Video of the Day19:40Alex Finn · Review
ChatGPT 5.6 vs Fable 5: Who Actually Wins
A creator burns $500 of Fable 5 credits in a day, declares ChatGPT 5.6 the execution winner anyway, and lays out a split workflow for using both.
July 9thThe argument in one line.
Manually prompting a coding agent one task at a time is the bottleneck, and replacing it with a spec-build-review loop turns a full day of prompting into two five-minute check-ins.
Read if. Skip if.
READ IF YOU ARE…
- You already use Claude Code or Codex daily and are tired of babysitting every prompt-test cycle yourself.
- You're juggling multiple side projects and only one advances at a time because you're the bottleneck.
- You want a concrete, repeatable system (not just a philosophy) for making your coding agent work while you're away from the keyboard.
SKIP IF…
- You haven't used an AI coding agent yet — this assumes you already know the basic prompt-and-test workflow it's replacing.
- You're not willing to set up Linear (or an equivalent tracker) and a messaging app — the loop depends on both.
The full version, fast.
The video's argument is that one-at-a-time prompting caps how much a coding agent can produce, because nothing advances unless a human is actively typing and testing. The fix is a three-skill loop — spec, build, review — run inside Claude Code or Codex. Spec interviews you each morning about a feature idea and files detailed issues in Linear. A build loop then runs every five minutes, pulling issues and coding them autonomously. A review loop tests each result in a browser, opens a sandboxed preview branch, and posts the pull request to Slack. The only manual steps left are answering the spec interview and reacting with an emoji to merge — everything in between runs unattended, even overnight.
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 – 01:31
01 · The claim: loops replace prompting
Cold open citing other builders (Peter Steinberger, Boris from Claude Code) already saying they don't prompt agents directly anymore — they build loops. Sets up the promise that this video will show how.
01:31 – 02:57
02 · Before: manual vibe coding
Diagrams the current default workflow — prompt, then manually test, repeat — and names the core problem: nothing advances unless a human is actively engaged.
02:57 – 04:56
03 · The Finn Loop, defined
Introduces the replacement structure: three skills (spec, build, review) chained into a loop that runs continuously and merges automatically, cutting daily manual work by roughly 95%.
04:56 – 06:43
04 · Sponsor: HubSpot's Claude Code Playbook
Paid read for HubSpot's free Claude Code Playbook — covers CLAUDE.md rules, hooks, sub-agents, and dynamic orchestration workflows the host says integrate with the loop being demonstrated.
06:43 – 09:58
05 · Skill 1: spec — turning ideas into scoped issues
Shows the /spec skill interviewing the host about a feature idea (~15 questions), then filing multiple detailed issues into Linear with acceptance criteria and explicit non-goals.
09:58 – 12:04
06 · Skill 2: build — the autonomous coding loop
Demonstrates setting the build skill on a repeating 5-minute loop (`/loop 5min /build`), which pulls issues from the Linear backlog and codes them without further prompting.
12:04 – 14:04
07 · Skill 3: review — browser testing and sandbox PRs
A parallel loop runs the review skill on issues marked ready, which opens a browser, tests the feature, spins up a sandboxed preview branch, and writes user testing instructions.
14:04 – 15:03
08 · The payoff: merge from Slack with one emoji
Finished pull requests land in a dedicated Slack channel with a description and a clickable sandbox preview; reacting with a rocket emoji tells the agent to merge it.
15:03 – 18:10
09 · What's left to automate, and the CTA
Host reflects that only two manual checkpoints remain (morning spec, evening merge) and says he's working on automating those too; points to a free Google Doc with the exact prompts and a GitHub repo, and suggests feeding the video transcript to an agent as the fastest way to set it up.
Lines worth screenshotting.
- One-at-a-time prompting caps a coding agent's output because nothing advances unless a human is actively prompting or testing it.
- Running six projects manually means only one project advances at a time — the human is the bottleneck, not the model.
- A three-skill loop — spec, build, review — turns a full day of manual prompting into two short human check-ins, morning and night.
- The spec skill interviews the user with roughly 15 clarifying questions before it will file a single issue, trading a few minutes of talking for a fully scoped task.
- Each issue the spec skill files includes acceptance criteria and explicit non-goals, so the build skill knows exactly what NOT to build as well as what to build.
