05:23Nate Herk | AI Automation · Demo
GPT-5.6 Sol Made an Entire Video From One Prompt
One prompt, nine AI agents, a $318 bill — and a lesson about when "maximum effort" actually pays for itself.
July 9thThe argument in one line.
Codex's browser and computer control let it click, type, and navigate like a human, which makes it useful exactly where APIs don't exist, but an API is still faster, cheaper, and more reliable whenever one is available.
Read if. Skip if.
READ IF YOU ARE…
- You build or ship web apps and want a way to stress-test the UI for edge cases before real users hit it.
- You have a recurring browser task (downloading statements, checking a dashboard, posting content) behind a login with no API.
- You're evaluating Codex, Claude Code, or similar CLI agents and want to know what browser/computer control actually looks like in practice.
- You're curious about the difference between browser use, computer use, and deterministic macro scripts and when each one is the right tool.
SKIP IF…
- You're looking for a deep technical explainer of how vision-based browser agents work under the hood, not a product demo.
- You need coverage of other browser-agent tools (this video is Codex-specific).
The full version, fast.
Codex's in-app browser lets the agent see and control a browser using vision instead of an API, and it remembers logged-in sessions so it doesn't need to re-authenticate every run. The video walks through three use cases: autonomous QA testing that finds real UI bugs (including a mobile-responsiveness failure), a one-shot 'skill' that logs into a banking dashboard, pulls statements, and saves them into a folder, and a YouTube-to-X-article pipeline that drafts a formatted post with embedded video screenshots. A newer computer-use plugin extends the same vision-and-click approach to native desktop apps, not just the browser. The through-line is a decision order: reach for an API first, fall back to a deterministic macro script if the clicks never change, and only use browser/computer use when the task genuinely requires visual judgment step to step.
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 – 01:56
01 · Codex browser basics and the annotate loop
Introduces the Codex desktop app and its in-app browser, explains that most tools get connected via API or plugin first, and demos the annotate feature for flagging UI bugs (overlapping fields, misaligned boxes) on a local test website.
01:56 – 05:50
02 · Codex takes the wheel: autonomous QA testing
Codex takes control of the browser and runs an open-ended QA pass on the test form, entering data, hitting validation errors, and switching to mobile view. Headless vs headed mode is explained along the way.
05:50 – 09:12
03 · Real bugs found, and how far to push it
The QA run surfaces two genuine data-integrity bugs (bad contact data getting through, a country-code field silently resetting) plus a mobile responsiveness failure, and Nate makes the case for AI-driven QA over manual guessing at edge cases.
05:50 – 10:01
04 · Building a bank-statement download skill
A one-shot request teaches Codex to log into the Relay dashboard, find two accounts, download their statements as CSVs, and file them, saved automatically as a reusable skill that can later be scheduled monthly.
10:01 – 10:53
05 · Password manager, safely
Because Relay logs sessions out for security, Nate imports credentials via a CSV into Codex's own password manager rather than pasting them into chat, then reruns the skill to log back in and pull the statement.
10:53 – 12:21
06 · The API-first decision order
Nate lays out the hierarchy explicitly: reach for an API first because it's fastest, cheapest, and most consistent; fall back to a deterministic macro script if the clicks never change shape; use browser use only when the task genuinely needs visual judgment at each step.
10:01 – 12:38
07 · YouTube video into a drafted X article
Codex is asked to turn a just-uploaded YouTube video into a formatted X article draft, including pulling screenshots from the video, while Nate opens a second session to confirm the saved X login still works by scrolling the feed live.
12:38 – 13:57
08 · Computer use on the actual desktop
Nate installs the computer-use plugin and asks Codex to open the Glido desktop app and toggle a Bluetooth setting. Codex declines to touch OS-level permission prompts but completes the in-app change, with a visible blue screen border marking when it has control.
13:57 – 16:27
09 · The article finishes, and the wrap-up
Back in the browser, Codex finishes drafting the X article: title, body, a generated thumbnail, and video screenshots dragged into place. Nate closes on the idea that APIs cover 95% of automation, browser use is the fallback worth having, and skills compound when chained together.
Lines worth screenshotting.
- Codex saves a browser login session after you sign in once, so it doesn't need to be told your credentials again on later runs.
