23:18Jake Van Clief · Tutorial
Stop Building AI Agents. Use This Folder System Instead.
A 23-minute walkthrough of the three-layer folder architecture that replaces AI agents, frameworks, and databases with plain markdown files.
March 10thThe argument in one line.
Claude Code removes the code knowledge barrier entirely — the bottleneck for building apps is no longer syntax but the ability to describe what you want and iterate on what you get.
Read if. Skip if.
READ IF YOU ARE…
- You have never written code but have ideas for apps, tools, games, or productivity utilities you want to build.
- You are a marketer, creator, or operator whose execution has always been bottlenecked by a lack of technical ability.
- You use Claude.ai in the browser and did not know a desktop app with an agent-mode code builder exists.
- You have tried no-code tools but hit their ceilings and want something that can build anything.
SKIP IF…
- You are an experienced developer looking for advanced Claude Code patterns, API usage, or team workflows.
- You already know plan mode, CLAUDE.md, and MCP connectors inside out.
The full version, fast.
Claude Code is a tab inside the Claude desktop app where you point it at a folder and describe what you want in plain language. It plans, codes, tests, and self-corrects without you touching a file. This video teaches the full beginner loop: approve a plan before building, create a CLAUDE.md memory file so project context survives new chat sessions, connect external tools via MCPs, bundle reusable processes into skills, push to GitHub for version control, and deploy live to Vercel in minutes. Two real builds ground every concept in working demos.
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.
Create a free account →Where the time goes.
00:00 – 00:21
01 · Intro
Host opens with the core premise: Claude Code requires no technical background. Lists what you can build.
00:21 – 00:55
02 · Getting Started
Paid Claude account required. Desktop app download. Three tabs explained: Chat, CoWork, Code.
00:55 – 06:04
03 · Build 1 — Plan, Build, Iterate
Full typing game built from two-sentence prompt through plan mode, five clarifying questions, agentic self-correction, screenshot feedback loop.
06:04 – 06:39
04 · Model Selection
Usage limits tied to tokens. Opus/Fable for first build, lighter model for edits on Pro; Max plan can stay on top model throughout.
06:39 – 07:52
05 · CLAUDE.md
/init creates a permanent project memory file. Explains context window limits and how to start fresh chats without losing project state.
07:52 – 10:58
06 · MCPs, Skills, and Plugins
MCPs connect to external tools (Gmail, Calendar, Context7). Skills are reusable processes. Plugins bundle both. Superpowers plugin and security review skill demonstrated.
10:58 – 13:33
07 · Build 2
Kanban action-item extractor connected to Granola meeting notes via MCP. Pulled real meeting data and built the full UI on first try.
13:33 – 17:17
08 · Connect to GitHub
Git install, Homebrew, GitHub CLI, browser-based auth. One-time setup. Version control framed as an undo button for the whole project.
17:17 – 19:09
09 · Deploy to the Web
Vercel free account, connect via GitHub, one-click deploy. Screenshot-based error debugging. Vercel auto-redeploys on every GitHub push.
Lines worth screenshotting.
- Claude Code is not the chat tab — it is a separate agent mode inside the desktop app where Claude reads and writes files directly on your computer.
- Switching to plan mode before building is the single highest-leverage habit: it is much easier to edit a text plan than to unwind already-written code.
- The CLAUDE.md file solves context window overflow — create it once and any new chat can pick up exactly where the last one left off.
- MCPs, skills, and plugins are three different things: MCPs connect tools, skills define processes, plugins bundle both.
- Claude self-corrects mid-build without prompting — if it hits a wrong parameter it detects the failure, fixes it, and keeps going.
- The Context7 MCP pulls live documentation for React, Tailwind, Vercel, and others — it eliminates a major source of hallucinations in framework-heavy builds.
- You can drop a screenshot directly into Claude Code to describe a visual bug or a design you want to replicate, and it will use that image as the spec.
- On the Pro plan, use Opus or Fable for the first build, then switch to a lighter model for follow-up edits to conserve your token budget.
- Vercel auto-redeploys whenever you push a change to GitHub — every fix Claude makes goes live without you doing anything manually.
- You only have to connect GitHub once — after that, every new project ships with a single prompt asking Claude to create and push the repo.