- A free project tracker (Linear in this case) functions as a second brain for the agent, letting a build loop resume exactly where a previous run left off.
- Running `/loop 5min /build` tells the agent to repeat one skill every five minutes indefinitely, effectively converting a single prompt into a standing background job.
- The review skill doesn't just read code — it opens a browser, clicks through the feature, and tests it the way a human QA pass would before marking it ready.
- Routing finished pull requests into Slack (or Discord) with a one-click sandbox preview turns code review into an emoji reaction instead of a context switch back into the IDE.
- The setup intentionally keeps two manual checkpoints — the morning spec interview and the end-of-day merge decision — because full autonomy on merging wasn't yet trusted.
Replace daily prompting with a three-skill loop, not more prompts.
WHAT TO LEARN
The ceiling on AI-assisted work isn't the model's capability, it's how often a human has to re-prompt and re-test it — and that ceiling moves when spec, build, and review become standing loops instead of one-off asks.
01The claim: loops replace prompting
- Multiple builders (a well-known AI Twitter voice and Claude Code's own creator) now say they've stopped prompting agents directly and instead design loops that prompt the agents for them.
02Before: manual vibe coding
- The default agent workflow — prompt, then manually test — stalls the moment a human stops actively driving it.
- Juggling several projects manually means only the one you're currently prompting moves forward; the rest sit idle.
03The Finn Loop, defined
- A three-skill chain — spec, build, review — replaces the single prompt-test cycle and is claimed to automate roughly 95% of day-to-day coding work.
- The loop is tool-agnostic: it can be built with Claude Code, Codex, or any agent that supports custom skills.
05Skill 1: spec — turning ideas into scoped issues
- The spec skill interviews the user with roughly 15 clarifying questions before filing a single issue, trading a short conversation for a fully scoped task.
- Each filed issue includes acceptance criteria and explicit non-goals, not just a feature description — that's what lets the build skill work unsupervised.
06Skill 2: build — the autonomous coding loop
- Setting a build skill on a repeating timer (`/loop 5min /build`) turns a single instruction into a standing job that keeps pulling and coding backlog issues.
- A free tracker like Linear acts as a second brain, letting the build loop resume exactly where the last run left off across sessions.
07Skill 3: review — browser testing and sandbox PRs
- The review skill actually opens a browser and clicks through the built feature rather than just reading the diff, closer to a real QA pass.
- Each reviewed change is packaged into its own sandboxed preview branch plus written testing instructions before it's handed back to a human.
08The payoff: merge from Slack with one emoji
- Routing finished pull requests into a chat channel with a clickable preview reduces the human's merge decision to a single emoji reaction.
- The whole review-to-merge exchange happens without opening the IDE or the coding agent at all.
09What's left to automate, and the CTA
- Even after automating build and review, two manual checkpoints were kept on purpose — the morning spec interview and the end-of-day merge call.
- The stated next frontier is automating idea generation itself, the one step still fully dependent on a human.
Terms worth knowing.
- Loop engineering
- Designing a repeating instruction set for an AI coding agent to run on its own, instead of sending it one manual prompt at a time.
- Vibe coding
- Building software primarily by describing what you want in natural language to an AI agent, rather than writing the code by hand.
- Custom skill (Claude Code)
- A reusable, named instruction set a coding agent can be told to run (e.g. /spec, /build, /review) that encodes a specific process step.
- /loop command
- A Claude Code instruction that repeats a given skill on an interval — for example, running a build skill every five minutes without further input.
- Linear
- A free project-management tool used here to track AI-generated issues, acceptance criteria, and task status so an agent can resume work across sessions.
- Sandbox preview branch
- An isolated, deployed copy of a single code change that a reviewer can click into and test without affecting the main branch or other in-progress work.
Things they pointed at.
13:24toolSlack
Lines you could clip.
00:27
“I don't prompt Claude anymore. What I mostly use now is loops. I create loops. They do my entire job.”
02:16
“You as the human being are the bottleneck.”
03:37
“Your work goes from sitting at your computer all day to coming in, waking up in the morning, giving a couple ideas, and at the end of day, you come back to your computer, and they're all done and merged.”
