The argument in one line.
Agentic workflows earn premium fees not because the build is hard but because they eliminate a specific business constraint, and the practitioner who can identify that constraint and price against its value will always outcompete one who prices by the hour.
Read if. Skip if.
READ IF YOU ARE…
- You already understand how traditional automations work in n8n or Zapier and want to see how Claude Code changes the build process.
- You are freelancing or consulting in AI automation and want a concrete framework for charging on value rather than hourly rates.
- You want a live walkthrough of building a multi-tool agentic system — from plan mode through debugging to a real email output.
- You are evaluating whether to add Claude Code to an existing automation practice.
SKIP IF…
- You have never touched an automation tool before — the video assumes familiarity with webhooks and APIs as baseline context.
- You are looking for a deep dive into a single tool like n8n or Zapier — this is specifically a Claude Code tutorial.
- You want production-ready code to copy — the build shown is an intentional first-pass demonstration, not a hardened template.
The full version, fast.
The agentic AI market is growing fast, and the gap between traditional automation and agentic systems comes down to one thing: an agent handles edge cases during the build phase, so the deployed code is more reliable from day one. The WAT framework (Workflows as markdown recipes, the Agent as executor, Tools as Python scripts) gives Claude Code a structured context for building complex automations from a single natural-language prompt. Once the system is running, pricing it on the value it delivers — hours saved, errors eliminated, revenue enabled — is what separates a $500 freelance job from a $10,000 engagement that becomes a long-term retainer.
Members feature
Chat with this breakdown.
Modern Creator members can chat with any breakdown — ask for the hook, quote a framework, find the exact transcript moment. Unlocks at T2: refer 3 friends + add your own API key.
Create a free account →Where the time goes.
00:00 – 00:38
01 · Intro — why now
Market-size hook, three-part agenda stated.
00:38 – 01:15
02 · Big money moving in
$8B today to $40-50B by 2030; 25% to 50% enterprise adoption by 2027.
01:15 – 03:50
03 · Why traditional automations break
Ceiling of rule-based systems; train-track analogy for the build-phase advantage.
03:50 – 04:28
04 · Why the basics still matter
n8n/Zapier fundamentals prevent blind spots when reviewing agent output.
04:28 – 07:18
05 · Claude Code setup
VS Code install, Claude Code extension, paid plan requirement, opening a project folder.
07:18 – 10:09
06 · WAT framework explained
Workflows as recipes, Tools as ingredients, Agent as the cook; Claude.md as standing system prompt.
10:09 – 20:56
07 · Live build — newsletter automation
Plan mode, clarifying questions, brand assets tagged, five tools generated, API keys added, first run with self-correction, final branded email delivered.
20:56 – 22:17
08 · Skills concept
Reusable system prompts the agent loads on demand; how to create your own.
22:17 – 24:55
09 · How to sell it
Doctor-not-pharmacist positioning, value-based pricing, $3K build to $50K/yr relationship, client retention through metric ownership.
Lines worth screenshotting.
- Agentic self-healing only works while the agent is actively running — once deployed to a schedule or webhook, the code behaves like traditional automation.
- The WAT framework separates concerns: Workflows are markdown instructions, Tools are Python scripts, and the Agent reads both to execute tasks without needing every step hardcoded.
- Claude.md functions as a project-scoped system prompt that loads before every message, giving the agent persistent context across a session.
- Plan mode forces the agent to ask clarifying questions before writing any code — one round of questions at the start prevents multiple debugging rounds at the end.
- Battle-testing an agentic workflow before deployment is the analogy to running ten different train types over a track before opening the line.
- Traditional automation breaks on unexpected inputs; agentic builds handle edge cases during construction, so the deployed version starts more robust.
- Skills are reusable system prompts the agent loads on demand — they let you encode hard-won knowledge about a specific task into a portable, callable artifact.
- Competing on the ability to build AI automations is a race to the bottom; competing on diagnosing the right problem to solve is not.
- The doctor-not-pharmacist framing means leading every client conversation with diagnostics, not demos — find the clog before adding more water to the pipe.
- Hourly pricing caps income at the time spent; value-based pricing ties the fee to the business outcome, which can be an order of magnitude larger for the same build.
- A $5,000 fee for a system that saves $10,000 a month is a two-week payback — framing the pitch that way makes the decision trivial for the client.
- Retaining clients after delivery requires the builder to own the metrics — if you do not track and report the ROI, the relationship ends at delivery.
- A $3,000 first build can become a $50,000 annual relationship once the client sees measurable results and wants the system expanded.
- Claude Code makes agentic workflow construction accessible without writing API calls by hand — the framework handles orchestration, the practitioner handles problem definition.
The build is table stakes. The diagnosis is the product.
WHAT TO LEARN
As Claude Code lowers the cost of building agentic systems toward zero, the practitioners who will earn premium fees are those who can identify which problem is actually worth solving — and prove it after delivery.