- The Superpowers plugin adds brainstorming, sub-agent orchestration, and debugging skills that Claude calls automatically when relevant.
- Building a Kanban app connected to real meeting notes via the Granola MCP took one first-try attempt with no corrections needed.
How to go from idea to live app without writing code.
WHAT TO LEARN
Claude Code's power for non-technical builders comes from four habits layered on top of each other — none of them require understanding code.
03Build 1 — Plan, Build, Iterate
- Always use plan mode before building: reviewing a text plan takes 30 seconds and prevents hours of rebuilding after a misunderstood direction.
- Drop screenshots into the chat when you have a visual bug or a design you want to replicate — Claude will use the image as the spec.
- Claude self-corrects mid-build without prompting — if it detects a wrong parameter it fixes it and keeps going.
04Model Selection
- On the Pro plan, use the best model for the initial plan and first build, then switch to a lighter model for follow-up edits so you preserve your token budget.
05CLAUDE.md
- Run /init at the start of every project to create a CLAUDE.md file — this is what lets you close a session and pick it up days later without re-explaining the whole project.
- When your chat history grows long, ask Claude for a session summary, open a fresh chat, paste it in, and point it at the same folder — you keep the momentum without the context drift.
06MCPs, Skills, and Plugins
- MCPs, skills, and plugins are not the same thing: MCPs connect Claude to your existing tools; skills give it a process to follow for a repeatable task; plugins bundle both.
- Connect Context7 early — it pulls live documentation for the frameworks being used and cuts hallucinated API calls dramatically.
08Connect to GitHub
- GitHub is version control as an undo button — you can always roll back to any previous working state, which makes experimentation safe.
09Deploy to the Web
- Vercel auto-redeploys on every GitHub push — once connected, you never touch the deploy step again for that project.
Terms worth knowing.
- MCP (Model Context Protocol)
- A protocol that lets Claude connect to external tools and services — calendars, note apps, code repositories. Anthropic calls them connectors in the UI.
- CLAUDE.md
- A markdown file created by running /init that stores permanent project memory — architecture, key decisions, current state. Claude reads it at the start of every new chat in the project folder.
- Plan mode
- A Claude Code setting where the model lays out a full build plan for your approval before writing any code, making it easy to redirect before work begins.
- Context window
- Claude's working memory for a conversation. When it fills up, Claude starts losing detail. The solution is a new chat with the CLAUDE.md file plus a session summary.
- Skill
- A saved, reusable process that Claude follows to accomplish a repeatable task. Can be prebuilt or created by asking Claude to package a session you just ran.
- Plugin
- A bundle that packages multiple skills, MCPs, and configuration together. Superpowers is a popular plugin that adds brainstorming, sub-agents, and debugging.
- Context7
- An MCP connector that injects current documentation for frameworks like React, Tailwind, and Vercel into the conversation, preventing Claude from using outdated API references.
- Vercel
- A hosting platform that connects to GitHub and deploys web projects automatically. The free tier is sufficient for most beginner projects.
Things they pointed at.
08:41toolContext7
09:14toolSuperpowers plugin
11:10toolGranola
Lines you could clip.
00:00
“People assume they won't be able to use Claude Code if they're not technical, but that is not true at all.”
04:04
“Instead of just responding, it tests, adjusts, and corrects course without you asking it to.”
10:38
“MCPs connect Claude to tools. Skills give Claude a process to follow. Plugins can bundle multiple skills, MCPs, and more together.”
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.
00:00People assume they won't be able to use Cloud Code if they're not technical, but that is not true at all. Anyone can use it to build apps, websites, automations, designs, Chrome extensions, productivity tools, and more, and you don't need to know any code.
00:15This is the full guide to start building today even as a complete beginner.
00:23First, you do need any paid cloud account. You can use it on the pro plan, then you get more usage on the max plan. You'll also need to download the desktop app.
00:32This isn't done through the web version. Just download that. You can click it from the cloud interface, or I'll link to it in the description as well.
00:40Install that like any app, and you're good to go. Once the desktop app is installed, you'll see three tabs. The chat tab, which is the same as the web version you're used to, the co work tab, and then the code tab.
00:52Click in there, and this is where the building happens.
00:57Getting started is really simple. Type what you want in the prompt box just like you would when you're prompting any AI tool. I will say, build me a game that teaches me how to type faster.