14:26
“All I need to do is react with a rocket ship emoji.”
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.
metaphoranalogy
00:00Everyone and their mothers has been talking about vibe coding loops lately, aka loop engineering. I mean, take a look here. Everyone from Peter Steinberg has been saying, hey.
00:11Don't prompt your agents anymore. You should be building your loops. Even Boris from Claude Code, the guy who invented Claude Code, all he's talking about is loops.
00:21I don't prompt Claude anymore. What I mostly use now is loops. I create loops.
00:25They do my entire job. Well, I'm here to tell you they ain't lying. Here is the issue, though, with all this.
00:32They've all been talking about loops, but nobody is telling you how to build a loop. There's no one out there directing you on what a loop actually is. I have good news for you.
00:43I'm about to show you. I'm here to report I've built an incredible loop that's basically automated 95% of the vibe coding work I do.
00:54In this video, I'm going to show you how to build it and use it, the most beginner friendly loop engineering video you've ever seen in your life. If you stick with me here and build out the things I'm about to show you with you, I'll include all the prompts, instructions, everything, you will produce a 100 x more with your vibe coding, or I'll refund you all the money you spent on this video.
01:16You are about to watch a historic first video, the first video that deep dives into building an extremely powerful vibe coding loop.
01:26This is loop engineering one zero one. Now let's lock in and get into it. So let's talk about how you vibe code before loop engineering and after loop engineering.
01:36This is how you vibe code before loop engineering. This is probably what you're doing today. You go to Claude Code.
01:42You go to Codex. You send it a prompt. Say, hey.
01:44Build this UI. Build this game. Build this feature.
01:47It builds it, and then you test it, and you sit there and manually test it. Then that's done. You send another prompt.
01:52Okay. Now add this button. Then adds the button, then you test it.
01:55Every part of this is manual. Right? Everything you do is completely manual.
02:00Everything you do requires either you typing a prompt or you testing it out. And here's the biggest issue with it all. If you're not at your computer and you're not actively prompting or testing, nothing's happening.
02:13Nothing's advancing. I'm juggling, like, six different projects at once right now. And before, if I wasn't spending time on each one of those projects, they weren't advancing.
02:23Only one project was advancing at once. . And while this was a big advancement over just manually writing code, right, that's what people were doing before a couple years ago.
02:36Insane. Right? Well, this is a big efficiency gain over just manually writing code.
02:40It's still not maximum performance. It's still not maximum automation because you're still doing everything manually.
02:48Let me introduce you to the new age. Let me introduce you to how you will be vibe coding after you're done watching this video. We're gonna go over here.
02:57This is the thin loop. That is right. I named the loop.
03:00I've hey. I invented the loop. I'm allowed to name a loop.
03:03This is the thin loop. Here is how it works. It consists of three different skills.
03:09Spec, build, review. You spend a couple minutes telling the agent exactly the ideas in your head, and then it goes in a loop and all day builds it out, reviews it, tested itself, builds out, reviews it, tests itself over and over and over again completely autonomously. And then at the end, you quickly click through, and it all merges.
03:30Instead of having to work all day completely manually prompting your agent and testing it yourself, the only thing you're doing is kinda loosely telling you the ideas in your head, and it goes and just builds and reviews, builds, reviews, tests, builds, reviews, tests, and merges it all.
03:45Your work goes from sitting at your computer all day to coming in, waking up in the morning, giving a couple ideas, and at the end of day, you come back to your computer, and they're all done and merged. 95% of your work now is completely automated.
03:58You're not sitting there and prompting over and over again. You're giving a couple ideas, and the AI figures it all out on its own, builds it all out, tests it. It's constantly working even if you aren't there.
04:08So even if you have just five minutes free in the morning, you go into this loop, which, again, I'll show you how to build out in just a second. Stick around here, and it'll go and work autonomously for you knowing exactly what to build, knowing exactly how to test, and knowing exactly how to merge.
04:22This can be done with any vibe coding tool on planet Earth you're using, whether it's Codex, Claude code, whatever you prefer. Plus, there are some additional tools added on, which I'm gonna show you, and they're all free. You just add them on to your coding agent, and you have this really, really nice loop setup that you can manage and control from anywhere in the world.