01Intro — why now
- Market-size claims ($7B to $93B) are a framing device, not an argument — the useful signal is the 25% to 50% enterprise adoption projection, which implies budget is real and flowing now.
02Big money moving in
- Enterprise adoption timelines (25% in 2025, 50% by 2027) suggest a two-year window before agentic workflow skills become expected rather than premium.
03Why traditional automations break
- Agentic self-healing is real during the active build phase, but once code is deployed to a schedule or webhook, it behaves like traditional automation — plan accordingly and battle-test before handing off.
- The train-track analogy captures the core advantage: a construction crew handles edge cases during the build so the deployed track starts in better shape than one laid rail by rail.
04Why the basics still matter
- Traditional automation fundamentals are not made obsolete by Claude Code — understanding webhooks, APIs, and data flow lets you catch agent mistakes that a beginner would miss entirely.
05Claude Code setup
- The Claude.md file functions as a standing system prompt for a project; every capability or constraint you put there persists across the session without re-stating it in every message.
- A paid Claude subscription is required for Claude Code access — the Pro plan at $17 per month is the entry point, with Max recommended for heavy build sessions.
06WAT framework explained
- The WAT framework separates three concerns that beginners conflate: the recipe (Workflow), the cook (Agent), and the ingredients (Tools) — keeping them separate makes each component auditable and reusable.
- Workflows are plain markdown — readable by any human without code knowledge — which means non-technical clients can review and approve the process logic before any code runs.
07Live build — newsletter automation
- Plan mode before any live build surfaces ambiguity early — one round of clarifying questions at the start prevents multiple debug rounds at the end.
- The agent self-corrected two errors (a Unicode encoding issue and a wrong API endpoint) without human intervention — demonstrating the build-phase advantage in real time.
- Deploying an agentic system means pushing the Workflows and Tools, not the Agent — the model does not run in production, the code does, which is why battle-testing matters.
08Skills concept
- Skills are reusable knowledge artifacts: instead of re-explaining a style preference or a tool's quirks each session, encode it once in a skill file and let the agent load it on demand.
09How to sell it
- Competing on the ability to build automations is already a commodity argument; the defensible position is the ability to diagnose which automation actually moves the needle for a specific business.
- Value-based pricing requires knowing the business outcome before quoting a number — if the system saves $10K a month, a $5K fee is a two-week payback, which reframes the cost as an obvious investment.
- Retention after delivery depends on tracking and reporting the ROI yourself — clients do not naturally connect the running system to the value it creates unless someone is doing the accounting.
Terms worth knowing.
- WAT Framework
- A Claude Code project structure dividing an agentic system into three layers: Workflows (markdown instruction files), the Agent (Claude Code itself), and Tools (Python scripts the agent can call). Workflows act as recipes; Tools are the ingredients; the Agent executes the recipe using the ingredients.
- Claude.md
- A markdown file placed at the root of a Claude Code project that functions as a persistent system prompt. It loads before every message in the session, giving the agent standing context about folder structure, goals, and constraints.
- Plan mode
- A Claude Code operating mode where the agent produces a detailed plan and asks clarifying questions before executing any changes. Used to align on scope before any code is written.
- Bypass permissions mode
- A Claude Code setting that allows the agent to make file edits and run tools without pausing to ask for approval on each action. Intended for trusted build sessions where the user wants continuous execution.
- Agentic workflow
- A multi-step automated process where an AI agent reasons about how to proceed, selects and calls tools, handles mid-run errors, and completes a goal without requiring a human to map out every node in advance.
- Value-based pricing
- A pricing model where the fee is set as a fraction of the measurable business value the system delivers — hours saved, errors eliminated, or revenue generated — rather than the time it took to build.
- Skills (Claude Code)
- Reusable system prompt files that Claude Code loads on demand when a task matches their domain. They encode specialized knowledge or style guidelines into a portable artifact the agent can invoke without being retrained.
Things they pointed at.
Lines you could clip.
03:00
“Traditional automation is like building a train track by hand. Agentic workflows are like telling a construction crew where to go and letting them figure out the problems.”
22:25
“If you're trying to compete on 'I can build AI automations,' you're going to be in a race to the bottom.”
22:55
“A pharmacist just fills a prescription that someone else wrote. A doctor sits down with the patient and figures out what's actually wrong.”
23:50
“That's how a $3,000 build turns into a $50,000-a-year relationship.”
Word for word.
metaphoranalogy
00:00AgenTic workflows are not just a trend. They're the future of the AI industry. More and more companies are making the shift to AgenTic workflows, and this is just getting started because it's estimated that the AI AgenTic market is going from about $7,000,000,000 this year to around 93,000,000,000 in the next couple of years.
00:13I can tell you right now that knowing how to build agentic workflows is going to be one of the most valuable skills that you can have. So in this video, I'm gonna break down why you should be building agentic workflows, and then I'm gonna actually build one live in front of you so you can see exactly how it And by the end, I'll show you how to actually sell these if you want to make some money with your skills.
