The argument in one line.
A hundred hours of daily use with an AI agent boils down to nine repeatable habits — the right model, redundant agents, and cross-device access — that separate a real AI employee from a chatbot that stalls out on hard tasks.
Read if. Skip if.
READ IF YOU ARE…
- You're already running an AI agent tool (Claude Code, an autonomous assistant, or similar) and want more consistent, autonomous results from it.
- You're a solo builder juggling multiple devices who wants an agent to operate machines you're not sitting in front of.
- Your agent has been slowing down, stalling mid-task, or going down without warning, and you want to know why.
- You're deciding which model to route an autonomous agent through and want a real cost-vs-reliability comparison.
SKIP IF…
- You've never used an AI agent before and want a from-scratch setup walkthrough — this assumes an existing install.
- You want deep coverage of a specific rival agent platform — the advice here is framed around one product.
The full version, fast.
Running an AI agent daily for months surfaces the same handful of failure points: picking a model that finishes tasks instead of stalling halfway (Opus, at real cost, versus cheaper ChatGPT or GLM 5.2 fallbacks), treating a single agent as a point of failure, and over-isolating the agent with its own hardware and accounts out of overblown security fears. The fix is a small set of habits: run at least two agent profiles on different models so they can monitor and repair each other, connect the agent across devices with a free mesh VPN so it can operate an entire machine fleet unattended, regularly prune old scheduled jobs since they're the top cause of slowdowns, and run a daily 'reverse prompt' interview so the agent surfaces its own next tasks instead of waiting to be told what to do.
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 – 00:28
01 · Cold open
Chatbot-vs-employee framing and the promise of nine lessons from 100+ hours of use.
00:28 – 03:28
02 · Choosing the right model
Opus recommended for reliability despite ~$40/day cost; ChatGPT 5.5+ as a usable fallback; GLM 5.2 as the cheap option.
03:28 – 08:00
03 · Running multiple agent profiles
Why a second (and third) agent profile on a different model acts as a failover that can diagnose and fix outages; includes a HubSpot-sponsored AI agent course plug.
08:00 – 10:14
04 · Security — stop over-isolating your agent
Argues against buying separate hardware/accounts per agent; the agent only executes the prompt it's given.
10:14 – 11:49
05 · Using the right platform
Desktop app for deep multi-profile work, a chat app for on-the-go deep tasks, iMessage for quick prompts.
11:49 – 14:19
06 · Improving performance
New chat-app formatting (tables, bold) for daily briefs; stale cron jobs named as the top cause of slowdowns and wasted tokens.
14:19 – 16:45
07 · Tailscale for cross-device control
A free mesh VPN lets one agent SSH into and run every other device in a fleet without a monitor on each one.
16:45 – 19:25
08 · Reverse prompting and the Kanban board
A daily interview where the agent asks the user questions to surface new tasks, which then get triaged into a Kanban board.
Lines worth screenshotting.
- Opus is described as the only model that reliably finishes an agent task start to finish, at a reported cost of roughly $40 a day — about $1,400 a month — in API spend.
- GLM 5.2 is positioned as the budget option: more robotic than Opus or ChatGPT, but still capable of finishing agent tasks at a fraction of the cost.
- Running only one AI agent creates a single point of failure — a second agent on a different model can detect when the first goes down and fix it automatically.
- In this workflow, a separately configured agent instance is called a 'profile,' and spinning one up is as simple as asking an existing agent to create a new profile on a different model.
- The fear that an agent could leak private data or contact the wrong person is dismissed as overblown: an agent only executes the prompt it's given, so isolating it onto separate hardware and accounts mostly adds friction without adding real safety.
- Old, forgotten scheduled jobs are named as the number one cause of a sluggish agent — regularly pausing unused jobs restores performance and cuts token spend.
- Tailscale, a free mesh VPN, lets one agent SSH into and operate an entire fleet of other computers without ever connecting a monitor to them.
- A daily 'reverse prompt' — having the agent interview the user each morning about priorities and stress points — is presented as the way to keep surfacing new tasks the agent can take over.
- New agent-generated task ideas get triaged into a built-in Kanban board reachable with a single terminal command.
- Chat-app formatting upgrades (tables, bold text, structured paragraphs) turn scheduled jobs into readable daily briefs, like a ranked AI-stocks table delivered every morning.
Nine habits that turn an AI agent into an employee, not a chatbot.
WHAT TO LEARN
Reliability, redundancy, and a few daily rituals matter more than any single feature when you're trying to get real autonomous work out of an AI agent.
02Choosing the right model
- The most reliable model for finishing agent tasks isn't the cheapest one — budget accordingly if the task actually needs to get done, not just attempted.
- A cheaper or free model can still be 'usable' for agent work even if it isn't the top-tier option, so cost-conscious users have a real fallback.