04:40You don't even have to touch Codex or Claude code anymore. I'll go into more details in second. This is super simple, super easy.
04:46I'll give you the exact prompts on how to set up the skills you need to set up this loop. And now what I'm gonna do is show you how it works, then show you how to set it up. But before we do that, building loops for your agent basically just makes your agent way more reliable.
05:01There are many other ways to make your agent reliable as well. And thank god for my friends at HubSpot. They built the Claude code playbook, build systems that make AI reliable.
05:13Just for the subscribers of my channel, you get this playbook for free. This playbook gives you systems that help your agents go from sometimes doing what you say to always doing what you say and being incredibly reliable. In this easy to read playbook, you'll learn all the systems and tricks to create a really impactful, powerful clawed rules file.
05:32You'll learn how to prompt your agent better so you get better results, hooks that make sure your agent don't go off the rail. And by the way, these all work with the loop I'm about to show you. They all integrate perfectly.
05:43It'll make the loop I'm about to show you even more reliable. Sub agents so you can have armies of agents working for you and so much more. It's gonna improve the quality of your Claude code output by a ton.
05:53My favorite part's the section on dynamic workflows. You can have Claude write an orchestration script that runs up to a thousand agents while keeping the lead agent's context completely clean. That's really, really relevant to you if you're gonna build out the coding loop we're talking about in this video because it all ties together.
06:10This is one of the best educational materials I've ever read about Claude Code. So make sure to check it out down below. Link for this free playbook down below.
06:19You got nothing to lose. And thanks to my good friends and partner at HubSpot for supporting the channel and the FinFam community. So as I talked about earlier, there are three skills involved with this loop.
06:29I'm gonna be doing this in Claude code. You can do this in Codex, Claude code, any tool you want. As long as you can build custom skills, which basically every tool on Planet Earth allows you to right now, you can run this loop.
06:40Again, three skills involved. Spec, build, and review.
06:44Mine are called HIM spec, HIM build, HIM reviews. I'm just doing it in my HIM project. But all you need to know is spec, build, and review.
06:50First is spec. Again, spec is the first part of this loop. This is what helps the coding agent capture all of your ideas.
06:58This is what's gonna kick off the entire loop you see here. Basically, what I'm about to show you is the only manual work you need to do to pump out tons and tons of high quality code. So you wake up in the morning, you grab your cup of coffee.
07:11Now you wanna get some things built out. So you're basically going to your agent saying, hey. Here's everything that's top of my mind.
07:17What you do is you use the spec skill. You give a high level what your idea is, what the feature is, and what the spec skill is going to do is gonna ask you enough questions about what your idea is until it understands it completely and can build out a ton of features for your agent to build.
07:35It's basically gonna interview you, come up with a ton of details. So say you have a game you wanna build, you do slash spec, then say, I wanna build a game, then you hit enter. And now my agent's gonna start asking me a bunch of questions until it feels fully confident it can spec out everything it wants to build in detail.
07:55So I just answered about 15 questions that allows it to understand in detail exactly the feature I'm trying to build in my app, Henry. It came back and now has five issues it's going to file for me and send to the building loop. Again, the spec skill comes up with a bunch of issues.
08:13Issues are basically detailed tasks with acceptance criteria, sends it to our loop, build review test, build review test. The agent handles all this for us, and then we come back at night after all the work is done and merge it really quick.
08:28So we did spec. It came up with five different issues. It's going to send to the loop.
08:32We just need to approve it. So as you can see here, the spec skill filed five new issues.
08:38And now if we go into linear, which is the free app we're using to track all these issues, we can check them all out. So here's an example. One of the issues it made, the AI built out this incredibly detailed document with everything about the issue or the task the AI agent needs to build, all the acceptance criteria, including the non goal, so what it shouldn't be doing, everything about the scope, notes, and expectations on how to test it.
09:06This is all automatically built out by that spec skill, multiple of these issues. And this is all in linear. For those who haven't used it yet, I've told you to download it a million times.
09:15Completely free project management tool that basically acts as a for your coding agent. As you can see here, it has all these different issues I'm tracking.
09:26It basically allows my coding agents, codex, Claude code, whatever I'm using to remember every task it's working on so that when I come back or spin up new agents, it can resume from its current state. It's basically a second brain, and it's awesome. Free.
