positions
Round 2: one-on-one debates, run in sequence
Round 3: vote and amend
Verdict PDF with scores, risks and an action plan
How the Roast Room turns one question into a scored, debated recommendation.
Steal forpressure-testing pricing, positioning or channel decisions
27:20list
Automated carousel pipeline
Input: an X post link, or a scheduled sweep every four hours
Research replies, articles and source clips
Verify the story is real
Build branded carousel with generated or clipped media
Re-check the source right before posting
Post, run comment-to-DM, log to a sheet
The end-to-end flow behind a news account that runs with almost no human time.
Steal forany curated news or commentary account
CTA Breakdown
How they asked for the click.
VERBAL ASK
36:00subscribe
“If you like these types of videos, let me know in the comments and I'll make more of these show me your workflow videos. And if you haven't already, maybe consider liking this video and subscribing to this channel.”
Soft, earned close after a recap that tells viewers to paste the repo into their agent. Pairs the subscribe ask with a weekly Friday AI news roundup as the reason to stay.
Add Modern Creator as a preferred source and Google shows you more of our breakdowns in Search, Top Stories, and AI Overviews. It only changes what you see, and you can undo it in your Google settings anytime.
Add to Preferred SourcesOpens your Google source preferences with us pre-loaded. Tick the box and you're done.
A first-look review of OpenAI's GPT-6 Astra, run through published benchmarks, a set of repeatable creative tests, and a computer-use experiment where the model built and animated its own 3D game world.
A creator prompts OpenAI's Codex into building a free, self-hosted dashboard that replaces a stack of SaaS tools for news, mentions, newsletters, and audience tracking.
Matt Wolfe opens the full toolbox behind his own YouTube intros — every AI app, model, and exact prompt, from wall-bursting entrances to a fully AI-dramatized Sam Altman text leak.
A 31-minute weekly roundup covering Claude Fable 5's censorship backlash, Apple's Siri reboot, Google's NotebookLM overhaul, and a rapid-fire batch of industry moves.
00:37
01:33
02:45
02:54
03:20
04:04
04:19
04:53
05:28
06:15
07:23
08:05
08:12
08:51
09:13
09:44
10:06
10:42
11:26
11:41
12:40
13:03
13:37
13:50
15:05
15:26
15:52
16:18
16:55
17:24
18:03
18:17
18:39
19:18
20:02
20:36
21:41
22:10
22:32
23:07
23:36
24:13
24:29
25:02
25:30
26:26
26:49
28:27
28:51
29:13
29:34
30:09
30:49
31:24
31:41
32:00
32:32
33:21
33:37
34:33
35:03
35:32
36:01
37:11
37:54
19:32
27:37
29:37
31:47
30:51
20:45