00:30So let's get into it. So before we build anything, I wanna show you why this all matters, because it's not just hype. This is real money moving into real technology.
00:37Right now, the agentic AI market is sitting at around $8,000,000,000. By 2030, that's expected to hit 40 to 50,000,000,000. That's not just a small jump.
00:43That's an entire industry being built in front of our eyes. And it's not just projections. About 25% of enterprises are already deploying AgenTic pilots this year, and by 2027, that number will jump to 50%.
00:53So half of major companies will be running some version of Agentic workflows within the next two years. And with that comes massive budget allocations, new security requirements, and a ton of new opportunities for people who know how to build these systems. So why is this happening now?
01:05What's driving the shift? It comes down to pretty much one thing, which is companies are starting to hit that ceiling of what traditional automation can do, and they're starting to realize they could move a lot faster with more agentic workflows. If you've been building workflows in tools like Noden or Zapier, you know the drill.
01:18You map out every step, you connect the different nodes or blocks, you handle the edge cases yourself, and it works until it breaks. Because traditional workflows will break when they hit something unexpected. And when that happens, someone has to usually go in manually and fix that.
01:29And that's maintenance. That's time. That's ultimately money.
01:32Now I do wanna be real with you here because there's a lot of noise online workflows that makes it sound like they're just completely magic and they fix themselves forever. And that is partially true, but only in a specific context, at least right now.
01:42Because when you're actively working in a tool like Cloud Code and you trigger a workflow yourself and say, hey, go research these competitors and build me a report, the agent is sitting right there with you. So if something breaks, the agent can catch it mid run. It can adjust its approach.
01:53It can update its tools and keep going. That self healing piece is very, very real, and it's incredibly powerful while you're building and while you're iterating. But once you deploy that workflow to run on its own, on a schedule, or triggered by a webhook or something like that, that is when you're deploying the code, you're deploying the tools, not the actual agent itself.
02:10So if you've seen my previous videos where we've used the WAT framework, we are basically deploying the W workflows and the T tools, but not the a agent. But I'll cover this more in-depth later during the live build if you're confused. What this means is that the self healing ability ultimately goes away when the code is up in the cloud, you know, running automatically.
02:27And at that point, it does behave more like a traditional automation, but that's really a good thing because automations are predictable, they're deterministic, and those types are the best ones. So then where's the real advantage? Really, sits in how you build.
02:37Traditional automation is like building a train track by hand. You're laying every rail, every switch, every connection all by yourself. Whereas with agentic workflows, it's like you're just telling a construction crew, hey.
02:46I need you to build a train track from here to there, and then they build it for you. Meaning, if they hit a problem during construction, they would figure it out. So you end up with a better train track, it's built faster with fewer mistakes because the agent handled the edge cases during the build process that you might have missed or not thought of.
03:00And then the idea is you battle test it before you ever actually deploy it, then so you have a lot of confidence that it will always work. So in our train analogy, before we deploy that train track, we would have like 10 different types of trains test drive on it. They would be different weights, different lengths, and maybe different wheels.
03:14And we'd wanna make sure that our track can work for for all different types of trains before we deploy it. And the reason this is actually possible now is because the technology has finally caught up. LLMs have gotten really reliable enough to use in production, and we're not just playing around with chatbots anymore.
03:26These models can reason, they can make decisions, and they can execute multistep tasks with real consistency. On top of that, we've got things to use like skills or MCP or a to a. We've also got infrastructure like trigger dot dev, modal, or Vercel that make deployment way simpler than it used to be.
03:40And most importantly, we've got tools like Cloud Code that make all of this accessible to nondevelopers. So we can see that the market is absolutely shifting towards agentic systems and the numbers back it up. But here's a question that's probably on your mind.
03:51Does this mean everything that I've learned about n to n or traditional automation is useless? Not even close. And let me explain why.
03:57The people who are going to struggle with agentic workflows are the ones who completely skip those fundamentals and jump straight into Cloud Code, tell to build something, and have no idea if what is being built is actually good. They probably don't know what a webhook is or how APIs work. They won't be able to spot when the agent made a bad decision because they've never built a thing manually themselves.
04:13That's not to say that a beginner can't learn Cloud Code. And because you actually understand how automations work under the hood, you can communicate precisely what you want much clearer. And you'll see once we hop into the live build just how important it is to actually be able to communicate really clearly.
04:25Alright. So now you understand why agentic workflows are such a big deal. Now I'm gonna show you how simple it is to build an agentic workflow using Cloud Code.
04:32And by the way, if you want to follow along with what I'm about to build, you can grab all the resources and files that you need completely for free in my free school community. The link for that is down in the description. Alright.
04:41So we're now in Visual Studio Code, which is where we're going to actually use Cloud Code. Visual Studio Code is just an IDE or an integrated development environment, and that's where, like I said, we're gonna be using Cloud Code. So if you don't have this up and running yet, all you have do is go to a browser and type in Visual Studio Code and download the right one for your operating system.