09:40You should download it. So all those issues are here. Next, after those issues are built, it's time for the automated part.
09:46Our work here is done. We came in in the morning. We drank our coffee.
09:50We gave a couple ideas, answered a couple questions. Now the AI takes it from here, and now it's going to use our two other skills, build and review to autonomously build everything out, then verify what it built works.
10:03Previously, what you were doing in vibe coding was you were saying, okay. Now build this out. You're waiting there while it codes and prompts.
10:09Then you're opening up localhost, testing it out, clicking around, then going back. Hey. Build this now.
10:14No. Change this. Now we have skills that describe in detail the best practices around how to build out these specs and how to review them and test them.
10:24I mean, it is doing thorough testing on its own. It's opening up browsers. It's clicking around.
10:29It's doing everything. Let me show you how this works. So let's set up the build loop.
10:34The build loop, I'll go over and over and over again building out every single spec that is in our backlog. Right? As you saw in the last screen, we had five specs built out from our spec skill.
10:44Now the build loop will go through and over and over and over again build all of them out. In Claude code, all we would need to do to do this is do slash loop five men slash him build.
10:56What this does, slash loop basically tells the chat, do this next thing over and over and over again. Five men tells it how often do it. So every five minutes, it's gonna do it.
11:07And what it's gonna do is run him build. Our new skill, again, I'll give you the prompt in a second how to set it up, that builds out any spec in our backlog inside linear. So those five specs that we just built out.
11:20So it's gonna, every five minutes, run him build. So, basically, put it on a loop all day just building, building, building, building, building for us. And, again, all the build skill is is a skill that tells Claude code or codex or whatever you're using exactly how to read and build out each one of those issues in linear.
11:41It also tells it how to move it along our pipeline, how to push it to the review skill, and how to keep our entire loop running even when we're not at our computer. So I'm going to hit enter on that, and it is going to start building out our specs. At the same time as that, we are going to set up our review loop.
11:59So let's do this. I'm gonna open up another chat. I'm gonna do the exact same thing slash loop five minute slash review, and I'm gonna hit enter on that.
12:09This is going to set up another loop where our agent is now gonna review every spec built out, every spec marked as waiting. So when our agent is done building out each one of the specs, it gives it a label that says, okay. Ready for review.
12:25And then our review loop waits to see that label to start reviewing everything. And all our review skill is is basically just instructs the agent how to review everything built out, so how to open it up in a browser, test it out, click around, how to apply the label once it's done being reviewed, how to spin up its own pull request with that specific code in it, how to put that pull request into a sandbox environment so you can test out just that specific change, and how to write instructions for the user on how to test it themselves.
12:58Each one of these new skills that I'm gonna have you build out, it's really, really simple to do. It's just one prompt. All it's doing is instructing the AI how to push issues through our loop here and how to keep everything moving and how to save you way more time and get you way more productive.
13:16So the agents are autonomously building out the issues, then another agent's autonomously reviewing them. What happens when the agent reviews an issue, test it out, sees that it works well, what it does is it takes that pull request and sends it to us in our messaging service of choice.
13:34So for me, that messaging service is Slack. You can use anything for this. You can use Discord if you want.
13:40You can use Telegram if you want. Slack is really built for this type of workflow, but you can a 100% do this in Discord as well. No big issue.
13:48One of the prompts I'll give you down below as well will instruct your AI agent on setting this all up. You don't need to set up Slack. You don't need to set up linear.
13:56You don't need to set up the loops. The AI does it all for you with the prompts I'm gonna give you. So I have this channel merge ready.
14:04The review loop messages me here. As you can see, Henry loops. It describes the pull request.
14:10It describes the issue, what it did. It gives me a link if I want to test it myself so I can open up this preview. It's just like a preview branch in Vercel that just has the one change the agent made.
14:21It gives me step by step on how to test it if I wanna test it myself. And then when I'm ready, all I need to do is react with a rocket ship emoji. When I react with the rocket ship emoji, the agent goes, got it.
14:36I'll merge it. And then it goes merged by me and puts a nice green check mark right on that merge to say, yep. It's merged in.
14:43It's live in the app. And just like that, the code was built. Right?