- An AI QA pass on a test form found two real data-integrity bugs a human review missed: invalid contact data got through, and switching the country code to UK silently reset to US on re-edit.
- Headless browser use runs in the background so you can keep working, while headed mode lets you watch the agent click in real time.
- The decision order for automating anything is API first, then a deterministic macro script if the clicks never change, and browser/computer use only when the task needs visual judgment at each step.
- Codex can import a CSV of site, username, password, and notes into its own password manager, so credentials never sit in chat history.
- A password-protected skill like downloading bank statements should be run and closely watched at least ten times before it's trusted unsupervised, because a vision-based agent can misclick.
- Using browser use instead of the X API to draft an article was cheaper in this case even though X has an API, because the API charges per use and this ran on an existing Codex subscription.
- Computer use extends the same vision-and-click approach from the browser to native desktop apps, and the screen shows a blue border whenever Codex has taken control.
- A finished browser-use skill (like downloading a monthly statement) can be turned into a scheduled recurring task, so a five-to-ten-minute chore disappears from the calendar entirely.
- Codex will refuse to proceed and stop itself if a task hits an admin password prompt or a security-sensitive permission it can't safely interpret.
Try the API first, browser use last, in that order
WHAT TO LEARN
AI browser and computer control genuinely works for QA testing and login-gated tasks with no API, but it's still the slowest and least reliable rung on the automation ladder, not the first one to reach for.
- Codex remembers a browser login after you sign in once, so recurring tasks behind a login don't need credentials re-entered every run.
- Turning an agent loose on your own UI to 'try to break it' surfaces real bugs, like a field that silently resets, faster and more thoroughly than manual click-through testing.
- Headless mode runs an automation in the background so you can keep working, while headed mode lets you watch it act step by step.
- A one-shot instruction can become a saved, reusable skill, and any skill can later be turned into a scheduled recurring task.
- Store credentials in a password manager the agent can pull from, not pasted into chat history, especially for anything touching a bank login.
- Watch a new automated skill closely for at least ten runs before trusting it unsupervised, since vision-based clicking can misfire.
- Reach for an API first for speed, cost, and consistency; use a deterministic macro script if the clicks never change; save browser or computer use for tasks that genuinely need visual judgment.
- Computer use extends the same approach beyond the browser to native desktop apps and OS settings, with a visible on-screen indicator whenever the agent has control.
- APIs still cover most automation needs; browser use is the tool worth having in reserve for the remaining cases with no API and no fixed click pattern.
Terms worth knowing.
- Browser use
- An AI agent capability that controls a real browser by looking at the screen and deciding where to click and type, instead of calling a website's API.
- Computer use
- The same vision-and-click approach as browser use, but applied to the whole desktop: native apps and system settings, not just a browser tab.
- Headless
- A mode where an automated browser session runs in the background with no visible window, so the user can keep working on something else at the same time.
- Headed
- A mode where an automated browser session runs in a visible window so the user can watch the agent act in real time.
- Skill (in Codex)
- A recorded, reusable sequence of steps an agent learned once by being told what to do, which can then be re-run or scheduled without re-explaining the task.
- Deterministic macro script
- A fixed, hard-coded sequence of clicks at the same pixel positions every time, with no vision or reasoning involved, used when a task never changes shape.
Things they pointed at.
00:00toolCodex
06:25toolRelay
12:43toolGlido
10:01toolX (Twitter)
Lines you could clip.
04:00
“Would you rather have something that has been not tested at all, or would you rather have something that has been tested a hundred times already by an AI agent?”
08:15
“Your first call should always be to go for an API. It's the fastest. It's usually the cheapest. It's usually just the most consistent.”
15:05
“Pretty much API will handle ninety-five percent of your automation things that you need.”
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.
Codex's browser use is probably the best that I've ever tried before. It can literally do anything on a browser or on your actual local computer, and if you need to be signed in for something, you just sign in once and Codex will save it. So possibilities are endless.
You can actually automate anything Let me show you guys how to set it up, how easy it is, and a few good use cases. Alright. So I'm using the Codex desktop app, which is just honestly the main way that I like to drive Codex.
It's super, super slick. And we get the browser to pop up on the right hand side, which I'll show you guys in a sec. So luckily, we live in a world now where most tools that we need to use have an API.