04:57And then once you open that up, it should look like this. First thing you have to do is install the Cloud Code extension. So you're gonna go over here to the left hand side.
05:04You're going to open up extensions, and then you will see right here Cloud Code. Or if you don't, you will search Cloud Code. And once you pull that open, it'll ask you to install it.
05:11And then once you do, it'll basically just prompt you to sign in with your Cloud subscription. Now you do have to be on a paid plan for Cloud in order to access Cloud Code. As you can see on the free version, you don't get Claude code, but right here on the paid version, you do.
05:23So you can start off with the pro plan at $17 a month, and then if you need to, if you keep hitting limits, you can upgrade to max, which honestly, you probably will. I'm on the max plan, and it is an amazing return on my investment. So I would just go with the max.
05:35But anyways, you'll get authenticated, and then it will bring you back here. And now we can actually get going using Cloud Code and building workflows. So I'm gonna close out of this screen, and what we're gonna do now is we're gonna open up a project.
05:45So on this left hand side, I'm gonna go up here to explore, and this says, you have not yet opened a folder, open a folder. So essentially, when we're in Cloud Code, we're going to be working within a certain folder, and that's kind of the way that I think of, like, this is the project that we're working on. So I'm gonna click open folder, and I'm gonna open up a blank project.
05:59So So you can see I'm in a folder called newsletters demo, and there's nothing in it. It's completely fresh. I'm gonna click select folder, and now we can see we're in this project.
06:07I'm real quick just gonna close out of this and close out of this just so we have a really clean interface to look at with not much going on, and I can explain what we're actually about to do. So to make this as simple as possible, in Cloud Code, we have an agent, and we have files. That's it.
06:19The left hand side is where we see those files. We'll see different workflows. We'll see tools.
06:22We'll see all these little things. And then on the right hand side, we'll have the Cloud Code agent, and that's where we talk to it, we plan with it, it asks us questions, and it actually executes and writes the code or builds the workflow for us. So if I switch back into Visual Studio Code and I double click right here, and then I open up this button that says Claude Code, this is where we actually open up the actual Claude Code agent right there.
06:40So I'll close out of this. You can see this is kind of what we're talking about now. Files on this side, there's nothing there yet, and the Claude Code agent right here.
06:45Now what we have to do next is give Claude Code a Claude dot m d file, which is basically just instructions for this specific project. And you can really just think of this as a system prompt. So that way, when we, the user, send a message to our ClawedCode agent, it doesn't just process what we said and respond to us, but it also, every time, reads the Clawed.
07:01Nb file. So this is where you're gonna put important things like how the folders are laid out, know, where to find your different files, what its end goal is, any frameworks that you might be using. So in this case, what we're gonna be doing is we're gonna be using a framework called WAT, which stands for workflows, agent, and tools.
07:15So real quick, if you pop over to my free community and you go to the classroom and then you click on Claude code, right here you'll see the WAT Claude dot m d. You can go ahead and download this file right here. And once you've downloaded that file, you can actually just drag it over here to the left hand side, and it should pop up as Claude dot m d.
07:29And if you wanted to, you could read through this entire, basically, system prompt to see what I'm telling it about how to build workflows, how to build tools, how to keep learning, and how to, you know, set up its its folders and everything, but I'm not gonna read that all out right now. What I'm gonna do is just basically tell Claude code to set up the project.
07:45Read the Claude dot m d file, and then set up the project and their structure, and then we'll start building workflows together. So I'm basically just gonna shoot that off, and it's gonna go ahead and read that and get everything ready. So we'll see soon on the left hand side, we've got all our different folders set up.
07:57But while it's going through and doing that, let me just explain what these different things are. So agent, that is the actual Cloud Code agent that we just talked to, as you saw. And the agent utilizes workflows and tools to help us automate things.
08:08So the first thing is workflows. These are markdown files, which you just saw similar to the Cloud. Md, and it looks like this.
08:14It's basically completely natural language. You could read through every line and understand exactly what's going on. It just uses things like pound signs and, you know, dashes and asterisks to separate, like, what's a header and what's bold to stress importance for the agent.
08:28Workflows are natural language processes, instructions. So right now, let's just use an analogy of a recipe.
08:34The workflow is the recipe, so you'd have a workflow for how to bake a chocolate cake. And when you wanna bake that chocolate cake, it's gonna tell you what to do in certain order. So it's gonna say preheat the oven to this, boil some water, I don't know why you boil water for a cake, crack two eggs in a bowl, you know, measure out a cup of flour, whatever it is.
08:49And those are the tools. So the tools are all of the ingredients, but without the structure of the workflow saying use tool one, then tool five, then tool seven, then tool 10, without the order and the structure, the tools are useless. So basically, the workflows tell the agent how to build the tools.