03Running multiple agent profiles
- Treat a single AI agent as a single point of failure — a second agent on a different account or model can monitor and repair the first when it goes down.
- Spinning up a second agent instance is as simple as asking an existing agent to configure one, no separate setup process required.
04Security — stop over-isolating your agent
- Security concerns about giving an agent broad account access are frequently overblown — an agent executes only the prompt it's given, and personal accountability matters more than account isolation.
05Using the right platform
- Match the interface to the task: a full desktop app for deep multi-agent work, a mobile chat app for on-the-go deep work, and simple messaging for quick one-off prompts.
06Improving performance
- New formatting features (tables, structured text) in chat interfaces make scheduled agent output — daily briefs, rankings, reports — dramatically more usable.
- Stale scheduled jobs are a leading, invisible cause of a slow or unreliable agent — audit and prune them on a regular cadence.
07Tailscale for cross-device control
- A free mesh-networking tool can let a single agent reach and operate every device you own, turning idle machines into usable compute without needing a monitor on each one.
08Reverse prompting and the Kanban board
- A daily structured check-in, where the agent interviews the user instead of waiting for instructions, surfaces automation opportunities the user wouldn't have thought to ask for.
- Routing agent-suggested tasks into a visual task board keeps a growing backlog of automation ideas organized instead of forgotten.
Terms worth knowing.
- Agent profile
- A separately configured instance of an AI agent, each running its own chosen model, so a user can operate more than one agent at once.
- Cron job
- A task scheduled to run automatically on a recurring basis, without a person triggering it each time.
- Tailscale
- A free tool that creates a private network linking a person's devices, so an agent on one machine can reach and operate the others.
- Reverse prompting
- Flipping the usual direction of a prompt so the AI asks the user questions first, then uses the answers to decide what tasks it should take on.
- Kanban board
- A visual task board with columns like to-do, in-progress, and done, used here to track and assign tasks to an AI agent.
Things they pointed at.
00:44toolClaude Opus
02:43toolChatGPT
02:44toolGLM 5.2
Lines you could clip.
00:44
“There is no model better than Opus. It is the absolute best agentic model ever made.”
01:37
“Even if it loses a leg halfway through a marathon race, it is going to crawl its way to the end of the finish line.”
09:13
“It is an AI. It's not sentient. You give it a prompt. It does the prompt.”
13:17
“Much like laws and rules, very easy to make new ones. It's very hard to take them away.”
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
00:00Hermes agent is the most powerful software ever made. When used correctly, you literally have your own full time AI employee. Here's the thing though.
00:09When used incorrectly, it's basically just a normal chatbot. In this video, I will go over every lesson I've learned from using Hermes agent for hundreds of hours the last four months.
00:22If you stick with me into the end, I promise you, you will be 100 times more productive. Now let's lock in and get into it. I have a ton of lessons to go through in this video, but let's start with one of the number one asked questions I get, which is which model should I be using for Hermes?
00:37Well, I have an official recommendation for you here. If you want the absolute best in class performance, there is no model better than Opus.
00:47It is the absolute best agentic model ever made. And now I know what you're gonna say. Wait, Alex.
00:51Isn't that API pricing? Yes. Yes.
00:55It is. I have spent $1,400 the last month on Opus credits for my Hermes agent alone.
01:01Yes. I'm spending a tremendous amount. Yes.
01:03On average, I am spending about $40 a day. Yes. I was in Cabo this one day where I didn't spend anything at all, but I am spending a tremendous amount on Opus for Hermes' agent, but for good reason.
01:15It is the only model on planet Earth where when I plug it into Hermes' agent, I know for a stone cold fact when I give my prompt to it, it's going to finish the task no matter what. The way I like to think about is this, when you give Opus a task to do in Hermes agent, even if it , it is going to crawl its way to the end of the finish line.
01:39With every other model, it stubs its toe halfway through the race, and then it rolls over and gives up. Opus, when used in Hermes, no matter what, it finds a way to complete your task.
01:51And for me, that is worth a tremendous amount of money. I am willing to spend double what I'm spending now in order to use Opus and Hermes because it runs my business so much. But I get it.
02:01Not everyone can spend thousands dollars a month on Opus, so you have other options. If you're already paying for a ChadGBT subscription, which most people are, you can plug that in.
02:11ChadGBT 5.5 and later has been very good with Hermes.
02:16It's not Opus level. It still trips up. It's still not as warm.
02:20It's still not as fun to talk to. It's still not as great at tasks, but it's usable.
02:25Everything before five five was not usable. It was quite frankly horrible. Now if you wanna save even more money, GLM 5.2 is also a great model.