So it's much easier to just connect codecs through the API, or if we just go to the plugins, there's hundreds of plugins in here. Every once in a while, we don't have an API, and you can do that with browser use. But before I show you an automation like that, let's just take a look at this example where you might be building a website, you might be building some sort of app, and you need a browser, an agent to actually test through things.
If you guys watched the recent video I did on like building an AI SaaS in one day, then this was actually from that demo where I had a browser agent get spun up and test the heck out of our app, and it did 85 focused automation checks with real browser workflow testing, means it was clicking around, it was typing things, it was hitting buttons, and it was trying to break the app, and it found a ton of bugs, and then we were able to just fix them.
So in this example I have a super simple website spun up here on the local host. It's a form submission as you can see, and there's a few issues before we actually go ahead and start testing this thing.
You can see like this spacing is weird, this thing is overlapping, and so what you can do is you can click on this annotate button, and that lets you choose very specific elements to actually change. So I could click right here on this phone number box, and I could describe, hey, this is kind of like overlapping.
It's out of bounds. It's covering up the company box, so I need you to fix this. And then when you shoot that off, it actually goes over here into your chat, and then you can make another annotation like, okay.
So this whole box isn't really aligned on the same y axis as number one and number three, so you need to fix that as well. And then those annotations are saved over here, and we can just go ahead and shoot them off. So that's kind of like a lovable style or like a claw design style thing that you can do with the in app browser in Codex.
What else is really cool about this is that you can actually just drive this thing. So you can go to Google, you can search for Grand Canyon images, you can go to all, you can go to different links if you want. You can use the browser right here while you have Codex open, but of course, Codex can also just take control of it.
Now we can see right here is my mouse, but also this is what Codex's mouse looks like, and that's how you know it's now sort of getting ready to take control of the browser. Okay. So now that those changes have been made, let's actually start testing out our UI.
I wanna see things that maybe me as a human, I would maybe go through here and test like five or six edge cases, but we can see how codecs can do it way quicker and way more. Okay. So you have the UI open.
I wanna make sure that there are no bugs. I wanna make sure that this thing can't break. So what I want you to do is use your browser use and just test the heck out of this thing.
Try different things. Try your best to break it, and let me know what bugs you find and what things we need to fix. And so by the way, while this is running, there's a difference between browser use being headless or headed.
Headless means it's running in the background, so you can keep working in the foreground and you won't actually see it going on, but it can run a lot of things in the background. But if you want it to be headed, that's basically where you're able to see it. So we're probably gonna be able to see some things right here, but if you wanted this to just work for a few hours for you headless in the background, you could ask it to do so, and then it wouldn't disturb whatever work you're doing.
So if you ever hear that terminology, that's what it means. So there you go. You can see that the mouse is moving around right now.
It tried to click continue, and then it says first name is required, answer a valid email address, and enter a 10 digit phone number. And now you can see it just entered in some information, and it was able to hit continue. And it's just gonna keep going through this QA check.
We're validating that some of these fields are required options and that the continue button won't actually let it move on without filling those in. And by the way, the reason you're seeing some of these UI bugs is because I asked this chat to, like, make there be a few UI things to fix because I wanted to show you guys the annotations.
So just ignore that. Mainly, what I'm trying to show you guys now is the actual browser use QA function. So here you can see as it's clicking around, as it's trying to navigate this UI, it already said the core click path mostly works, but I've confirmed two real data integrity problems already, which is that obviously invalid contact data does get through and changing the country code to UK resets to US when you return to edit.
I'm now testing keyboard submission and restart behavior, which often exposes bypasses the click path misses. So think about it like this. No matter what you get, you're gonna wanna test it.
But would you rather have something that has been not tested at all, or would you rather have something that has been tested a 100 times already by an AI agent? Especially if you tell the agent to try to break it, it's gonna find some things that need to be fixed. No matter how good you are at trying to predict edge cases, when you push an app into production and users start using it, people are weird.
People are unpredictable, so they're gonna do things. And so this agent is able to hopefully simulate weird humans and just find things that you might not have thought of. You can see here it even switched this to mobile view to still make sure that everything's working.
And look at this. In mobile, it found a few failures in responsiveness, so that isn't something that I yet had tested. Okay.