09:02And what's really cool about both of these is as they're being built and as they're being used, the agent will improve them over time if it makes mistakes or if it learns things. So that is why we use the WAT framework to build our workflows with ClockCode. So now that that's done, you can see that this is finished up, and it's basically said, okay, the project is set up.
09:17Here's a summary of the structure. Here's what I understand. We're going to be building workflows in this project, likely around newsletter operations.
09:23WAT framework, I will act as the agent. I will read workflows. I will run tools.
09:27I will handle errors and improve the system. I've got Python ready to go, and I'm gonna store secrets in the dot ENV. So this is where we're gonna put our API keys rather than putting them straight into Claude so that they could be exposed who knows where.
09:38Okay. So what I'm gonna do is go ahead and do a slash clear just to get rid of this conversation, and we can start fresh, and we're gonna start to plan out this workflow that we wanna build. Before we start planning, I'm gonna switch this to plan mode.
09:49So you can see we're in bypass permissions, you can go to ask before edits, you can go to edit automatically, but I wanna go to plan mode. And it's really, important, as we talked about earlier, to be able to communicate clearly what you want. And the cool thing about Cloud Code is when we give it a plan, even if it's pretty ambiguous, it will come back and say, okay, in order for this to be good, I need to know x, y, and z.
10:05So I'm gonna give it a fairly ambiguous prompt here, and then you're gonna see it ask us questions and plan out this workflow for us. Hey, Claude. I want to build a workflow, which will basically automation.
10:15I want to be able to tell you that I need a newsletter about a certain topic, and you will do research. You will structure it in HTML. You will make it look pretty, and you will also create a few infographics to go with it.
10:26So help me figure out what text stack to use here and what else you might suggest that I haven't yet thought of. So I'm gonna shoot that off. Now whether we're in plan mode or, you know, bypass permissions, what happens is the agent starts thinking and it starts testing things out.
10:38So it's thinking, it's reading through files. It has this little thing that will say computing or deciphering or wobbling or whatever it is, just a bunch of little silly words. But that just basically shows you exactly what it's doing.
10:48Alright. So we're just at the point where it's asking us some questions before it continues working on the plan. The first thing is, for research, do you want to add an external search API to pull in data?
10:56So what I'm gonna do is say, yeah, sure, let's just go ahead and do Perplexity. For delivery, it asks us if we wanna use Beehive or if we just wanna send the HTML file for now. I'm actually just gonna go ahead and say, let's actually just send this over in Gmail.
11:08And now it asks us about brand assets, which is really cool. So if we want to, we can send over some brand guidelines or logos and stuff like to make sure that the newsletters are always formatted and they feel on brand. So I'm gonna go ahead and say, yes, I will provide some brand assets.
11:22So then what happens is it comes back with a final plan. Let me just zoom out a little bit so we can actually see that a little bit better. We'll go ahead and see what it came up with.
11:28So newsletter automation workflow, we want to conduct research, generate HTML with polished visual design, create infographics to accompany the content. We've got a research layer. We've got the content generation.
11:38We've the infographics, so it says that it could use data stats infographics or it could use SVG.
11:44Why not image generation? It's too unpredictable. It can't embed.
11:47I'm actually gonna go ahead and say that I wanted to use Nano Banana. So I'm gonna go ahead and type in here. For the infographics, I want you to generate AI images using Nano Banana.
11:55You can use a platform called key.ai. So this just shows the importance of plan mode and reading through the plan, so that you can make sure before it actually starts building everything, you like what it's going to do. Okay.
12:04So now that new plan has been done, you can see the tech stack is gonna be researched with Perplexity, the content will be written with Claude. The infographics will be created with Nano Banana. We will write the email in HTML and then send that via Gmail.
12:16And it even comes up with a section here about things the user likely hasn't considered. So things like human review, subject line, metadata, brand consistency, all this type of stuff. Now the last thing that I actually forgot to give it was my brand assets.
12:28So what I'm gonna do real quick before we accept or, you know, keep working on the plan, I'm gonna create a new folder over here. I'm gonna call this brand underscore assets, and you can see I dragged in two things.
12:37I dragged in AIS PNG, which is our logo, and I dragged in our brand guidelines. So I want the newsletter to be formatted in this way. So I'm gonna click on no key planning, and I'm going to tell Claude that it needs to use those two assets.
12:49So what's cool is that I can actually directly tag them. So I'm saying make sure the whole newsletter is branded based on my logo and brand guidelines. So for logo, I'm gonna do at, and I'm gonna type in AIS, and you can see that it's gonna show AIS PNG.
12:59And then here I can do at AIS, and I'm gonna click on brand guidelines. So now, it's going to look at those exact two things, and it's going to be able to make sure that the newsletter is branded. Okay.
13:08So this time the plan looks good to go, and I'm just gonna go ahead and auto accept, and I'm gonna turn on bypass permissions. So it's gonna build everything out. It's going to put the different files that we need, and then we should be able to basically just add our API keys and then test it.