01:09Make it visual, gamified, fun, and effective.
01:14But that's a very basic prompt on purpose, and this will be a fun one to kick it off. I'll do a practical build as well after covering a couple of the core concepts. And next, Claude needs somewhere to work.
01:25A big difference between Claude chat and Claude code is code actually creates and edits files directly on your computer. So we need to give it access to a folder to do all that in. And to stay more organized, I have a dedicated Claude code folder, then I create subfolders within that for each new project.
01:41And I'm creating a new folder. You could give it an existing folder as well. And now this is where Claude will create and edit everything.
01:48Next, come down and switch it to plan mode. Instead of building right away, Claude will lay out the whole plan for you to adjust or approve. It's much easier to adjust the plan upfront than fix things after it's already started building.
02:02That's all we need. Send it off. Your first time using it, it will ask you for permission to work in that folder.
02:08Just approve it. Then usually, it will have a few questions. This is asking the style of game I want.
02:14I think a racing game sounds good. Then the type of learning. I'll just do pure arcade for a demo.
02:20Then how to structure it. Then it came up with a couple more questions. The visual theme, I think neon synthwave car sounds cool.
02:27Then I'll do fun quotes and sentences for what to type. Now it's off. And now just from my two sentence prompt, it came back with a full detailed plan, the gameplay loop, why it's effective, architecture, build sequence.
02:41If you want to make any changes, you can highlight a section and give Claude notes. Otherwise, if you like it, accept the plan, and Claude will start building. It's all done building, and it looks awesome.
02:52So let's test it.
03:09That is functioning perfectly all from that basic prompt I had and answering five simple questions. That is insane to be able to do.
03:18And now to make any changes, all you do is ask for them. Like, one quick thing I noticed is Claude left its own score of a 173 words per minute from when it was testing, so I'll actually take a screenshot then ask it to remove that.
03:31Anytime there's something you want changed where a visual would help, just take a screenshot and drop it in. That's really helpful, and that also works if you want it to replicate something you've seen. You could mock up an element or website, and Claude can recreate it in your build.
03:46That was a simple change, and it's fixed. And anytime you want some clarity, you can ask questions, Then Claude will know not to build. Like, I don't wanna play through a bunch of levels to understand the whole game yet, and I won't look through any of the code.
03:58I'll just ask Claude to explain it. So I'm just gonna ask just how this works if it's going to be getting progressively harder. Then instead of building, it knows to answer my question.
04:07That explains how all the gameplay logic works. I can ask for changes from there now that I understand it, like adding difficulty levels. Then it starts building again.
04:15Then you just go back and forth from there using natural language like this. You don't need to understand the code. Just describe what you want the same way you'd explain it to a person.
04:24We've already built something pretty complex, and it was really that easy. Before I cover more concepts, I wanna go back and show what happened and what makes this so powerful. After I approved the plan, it started building.
04:36As part of that process, it used a bunch of tools, then it started testing the game. They can adapt to new information from that testing. Right here, it says, I need to correct course.
04:46So it was using the wrong parameters. It discovered that and fixed the error and then went back to testing. That's a good example of what an agentic model like this can do.
04:55It can take action on its own. Instead of just responding, it tests, adjusts, and corrects course without you asking it to. And along the way, it's actually testing the game.
05:04It pulls it up, clicks buttons, it types to make it through a level, and made sure everything was functioning. It does all of that on its own before delivering the end result to you. I think this will always be amazing to me.
05:16This game was actually pretty fun, so I made some more changes, added different levels of difficulty. Hard includes a bunch of symbols and numbers. I also added a full testing mode that's like a real typing test to understand where you're at, and then it can place you in the levels from that.
05:30Just a few different things like that using the same process I already showed. Just describe it, Claude builds it. If you wanna use Claude code for marketing work, we've got a free guide for you.
05:40It has four workflows and 12 prompts that you can copy paste to go from idea to finished product in a single session. Things like building a lead magnet or testing a positioning angle the same day you think of it. You can even launch a campaign without writing a single line of code.
05:54If you don't know exactly what to build after watching this video, this has real world use cases that are easy to get started with. That's free. Just click the link in the description.
06:06Now I wanna touch on the different models. You'll see a drop down with a big list of models to choose from. These change all the time, so I don't wanna focus on specific model numbers.