So this thing finished up now, and you can see that we have a bunch of things that passed, but a bunch of things that also failed. So it was able to find all of these bugs because it was testing the UI, and it didn't even do it that long. If we wanted to make this even harder, we could do a slash goal and we could say, hey.
Don't stop until you've tried a 100 different unique scenarios of, you know, UI edge cases and then come back to me. But it still found a lot of things that were broken, and now all we'd have to do is say, okay. Cool.
Go implement those changes. Go fix all those bugs. Okay.
So let me show you guys another example. This is when you maybe have some sort of platform where you want to be able to, like, download statements or something, but they don't have an API. So you can actually interact with it with Codex's browser use because it basically uses vision and then AI to analyze, like, what it's looking at and where to click.
And I would I just wanna show you how easy it actually is to build these. All I said was, hey. You know, I wanna build this skill, blah blah blah.
What would be helpful? And you could record a quick Loom. You could send screenshots with arrows, but you actually don't have to.
You can basically just describe pretty clearly what you need to do. So what happened here is it opened up Relay, I signed in, and it saved that session. Now I said, okay.
In the Relay dashboard, you're signed in. What I need you to do is go to the dashboard, click on accounts, find the statements, click on these two accounts, download them as CSVs, and then put them into this folder.
It And was able to do that on one shot. I didn't have to give it any feedback, and it downloaded them and saved that whole flow as a skill. Now this is super helpful because now I could, at the end of the month, just set this up as a scheduled routine because I could set a scheduled routine here and say, hey.
Use this skill on the most recent, you know, month statement in Relay. And for the most part, Codex is going to save your sessions when you're logged in. However, there are some limitations like the fact that Relay is going to pretty much boot you out because it's, you know, it's a banking platform.
It's going to be secure and boot you out. So look at this here. I asked it to do this again, and it said, hey.
Relay's open at the login screen, but you have to sign in again. Now what's really interesting that you can do is you can actually open up your settings. You can have a password manager inside of Codex, and you can see this goes to your browser, and now you can go to import them so that Codex can actually fill that out for you.
And that way you're not putting it into the chat history or anything like that. You're saving it more securely. So all you have to do for that is create a CSV file that looks like this.
I've got the name, the URL, the username, the password, and any notes, which in this case are empty. I imported that here right here as a file, a CSV file, and now we have relay.com password.
Go ahead and try this again. In the password manager for the in app Codex browser, you should be able to log in now and then run the skill on June. Alright.
So over here now, you can see the browser has taken control, and it is going to put in my email and my password. Now if this asks me for a two factor authentication code for my phone or something, then I'm obviously not gonna be able to do that. I have to do that manually.
But, hey, if I was on a Mac and my text went there and I used computer use to do that, technically, you would be able to automate that whole thing, but I would say you probably wanna be careful about stuff like that. But as you can see, it was able to pull the passwords from my password manager, paste those in, and now it should be able to log in to Relay for me.
You can see here that the mouse has moved over to accounts. It's then going over to statements, and it's gonna be able to download these two statements for us. As you can see, it's pretty cool that it was able to figure all this out.
Remember, I've only ran this skill once, and all I did was instruct it with natural language to do this. Now realistically, is that the way you should do it, especially with something like a bank account?
No. What you should do is have it do the skill.
You sit here and watch it, and have it do that, like, at least 10 times where you're very closely watching it to make sure nothing goes wrong, and you're making sure the script in the skill is super strict. Because at the end of the day, it's using vision, it's using AI, and that's how it's deciding what to click and what to do.
So really the way that I think about it is when you want to automate something, your first call should always be to go for an API. Like, that's what you wanna do. It's the fastest.
It's usually the cheapest. It's usually just the most consistent. Now if there's no API, that's where you would maybe say, okay.
Cool. Well, now let me see if I could use, like, a deterministic, you know, like, macro script.
Right? And that's where you'd basically be able to have yes. You know, it'd be more of a browser use because you have a mouse that's clicking around, but it's not like your mouse needs reasoning.
Your mouse doesn't need to look at the screen, figure out where to click, and based on the next UI that pops up, where do I click again? This is basically more like, okay. I have to click on this pixel, then this pixel, then this pixel every single time.
That's something that you could do for much cheaper and much safer by just programming a macro. And that's not that hard either.