14:47All we had to do is come in the beginning of the day, answer a bunch of from our agent. The agent then autonomously builds and reviews and tests everything. Then we come in and just click rocket emoji, rocket emoji, rocket emoji, rocket emoji, and it's all merged and done.
15:01Our work went from a 100% manual, take all day you have to sit at your computer, to you just come in at the beginning of the day, answer a few questions, and at the end of the day, you hit merge, and you're good to go. This is the thin loop.
15:14This was what makes it so powerful. If you look down below, there is a Google Doc.
15:20The Google Doc has several prompts in it. It has prompts for setting up each of the three skills as well as a prompt you can give to your agent, whether it's Clawd Code, Codex, or whatever to set up the Slack, Discord, linear, whatever you're using and get the entire system connected in place. This isn't gatekept behind an email or anything.
15:40It's completely free. Just click the link. You don't have to do anything.
15:42It's just a Google Doc you can copy and paste into your agent. We don't gatekeep here on the FinFam channel. AI, especially with Fable five and GPT five six, has become so smart.
15:54There is no more need to babysit every step of the way. Basically, every part should be automated.
16:01Right? And we're still doing manual work. I'm working on now figuring out how to automate even the manual work.
16:07How can we automate coming up with ideas? That's what I'm building out right now.
16:11I wanna get the spec step even easier and even less human intensive. And as AI becomes smarter, it might even already be at that point. We don't even need to merge it ourselves.
16:21We can probably just trust it to merge it for us. But right now, I still want these two manual steps beginning of day, end of the day. But all that hard work in the middle of the day, that's done.
16:29You don't have to worry about it anymore. That's all handled by the thin loop. All the tools you need for this, completely free.
16:36I'll link them all down below. The prompts to set this up, completely free, link down below. You have nothing to lose by setting up this loop.
16:43It just saves you tons and tons of time and helps you get done way more. You take this a step further. You start five or six different projects.
16:51You just come in the morning, answer specs for all six of them. They work autonomously all day. At the end of the day, you have six projects moving forward without your work all the time.
17:02Everyone on the Internet's been talking about coding loops. Now you know it. Now you can implement it.
17:07And if you implement this, you are ahead of, like, literally 99.99999 of people. I'm not even joking.
17:15Even the most hardcore vibe coders right now are not setting up loops like this. Do yourself a favor. Block off half an hour.
17:23Go through this again. Take the prompts from down below. Give them to your agent.
17:27Get this set up. If you wanna take it even a step further, you can copy the link of this video up above or hit share down below.
17:35Give it to your agent. Say, hey. Look at the transcript of this video and set it up for me.
17:38Like, that's actually probably the easiest way to set this up. If you learned anything at all, make sure to leave a like down below. Turn on notifications and subscribe because all I do is make amazing videos about AI.
17:51It's an absolute honor and a pleasure to be helping you out, to be educating you, to be working with you on these things. I'm discovering new things every day. All I do is discover things then share it with you.
18:01So I hope you're enjoying it. Hope you're learning something from it. I absolutely love this stuff.
18:05It is so much fun, and I hope you're having fun with it too. And I'll see you in the next video.
The Hook
The bait, then the rug-pull.
The title makes the sweeping claim, then immediately backs off into something more useful: prompting isn't gone, it's just no longer the whole job. What follows is a demonstration of the loop that replaces it — three named skills, wired to a tracker and a chat app, doing the prompting and testing that used to require a human at the keyboard all day.
Named ideas worth stealing.
02:57model
The Finn Loop (spec / build / review)
- Spec
- Build
- Review
- Merge
A three-skill loop where a spec skill turns loose ideas into scoped, acceptance-criteria-bearing issues; a build skill runs on a timer to code each issue; and a review skill runs on a separate timer to test, package, and route finished work for a one-click human merge.
Steal forany recurring dev workflow (feature builds, content pipelines, QA passes) where the bottleneck is a human re-prompting the same three steps over and over
How they asked for the click.
VERBAL ASK
15:18link
“There is a Google Doc. The Google Doc has several prompts in it... This isn't gatekept behind an email or anything. It's completely free. Just click the link.”
Ungated Google Doc with copy-paste setup prompts plus a public GitHub repo, referenced directly in the description — low-friction CTA with no email capture.
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.