02:35You can plug it in. It's a fraction the price of both of these, and it'll still get the job done. It's a little bit more robotic than Chad GPT and Opus, probably because it's distilled from these other two.
02:45But it's still very good, and it is very, very cheap. So if you're an ultra money saving mode, I'd recommend GLM 5.2. So it's really up to you.
02:52You got a menu. Do you go with the best in class, the filet mignon Opus where you can be sure every task will be done. Do you go with Chad GPT?
03:01Do you already have a subscription Chad GPT? That's fine. Plug it in.
03:05You won't have to spend more money. Or if you wanna go to UltraSamo, GLM. Listen.
03:09If you're running a serious online business and you're making revenue, I say spend the money, go with Opus. Your job will get done. The task you give will get done, and that kind of peace of mind is super important.
03:21So my official recommendation is Opus. If you already have an account, just go chat g p t. Cost savings, go GLM 5.2.
03:28Second lesson I learned, and this is a massive one that literally 100% of people watching this video should do, you need to have at least two Hermes agents running at all times. Only having one is not enough. Let me walk through this for you.
03:41So Hermes, I named my first Hermes agent. Hermes, I just like that name. Hermes is my main agent.
03:47It's running off Opus just as we just talked about, but I also have a second agent, GPT. Mez. Why do I have a second one GPT?
03:54Mez, obviously, it's running off Chad GPT. The reason why you need at least a second and sometimes third and fourth Hermes agent is they all watch over each other. Hermes isn't perfect.
04:06It breaks at different times. I find Open Claw breaks a little bit more. Hermes breaks less, but it still does break.
04:13And when it breaks, you need failovers. You need ways to fix it. So just yesterday, my account, my ChaiGBT account connected to GPT.
04:22Me's went down for some reason. The token expired or something went wrong. If it was my only Hermes agent, I wouldn't know what the hell to do.
04:29I wouldn't know how the hell to fix it. I'd probably panic. I'd probably be like, oh, my best friend's gone.
04:33I don't know where he went. But when you have multiple Hermes agents, they can all monitor, watch over each other, and fix each other automatically.
04:43So as you can see here, when GPTimes went down, I took a screenshot, gave it to Hermes, my main agent, and said, my other agent, gpt.
04:50Mez is down. Give me errors. Can you fix it?
04:53And literally, as you can see here, didn't even have a message again. Came back to me. He said it's done and it worked.
04:58Gpt.mez is back up. You need to have that failover. And so if you have any extra accounts, if you're using Opus and you have a ChadGBT account, if you're using ChadGBT and you have a Gemini account or Google account, you need to plug them in so that you have those extra Hermes bots available.
05:15If you wanna take this a step further, I'd even recommend using, like, an OpenClaw as your backup account too because then you can have them not only watch over each other to make sure they're up, but then you can also take advantage of any features that one or the other comes out with that the other is not using. Now how do you set up a second or third Hermes agent the best way?
05:36Well, you basically have two options. The easiest way is just go to one of your agents and say, set me up a new Hermes profile. Make it powered by ChadGBT.
05:44So profile here, Hermes profile. Profile is the terminology in Hermes basically for other agents.
05:52They're called profiles. So if you set up a second Hermes profile, you're basically setting up a second Hermes agent. So just go and say, hey.
05:59Set me up a new Hermes profile. Then you let them know what model you wanna use. If you wanna get even more custom, you can say, name it Harry or whatever you want.
06:07You put it in there. You hit enter. It'll build it for you.
06:10There's one other way, and that is through dashboard. So if you go into the Hermes dashboard and then you go over to profiles, you can go in and click create in the top right, and then you can go through this nice user flow to choose a model, give it a name, everything you want.
06:27You can put it in there, and that'll build the profile for you as well and launch it. Now you have a second and third Hermes agent good to go that will watch over each other. That was my second lesson learned.
06:38Before we get into the third lesson, after a hundred hours with Hermes agent, one thing became clear. The more agents you build, the better you get at building them. You start seeing different patterns.
06:49My friends over at HubSpot who have sponsored this video put together a free AI agent building course just for my audience. You can access with the link down below. It's 18 free videos on how to build your own AI agents.
07:06They break AI agents down every component you need to know from memory to tools to plugging in the models. You can see memories and tools here, how to test and publish your different agents. This allows you a lot more hands on on building AI agents.
07:22They also talk about a lot of other really important interesting concepts when it comes to the nitty gritty of AI agents, like automations versus agents, fixed step versus dynamic reasoning, which would have saved me a ton of headaches early on building these AI agents out, and how to plug your AI agents to many different tools like n eight n, Notion, Make, Chatbase, and a whole lot of other platforms.
07:46So you'll be able to plug your AI agent to every single tool you use on your computer. It's a free complete course, 18 different videos. The link is down below.