06:15But the reason this choice matters is because Claude has usage limits based on how many tokens you use, and the better models also use more tokens. The models change, but the good rule of thumb is if you're on the pro plan, use the highest model, like Opus or Fable, for the plan and first build, then switch to a lower model for the follow-up edits.
06:34If you're on the max plan, you'll usually be fine sticking with the highest model all the time. I've got the game built and made some edits.
06:43From here, there's something you'll always want to do so Claude has persistent memory of your project. Create a Claude dot m d file, a permanent reference document that holds everything Claude needs to know about the project long term. To do that, just type forward slash in it, then send it, and Claude knows exactly what to do.
07:01It reads through all the code and the chat history, then creates a markdown file that contains all of the important aspects. This is what the file looks like. It was added right to the project folder.
07:12And this is just markdown. It's not code or anything. All these symbols are just for formatting.
07:16If I open this in an app like Obsidian that uses markdown, this is what the file looks like. You don't need to use Obsidian. I just wanted to show that this is a simple text file, not some code base or anything.
07:26And, really, you don't even have to look at that. But that file will be there as a permanent reference file for Claude, and you can ask Claude to update it with any specifics at any time. Or after a long session, you can just say update the Claude MD file with anything important that we covered.
07:42Now this game still lives only on my computer, but before I show how to actually deploy this live, I wanna show you some features that make Claude code much more powerful.
07:53You can build a ton of stuff with what I've already shown, but there's some pretty easy power ups to help. First is MCPs. These connect Claude to external tools.
08:02These are under customize, then Anthropic calls them connectors, which is a more understandable name for them.
08:08But you'll also hear them called MCPs because that's the name of the protocol they use. You can come up to the plus button, then browse connectors. Then there's prebuilt connectors for a massive list of tools.
08:21Common ones like Gmail, Google Calendar, and Notion. Those are major ones, but there's tons more in here for most tools you can think of. One I'd recommend everyone connect is called context seven.
08:31It pulls in up to date documentation for things like React, Expo, Tailwind, Vercel, and a lot more. These tools change, and Claude may have been trained on an older version or pull up outdated info from the web. Context seven makes sure it's always working from current documentation.
08:47So definitely worth connecting, then it will always be there, and it will use it whenever it needs to. That reduces a lot of hallucinations when it's implementing those frameworks. And I'll disconnect mine just to show this.
08:57To connect any of these, you just click connect, then it will have you log in through the platform. Then you're good to go. And while we're in here, there's also plug ins.
09:07These are packages of skills and tools. There's prebuilt plugins from Anthropic that are very powerful, and they ship new ones regularly. You can look through to see what might be useful to what you're building.
09:17One I'd recommend is called superpowers. It adds a bunch of different skills Claude can call automatically when needed to help with all sorts of things like brainstorming, sub agents, debugging, and more.
09:28Definitely a useful one to install. Then Claude will utilize any of these skills automatically whenever it's relevant to a task. And I mentioned skills.
09:37These are reusable processes that Claude will follow to achieve repeatable tasks. They have prebuilt skills that are awesome, but you can also create your own skill. So how I typically do that is whenever I go through a process myself that involves multiple prompts and iterations, if that's a process I want to repeat again in the future, you can say package that up as a skill, then Claude will analyze everything you did and turn that into a reusable skill, which will get called and executed in the same way every time moving forward.
10:05Here's a quick example of a skill. I'll ask Claude to do a security review. Now it has a built in process for doing this and walks through the whole thing.
10:14This is a super important step before pushing anything public. Claude will find vulnerabilities, exposed API keys, things like that, which could lead to issues.
10:23There's nothing present that would be an issue for a project like this, but you can see Claude identified the main attack surfaces for this type of game. Then it searched through, went to see if any of those vulnerabilities were present. And that one's a useful skill, but they can be for anything.
10:36Like, I have one for writing social media posts and critiquing YouTube scripts. There's one for front end design, creating payment systems. Basically, any task you can do in Claude, you can create a skill to streamline it.
10:47And those three things can get mixed up. So MCPs connect Claude to tools. Skills give Claude a process to follow.
10:54Plug ins can bundle multiple skills, MCPs, and more together. Now I wanna show you something more practical, closer to what you'd actually build for work, a real productivity tool using your existing apps.