13:19So what it's doing now is it creates a to do list. So this is all of the things that it has to do, and as it actually completes them, it crosses them out. So it's really cool because you can work on something else on a different screen and just kind of check-in on Claude code to see where it's at and if it needs any help.
13:32Now you guys may be wondering about this bypass permissions mode. If you don't see this, you just have to go to your settings. In your settings, search for Claude code, and then right here, you'll be able to see allow dangerously skip permissions, which turns on allow bypass permissions mode.
13:45Okay. So that is finished up. It's telling us here's what it built.
13:48So it created two config files, which we can see right here. It's got newsletter style, which basically just shows like the colors and the text in the background, and it's got recipients, which is where we need to add who this is actually being sent to. So this is where we would add a huge list of, you know, our email list, basically.
14:01Then it created one, two, three, four, five different tools, I open up those right here. The tools are research, generate infographic, assemble HTML, send via Gmail, and archive the sheets. And here is what all of those five tools do.
14:13And then, of course, we have the actual workflow right here, which is our markdown file, which basically shows step by step how to actually build the newsletter and what tools to use. And this is the complete natural language just explaining the process. So now that those have all been created, the last thing that we have to do before we actually test it out is we have to give it credentials.
14:29So Anthropic, Perplexity, key.ai, and then our Gmail. So what I'd do is I'd go to Perplexity, grab my API key, I would come into the dot env, and then over here, it's created these placeholders.
14:38So all that I have to do is paste in my API key right there and then hit save to make sure that all of this saves. So I'm gonna go ahead and do this now for my other API keys. Okay.
14:45So we've done everything that it told us to do. We've set up all our credentials, at least I hope we have. If we run into any errors, Cloud Code should fix it or tell us what to do.
14:52What I'm gonna do now is just kick off a prompt. Write me a newsletter about AgenTic AI. So I literally just said, write me a newsletter about AgenTic AI, and that's it.
15:01What it's doing now is it's looking through the relevant workflows and tools, and it's gonna figure out what to do. Here you can see it said, I found the newsletter workflow. Starting with step one, I'm gonna do some research.
15:09You can see after that, it's gonna plan and generate the infographics. It's gonna write the newsletter content, and then we actually have a human review point. So it's going to get subject line approval, and then if it's approved, it'll go ahead and send the newsletter.
15:20So now your job at this point is just to watch it and to make sure it's doing everything right. And if it runs into issues, it should fix itself, but sometimes it may need you to help steer it in the right direction. The first test run is the only one where it's really like this because you have to see how it works.
15:31But then after that, you should be able to just trust that it's gonna run pretty much perfectly every time. Here you can see we've already run into our first issue. There was a Unicode encoding issue, but it's just gonna go ahead and fix it.
15:40And that's great because I don't really know what this means at all, so I'm glad that it understands what to do. Nice. So you can see it planned out three infographics.
15:46It's got a market growth. It's got Gartner roadmap, and it's got impact metrics. So here's a good example.
15:51It was trying to generate those infographics using key.ai, and it was getting an error. So what it did is it looked into the problem.
15:58It said, let me investigate to find the correct endpoint. It did some web searching, it looked through the docs, it did multiple searches as you can see, and it figured out that the endpoints have changed, and now it's able to switch the tool so that it works this time. There we go.
16:09So it said I found the fix. Here's the right endpoint. Let me update the tool so that this doesn't happen again, and now it just went ahead and fixed the tool.
16:15Alright. At this point, it did a human review step, and we could obviously say we don't want this if we don't want it. But But for now, let's just go ahead and see what it wants.
16:21It wants us to approve a subject line. It asks us to choose which one. I'll go ahead and send five, and then we will see the final output.
16:28Okay. So a few things happened, and I'm actually glad they did so I can show you how you need to troubleshoot this. The first thing is we got the email, but the HTML is all messed up.
16:35It came through with a background color, but then all of this just is horrible. So we're gonna have it fix this. The second thing is I gave it the wrong Google Sheet ID to archive to Sheets because there was some sort of access issue.
16:44So I'm gonna go ahead and fix that Sheet ID, and I'm just gonna use my natural language to tell it that this is horrible. I've updated the Sheet ID. However, the actual email that I received is completely awful.
16:55I can't read any of it. It doesn't even make any sense. Take a look and figure out what happened, and try to send me it again.
17:00So it's gonna go ahead and diagnose what happened, and then hopefully send us a better version. So once again, it found the issue. It found out exactly how to fix it, and now it's updating the workflow and the tool so it doesn't happen again.
17:10Now, of course, Cloud Code's not perfect. You guys can see that in this demo. But think about if you were doing this in something else like NNN or something that's a bit more manual, and you were running into these issues, and you'd have to go back and fix all of the logic yourself and try to debug all this.
17:21I've literally just been telling it to fix it, and then, like, doing other work or going in the other room and waiting for it to figure it out on its own. Okay. Now it fixed everything, and if I go over to my email, we see this newsletter.