You just ask Claude or Codex, hey. Help me figure out how to make, like, a deterministic macro script to just click on these pixels in that order every single time. But if you can't do that every single time because there is an element of vision or reasoning, then you need to come in here and you need to do something like some browser use.
And luckily, Codex has your back. I've tested a lot of different apps and different CLIs and different things for browser use, and so far, Codex is just really solid. So as you can see now in my downloads, this is the statements that it just downloaded as a ZIP file, and it basically took these and it put it into my HERC two project.
If I go in here and I scroll down to statements and I go to probably June yes. June, you can see right here, it put those in here in the correct spot. Okay.
So that was an example where we needed to save a password somewhere. Right? But I've done this with things like school.
I've done this with things like x. I've even done this with things like Instagram that don't make you constantly re sign in because it saves that session. So let me show you another example.
I'm gonna go over here to YouTube, and I'm going to grab the URL from the video that I uploaded earlier today. I'm gonna go back into Codex, paste in that URL, and say, I need you to turn this YouTube video into an X article for me and then use browser use to go ahead and format it and put it into an X article as a draft, and then I will go ahead and review it.
So I know some of you guys are probably thinking, why don't you just use X's API for that? You can, but it's a little bit weird with the formatting. It's also weird with sometimes adding things like media or thumbnails for some reason, at least with my testing that I used to do.
And it's also it charges you. Right? Because you have to pay x per usage in order to do something like that.
And so because this is just part of my Codec subscription, I can just run this skill, and it will go ahead and format everything for me and take care of it. I even have this skill worked out where it can go ahead and open up my YouTube videos, and it can take screenshots of specific moments and put those into the article too where it makes sense.
So obviously, is a bit of a loaded process because it has to do a few steps before it actually has the article ready to put into x. So while that's happening, let's just open up a new chat, and let's see if our x session is there. Can you open up a browser?
I wanna see it right here in the app, and just go to X and scroll around a little bit and show me if there's anything new that has just come out, like in the AI space. Just scroll on my X feed.
And so because this was a brand new session, we can actually see if X has already signed in and if it's able to interact with things.
Cool. So it just opened up x. Let me get my mouse out of here.
You can see clearly that this is already signed in as me and my feed is visible, and now it is going ahead and it's starting to scroll on the x page. So just start to think about already, how could you create some sort of skills out of this and then schedule these as tasks? So maybe every morning, if you wanted it to scroll through Instagram and things like that or scroll through your own profile or mark things as read or unread, you could totally go ahead and do that no problem because you can set up the scheduled tasks right in here and use browser use skills that you've already set up.
So you can see two things that I already noticed was Grockbot and Grock 4.6. So this is an interesting case though because there is an API, but using the browser use is actually cheaper. So that's why in this case, we decided to do it and test it out.
Now what about computer use that you guys have also probably heard? These are basically the same thing. It's still gonna use vision.
It's still gonna use AI. But the difference here is that the browser is basically things that are on the Internet or things that you would type into a browser like Chrome, but the computer use are things that might be on your actual computer. So changing your computer settings, opening up desktop apps of things.
So let's go back into Codex while we're waiting for this x article to finish up. Let's see how this is going. It is still breaking down and turning it into an article.
Let's see if we can do some computer use. So one thing you will have to do though is you'll to go to plugins and you'll have to actually install computer use, which is just as simple as typing in computer use and hitting install, like, literally two seconds. And then, hey, Codex.
I need you to use computer use to open up my desktop app for Glido, and I just want you to go to the settings and turn on the ability for it to allow and use, like, Bluetooth devices. So just go ahead and get that set up for me. And so this is a little bit different.
Right? Because it's not gonna open up your in app browser. It's going to actually kind of show your screen being taken over.
It said, I'll stop if Windows asks for an admin password or presents a security sensitive permission that it can't safely interpret. It shouldn't run into any of that, but it's good that it sort of has that guardrail baked in. Interesting.
Okay. So it said Bluetooth access is a privacy permission, so the computer use won't let me actually do that. But what it said it's gonna do is open up Glido.
As you can see, I didn't open that up. It opened up Glido for me. And it doesn't look like on my recording, you guys can actually see this right now, but my screen kind of has, like, a big blue hue around the edges, so you will clearly know if Codex is using your computer.