11:07I'll go back to my connectors, and you can see I have granola connected. I use that for meeting notes.
11:14I can make sure the permissions I want it to have are available, then go back to my chat, and I'll use this prompt. Build a Kanban style app for extracting action items from meeting notes into a to do list where cards move between to do, in progress, and done. Use a connected granola MCP to pull in meeting notes and extract action items.
11:33Now I'll create a new folder for Claude to work in, switch to plan mode, and send it off.
11:42Answer a few questions, and Claude comes back with the plan. I approve that plan, then it gets to work.
11:49Now here's what it came back with. It pulled my most recent meeting, identified all the action items and who they're for. I can move those around to in progress and done.
11:59That was a simple build, but pretty useful, and it nailed it completely on the first try. Once you start connecting tools you already use and building them into new interfaces and systems, you can massively open up what you're able to achieve and start making really time saving tools for yourself. Now I'll go ahead and run forward slash init.
12:18So Claude will create that Claude dot m d file. And another reason this file is important is if your chat history gets too long, you can start a brand new chat, point it at that folder, and Claude can read that and know everything about the project. Down here, you can hover to see how much of your context window is filled.
12:35Your context window is basically Claude's working memory for that conversation, and there's a limit to how much it can hold at once. Claude will automatically compact that when it gets too full, but over time, it will start losing details or getting confused. After a while, it's better to open a new chat.
12:50And I'll usually ask Claude for a summary before doing that as well with a prompt like this. That's especially helpful if you're actively working on a feature or there's more you'll be building that it knows about. Things like that wouldn't typically be in the Claude MD file.
13:03Then you just open a new chat, paste that response it gave, point it at the same folder, then it will also read the Claude dot MD file, and you're good to pick up right where you left off, but without a messy context history. Alright. You know how to build things now, but this still lives only on your computer.
13:19You may want to share your project with someone or deploy it live to the public. That process is simple, although it takes a little bit of setup the first time you do it. You'll need to install git if you don't have it and connect Claude to GitHub.
13:34So first, we need git installed locally. On a newer Mac, it's already installed. Windows users will have slightly different steps.
13:41But since we're asking Claude, it'll give you the right instructions for your specific setup automatically. Just start with this prompt. Check if I have git installed.
13:49If not, install it for me. And mine is already installed because it came with my Mac out of the box. If yours isn't, Cloud will walk you through it.
13:57Just follow what it says. And next, we need to connect a GitHub account. GitHub is a cloud platform for hosting code.
14:04Once your project is there, you can access it from any device, share it with others, or deploy it to the web. It also handles version control, like an undo button for your whole project. You always have a saved snapshot so you can roll back to any previous state if something goes wrong.
14:19Just ask Claude to connect to GitHub so it can push code on your behalf and to walk you through anything that needs manual input. Claude will walk you through it, and the steps will be a little different depending on your setup, especially Windows versus Mac. But I do wanna walk through them on screen even though yours may be different.
14:35This is the most tedious part so far and the easiest to get lost in. So this will show you what it feels like to go through these, and some of the steps will be the same for every setup. And what's nice is you only need to do this process once.
14:48So it will tell me the four step process we're going to go through to do that. Installing Homebrew is the first step of that process. So I'll tell it to start that, then it comes back and tells me I need to copy and paste a command into the terminal.
15:00So this is where we need to actually interact with the terminal ourselves to run a couple commands. Claude makes this easy. You can use the same panel button you use for the preview window and open up the terminal right here.
15:10Then it's just copy, paste, and hit enter. Then it asks me to put in my password. This is the password to my computer.
15:17And when you type this, it won't actually do anything as you're typing. The cursor doesn't move. That's just how it hides passwords by default.
15:24So just type in the full password and hit enter. And just wait a minute, then when the input field reappears, it's done. Then tell Claude that Homebrew is installed and ask what Now it popped up asking if it can run a terminal command itself to install the GitHub CLI.
15:38Oh, I will allow. Then it installs it. And the last part is it needs me to run one or more terminal commands to authenticate to actually connect to my GitHub account.
15:48So we are almost there. For this step, you do need a GitHub account. If you don't have one, it's free.