17:30What happens when AI stops waiting for instructions? We can see that we've got our logo up top. We've got AIS intelligence brief.
17:36It does think that it's June 2026, which is wrong, but we could obviously fix that very easily. But now we move into the actual newsletter. And keep in mind, this started with one prompt that said, write me a newsletter about AgenTek AI.
17:46That was it. Also, throughout the newsletter, pay attention to the fact that it's using our fonts, it's using our brand guidelines, our colors, all of that in this newsletter. So the first section is about the market landscape, an explosion that cannot be ignored.
17:56I'm not gonna go ahead and read all of this text. It would just take too long. A nano banana AI generated image with text, with graphics, and this infographic is also adhering to our brand guidelines.
18:05In section two, have architecture. We've got a little bit of a quote here, and if we keep scrolling down, we've got some more statistics. We've got section three.
18:11We've got another quote, and we have another infographic, once again, adhering to our brand guidelines and using a little logo up here as well. And that's pretty much how the rest of the newsletter goes.
18:20We've got section four, and we can see our third and final infographic that has a different version of the AIS logo as well as our brand guidelines. So this was literally iteration one. There's a lot of things that we can prove here, and all we would do is we'd open up Clog code, and we'd ask it to make it better using natural language.
18:34We could actually make sure that every infographic it creates uses our actual logo rather than prompting some sort of AIS logo in there. It ends with some key takeaways, and then we have it ends with some key takeaways. We have a call to action down here, and then all of the sources we could actually click on, and it would take us to that actual site where it pulled the data from.
18:51So that was version one of the newsletter, and I think that that's pretty solid. Now the cool thing about these projects in Cloud Code is as you use them more, they get better and better. Because every time I run this workflow, it might find something else out, and it will update its Cloud MD, it'll update its workflows, it'll update its tools.
19:05As I give it more brand asset, as I give it more context and more knowledge, it just gets better and better. And then once you really trust the actual workflows and tools, that's when you go ahead and you come back into this, and then once you really trust the workflows and the tools that you've created using Cloud Code, you would basically take these two things, and you would push those into like a GitHub repository, and you'd sync those to something like trigger dot dev or modal in order to actually have them run every single Monday at 6AM or daily, something like that.
19:29I'm not gonna dive into that in this video, but if you wanna see one where I did, then I'll tag one right up here. So what you guys just saw here was me using hardly any prompting, just using my natural language, giving it a few logos and colors, and then giving us a really, really good output for a newsletter. Now one thing that we didn't cover in this video, but we will be covering a lot more in the future, is how you could actually make your workflows even better and better, and that's the idea of using skills.
19:51Whether it is a skill that you create yourself or whether it's a skill that someone else has already built. So skills are basically just system prompts that you could load in when you need them. So let's say you ask Cloud for help.
20:00Hey, can you design me a website? The agent will then check through all of the skills it has access to, and it will see, based on all of these skills, does my current request require this? So it's almost like the same way it decides if it should use a tool or not.
20:11So for example, there is a front end design skill that makes Cloud Code so much better at designing websites, and so if I'm ever building a project where I need it to be able to build websites, I would tell it to always invoke the front end design skill. The reason I'm bringing this up is because you can create your own.
20:24So what I might do in this version is once I realize what I really like about how it creates newsletters, I will tell it to turn that into a skill. So maybe it is the skill of making infographics look really, really polished with the AIS logo in the top left corner, and I could create that skill so that every time it needs to create a new infographic, it reads that first, and then it makes its outputs a lot more consistent.
20:43So I know that this seems a little bit intimidating at first, but hopefully you guys realize after watching this how easy it was for me to actually do this. Once again, with hardly any technical knowledge, we didn't set up any API calls, we didn't do anything like that, we just talked to it. But now the question is, how do you actually turn a skill like this into income?
20:58So this is something that I see all the time. A business owner watches free YouTube videos or LinkedIn posts or whatever it is and sees flashy AI demo. Maybe that's a voice agent or a really cool chatbot or a crazy looking dashboard, and they come to you or some sort of like, you know, AI agency, and they say, I want that.
21:12When you actually sit down and you look at their business and their operations, that's not what they need at all. The real problem is that leads might be falling through the cracks or the onboarding is taking way too long or there's tons of manual data entry going on. Just think about it like plumbing.
21:23If you have a , it doesn't matter how much water you pour into it. It's not gonna flow any faster if there's a clog. Most businesses are out here trying to put as much water into the pipe as possible, hire more people, throwing AI at random problems, but what they actually need is someone who can come in, find the clog, and then clear that, and then start to add more water in.
21:39That's really the skill. And if you can cut through the noise and identify real constraints and unclog that pipe, that's worth way more than building some super flashy agent that looks cool but doesn't actually move the needle. The build itself is also not what businesses are paying for because building is getting easier and easier every day, which is good news, but it also kinda brings about some panic because more people can spin up these automations much quicker, and that's becoming a little bit more commoditized.