And there you go. You can see that it actually turned on the include Bluetooth devices button. And I think it got confused because I think at first, it thought that I was messing with my actual computer settings rather than, like, an in app settings, so it thought that that was a security thing.
But it looks like it figured that out on the way. And I think the computer use thing is pretty interesting because you can remote into your codex from your phone. So I can control all of these sessions on my phone.
And what I could do is on my phone, I could say, hey. Computer use. Go ahead and change my settings or go ahead and do something on a desktop app that's on my PC that I'm actually not sitting in front of, and then you could control your computer from your phone.
So, anyways, we're back in the session where it's creating that x article. You can see that it is actually creating some thumbnails for the actual article. So hopefully, we're getting close to the point where it's gonna actually open up x and start to put stuff in there, but I'll check-in with you guys when we get there.
Okay. So it just decided to open up x. You can see that it's going to the drafts in my signed in x, and then it's going to go ahead and format this new article, and then we'll take a look.
It's clicking on the plus button. Man, I think it even just, like, resized the page a little bit. It was getting a little picky.
In goes the title, and then it just pasted in the entire content of the article. And now it's uploading this thumbnail, which I don't think looks very good.
That part of the skill has not been refined at all, but it's still cool that it was able to make that thumbnail and then go ahead and put it in there. So I literally just have to make sure that it looks okay and I like it and I can publish it. Now I know what a lot of you guys are probably thinking when it comes to this browser use stuff.
It's like, what's the point, Nate? Like, where's the value?
And, honestly, I understand where you're coming from. And that's why I wanted to show you guys this piece where it's like, pretty much API will handle 95% of your automation things that you need.
Then And a lot of the browser use opportunities might just be a script, but then when you need it, if you have this in your back pocket, it's good. And you also might think, okay. Cool.
But, like, how much time does this really save? This probably saves me, like, maybe five to ten minutes, like, realistically. But what's cool about it is that I can basically have this pipeline now where I have a bunch of these browser use skills.
And so when I need to do something, I just open up Codex, I shoot off that skill, and I can go back to the other task that I was working on. It kind of just, like, helps you do more without context switching as much. And as you start to stack more and more of these pipelines and combine them together, you can get some really cool things to happen when you start to chain together these skills.
And look. This one actually did it. It basically did the thing where I said, it opened up the YouTube video.
It took screenshots of it, and now it's going ahead and it's planting some screenshots from my video in the article. So if that doesn't prove the capabilities of this thing being intelligent, take screenshots, look at the page, know where to click, know what to do, then I don't know what else will. Besides the fact that I've had this thing play chess, I've had it play games, I've had it set a world record on Tetris, it can do a lot of cool things.
Look at this. You can see that it even took the image and drug it all the way down to where it actually fits in the article.
I haven't actually seen it do that before live. That was pretty cool. And this thing is just still going at it.
But that is going to do it for today's video. Hope you guys enjoyed it. Hope you learned something new.
And if you did, please give it a like. It helps me out a ton. And as always, I appreciate you guys making it to the end of the video, and I'll see you on the next one.
Thanks, ever
The Hook
The bait, then the rug-pull.
Nate Herk opens with the claim that Codex's browser control is the best he's tested: sign in once, and it remembers the session for every run after. What follows is three back-to-back demos, from QA-testing a broken form to quietly drafting a social post, that either back that claim up or show exactly where it runs into limits.
Named ideas worth stealing.
10:53list
The automation decision order
- Use an API if one exists
- Use a deterministic macro script if the clicks never change
- Use browser use / computer use only when the task needs visual judgment
A three-tier hierarchy for deciding how to automate any task, in order of speed, cost, and reliability.
Steal forany internal tooling or client-automation decision where a no-code or AI shortcut is tempting but an API already exists
How they asked for the click.
VERBAL ASK
19:58subscribe
“if you did, please give it a like... I appreciate you guys making it to the end of the video, and I'll see you on the next one.”
soft, brief sign-off ask for a like at the very end, no hard sales pitch
FROM THE DESCRIPTION
PRIMARY CTAWhere the creator wants you to go next.
AFFILIATECommission earned if you click.
OTHER LINKSAlso linked in the description.
Visual structure at a glance.