15:53Set it up like any other account. Once you're ready, copy the command Claude gave, paste it into the terminal, and hit enter. Then it will ask a few questions, and Claude actually told me exactly what to answer for each of those questions already.
16:06I use it on github.com. Preferred protocol is HTTPS, then authenticate by logging in with a web browser.
16:14Now it gives me a code to copy. Copy that, then hit enter to open the link it gave. Continue with my account, paste the code, then authorize GitHub.
16:24Then it sends a code to that email. I'll enter that here, and we're all set. GitHub is officially connected.
16:31Back in Claude code, I'll say done. Now it's just verifying it works. It did.
16:36So it says it can now push code, create and clone repos, and open PRs on my behalf. Perfect. Now that it's set up, you won't ever have to do that again.
16:45You can just ask Claude to create a new GitHub repository for this project and push all the current code. Just answer a quick question if I want it public or private, then it's done with a direct link to the repo it just created.
16:59I'll open that up, and this is the repository on GitHub with all the files that have been created so far. And that probably felt like a lot if you're new to all of this. That's why I walked through every step.
17:08The good news is, again, you only need to do the initial setup once. From here, for any new project, you just ask it to push it to GitHub, and it handles it all.
17:19Now that we have a GitHub repository, it's really easy to push that live to the web using Vercel. First, you'll need to create a Vercel account.
17:27You can sign up for free using your GitHub account, then it will take you to this page. Then right in this box where it says import Git repository, I'll click the button continue with GitHub, click install, and it will connect Vercel to my GitHub account.
17:40I'll select all repositories and install. Then that box populates with the repositories I have on GitHub. So I'll click import on Neon Type Racer.
17:49Then I don't need to change anything on this page. Just hit deploy, and that's it. Wait a few seconds for it to finish, then the game is live on the web.
17:58At least that's normally all it takes, but I have an error, which is perfect to show. I'll take a screenshot, drop it into Claude, and ask why it doesn't work. It identified the exact issue, which is just that my file had spaces, but websites can't, so Vercel use dashes.
18:14It proposed solutions, so I'll pick one, then Claude will fix it. And what's nice is Vercel will automatically detect any changes in GitHub and redeploy with the newest update. You don't have to do anything.
18:25Cloud is finished, so let's check for cell. And it looks like it worked. The domain is right here that this is playable at.
18:31This is a live URL I could send to anyone to play right now.
18:47And everything is working perfectly. So that's how to build a working web app, connect it to real tools, use skills and plug ins, and deploy it live. This is all you need to get started.
18:58The best way to learn more is to just start building. Then anytime you run into a problem, ask Cloud for help, and you'll learn more along the way. Just pick something you would actually use and build that.
The Hook
The bait, then the rug-pull.
The word 'code' in the product name is doing real damage. Futurepedia's 19-minute walkthrough opens by dismantling the assumption directly — and then proves it by building a neon typing game from a two-sentence prompt, deploying it live to Vercel, and stopping only to name every concept along the way.
Named ideas worth stealing.
01:48concept
Plan mode first
Always switch to plan mode before building. Claude lays out the full architecture for approval before writing code — much easier to adjust a text plan than to unwind built code.
Steal forAny complex build where scope-creep or misunderstanding early wastes hours
10:38model
MCPs / Skills / Plugins trinity
- MCPs connect Claude to tools
- Skills give Claude a process to follow
- Plugins bundle skills, MCPs, and more
The three extension mechanisms for Claude Code, which the host explicitly calls out as commonly confused.
Steal forExplaining Claude Code capabilities to any non-technical audience
11:59model
Context window management loop
- Run /init to create CLAUDE.md
- Ask Claude for a session summary before ending a long chat
- Open new chat, paste summary, point at same folder
How to maintain project continuity indefinitely despite context window limits.
Steal forAny long-running project or multi-session build
How they asked for the click.
VERBAL ASK
05:23link
“If you wanna use Claude Code for marketing work, we've got a free guide for you. It has four workflows and 12 prompts. That's free. Just click the link in the description.”
Mid-roll HubSpot sponsor read delivered as a resource mention rather than a hard ad — low friction, contextually relevant to the audience.
MENTIONED ON CAMERA
FROM THE DESCRIPTION
PRIMARY CTAWhere the creator wants you to go next.
OTHER LINKSAlso linked in the description.
Visual structure at a glance.