22:00So if you're trying to compete on I can build AI automations, you're going to be in a race to the bottom. What you need to do is act as the doctor, not the pharmacist. I've used this analogy a lot on my channel.
22:09A pharmacist just fills a prescription that someone else wrote, but a doctor sits down with the patient, asks questions, runs diagnostics, and figures out what's actually wrong before anything is then prescribed. That's the difference between someone who just builds workflows and someone that businesses will pay serious money to work with.
22:23So when you're talking to a business owner, you're not leading with I build agentic workflows and Cloud Code. They don't care about that. You're leading with, I can save you x amount of time per month.
22:32You're leading with, I can save this process x percentage of errors. And that's exactly why you should not be pricing yourself hourly. Because if you can build something in thirty minutes that ends up saving the business, let's just say, twenty hours a week, that's not a thirty minute job.
22:43That's tens of thousands of dollars in value over the course of a year. So if you price yourself at an hourly rate, you're putting a ceiling on your income, and you're completely ignoring the value that you're actually delivering. Now hourly can be fine early on when you're just getting started and you're building trust and you need to get your first few wins.
22:57But once you can clearly show the ROI, the hours saved, the cost eliminated, the revenue generated, all that kind of stuff, then your pricing should really be reflecting that value, not your time. Trading time for money is not very scalable. So here's a simple way to think about it.
23:09You sit down with a client and you figure out their processes, and you calculate that this system is going to save them $10,000 a month. Now let's say you charge $5,000 for that build. That should be a no brainer for them.
23:18They make their money back in two weeks, and then everything else is just profit for the business. And it's also a great deal for you because that build might just have taken you a few days, maybe a few weeks. That is basically value based pricing.
23:28Everybody wins. Now in terms of actually finding clients, I've done a full deep dive on that in another video, which I will go ahead and link right up here. But at a high level, the approach is simple.
23:35You don't need a huge audience. You don't need to start a full blown agency. You just need to start conversations with the right people.
23:40You need to be transparent about what you're building and lead with how you can help them. Once you deliver the solution, you stick around because once that first system is running and they see the results, they're going to want more. They're going to want you to optimize the build.
23:49They're gonna want you to expand on it. They're gonna want you to help find new opportunities inside their business. That's how a $3,000 build turns into a $50,000 a year relationship.
23:57But the key there is that you have to be the one to track the metrics. You have to take ownership over that. You have to practically show them the value that the system is actually adding.
24:05That's super, super important. That's exactly the Freelancer to consultant to trusted partner. You're not just building workflows.
24:10You're becoming the person businesses rely on to make their operations smarter. So we just went from understanding what's happening in the agentic workflow market to actually building one live and seeing how to sell these systems for premium prices. Here's the thing though, this isn't just the future of automation, it's happening right now.
24:24Companies are already making the shift and the demand for people who can build these systems is only going to grow. So if you wanna dive deeper into this kind of stuff, I've got a community with over a quarter million members where I share templates, resources, and all the files from videos just like this one. And if you're serious about making money with AI automation, if you want access to live q and a's with me, if you want direct support, and even job opportunities, you can check out my paid community.
24:44Both of those links are in the description. But that's gonna do it for this one. If you guys enjoyed, learned something new, please give it a That like.
24:49Way helps me out a ton. And as always, I appreciate you guys making it to the end of the video. I'll see you on the next one.
24:53Thanks, everyone.
The Hook
The bait, then the rug-pull.
The title makes a dollar-figure promise, and the first ten seconds back it with a market-size claim — agentic AI going from $7 billion to $93 billion — before pivoting to a three-part agenda: understand why, build one live, learn to sell it.
Named ideas worth stealing.
07:18acronym
WAT Framework
- Workflows
- Agent
- Tools
A three-layer architecture for Claude Code projects. Workflows are markdown instruction files (the recipe). Tools are Python scripts (the ingredients). The Agent reads both and executes the process.
Steal forStructuring any Claude Code automation project; pitching the architecture to non-technical clients
22:25concept
Doctor vs. Pharmacist
A positioning framework for AI consultants. A pharmacist fills a prescription written by someone else. A doctor diagnoses before prescribing. Builders who diagnose the business constraint first command premium fees.
Steal forClient intake conversations; proposal framing; objection handling on pricing
03:20concept
Battle-test before deploy
Run the agentic system through diverse edge-case scenarios while Claude Code can self-correct, before pushing the code to a scheduled or webhook deployment where the agent is no longer present.
Steal forQA process for any agentic system before handing off to a client or deploying to production
How they asked for the click.
24:00link
“I've got a community with over a quarter million members where I share templates, resources, and all the files from videos just like this one.”
Soft double CTA at the end: free community (templates) and paid community (live Q&As, job opportunities). Neither is hard-pitched during the video body.
Visual structure at a glance.