07:56Make sure to check it out, and thank you to HubSpot for supporting the channel. Lesson number three I've learned over the last several months and hundreds of hours using Hermes agent. The next tip I wanna go over is a massive mistake I see a lot of people make, which is this.
08:10They buy their own computer for their Hermes agent. They give it their own Gmail account. They give it their own iMessage account.
08:17They give it accounts for every single little thing it does. They completely separate it from everything they do. This is mistake.
08:26You do not need to buy your own Mac mini for every agent you have. You do not need to give your agent its own Gmail account, its own Apple account. You are adding needless friction to your entire experience.
08:39And I get why people do it. Right? They have security concerns.
08:42Oh, Alex, if I give my Hermes agent access to my Gmail, can't it leak all of my emails? Oh, Alex, if I give it access to my iMessage account, won't it text my ex girlfriend? No.
08:52That's not how any of this works. Hermes' agent only does exactly what you tell it to do. If you tell it to write you a tweet, it isn't gonna go into your iPhotos and leak all your nudes.
09:04If you tell it to get the latest AI news, it isn't going to go then and email your mom. That's not how any of this works.
09:13It is an AI. It's not sentient. You give it a prompt.
09:16It does the prompt. You give it. That's it.
09:19So as long as you have personal accountability and think deeply about what you're telling your agent to do, it's not gonna do anything you don't want it to do. My question to you is this.
09:28How many people do you know have had a security incident with Hermes? Truly, tell me. How many people do you personally know have had their Hermes agent go and then email everyone on their contact list?
09:39The answer is probably none. You probably don't know a single person who's ever had a security incident. That's because a lot of the security concerns are largely overblown.
09:49And I know what's gonna happen now. I'm gonna get a thousand comments that say, Alex, you jerk. You're telling people do this dangerous shut up.
09:56I don't care. If you have some personal accountability, you act like an adult, you're not gonna need to add 20 different accounts for everything your Hermes agent does. You're just slowing down everything you do, adding tremendous amounts of friction.
10:08Put it on your main computer, put it on your main accounts, and then be a responsible adult. The next lesson I learned is what platforms to be using your Hermes agent on. I use three main platforms for Hermes agent.
10:20When I am at my computer, I use Hermes desktop. Hermes desktop is excellent. It's the best user experience for an AI agent on planet Earth.
10:28You can quickly switch between all your profiles. So if you're doing multi agent profiles like I told you to do towards the beginning of this video, you can switch to them very easily. You can see all your cron jobs very easily in here.
10:40You can pin your different sessions instead of having just having one massive session. You can have separate sessions, pin them, pop them out, talk to multiple Hermes agents at once. It's excellent.
10:50When I'm on the go and I'm doing deep work, I use Telegram. So I'm still using the Telegram app on my phone, but only for deep work, only if I'm doing multithreading things on my phone.
11:02I hope they come out with a mobile app soon. I know OpenClaw just came out with one. But if I'm on the go and I'm doing deep work, I'm using Telegram app on my phone.
11:09But other than that, this is a new addition. When I am on the go and I have quick prompts I need to do, I'm using iMessage. IMessage is actually fantastic with Hermes agent.
11:18This is a brand new addition as well to Hermes in their latest update. They had out of the box iMessage. I highly recommend setting iMessage up.
11:26I added a contact called Hermes to my phone. I pinned it to the top of my iMessages, and now I can message my Hermes agent through iMessage, the fastest, easiest app that I'm on at all times to get things done quickly.
11:40So quick tasks, iMessage, on the go, deep tasks, Telegram, and when I'm at my computer, Hermes desktop. That's how you need to be using Hermes agent.
11:48The next tip is related to what we just talked about, and then is the deep work on the go. There is some amazing new features inside of Telegram when you're doing deep work on mobile, on the go, on your phone, and that is formatting inside the messages.
12:04You now can have so many nice pieces of formatting in your messages. As you can see here, you have tables. You have bold.
12:11You have paragraphs. You have different things you can do. You have really nice in-depth formatting now inside of Telegram.
12:17I'd highly recommend taking advantage of this. Set up cron jobs. Ask questions where you ask for generated tables.
12:26So I have a do stock research on the top AI related stocks every day. I tell it to put it into a table. I tell it to give it a bunch of ratings and information there.
12:35And now every morning, I wake up to this really nice table with information on AI stocks I should be investing in. Take advantage of this new formatting in Hermes. Set up different cron jobs where it gives you tables of stock information or tables with your top performing content or tables with your most important emails.
12:54It makes it a really nice way to use and organize everything going on inside Hermes. The next lesson learned is around performance. One of the big complaints I get is, hey.
13:03My agent's slowing down. It's getting stupid. It's always busy.
13:06People have a lot of performance issues with their Hermes agent. What I find the number one culprit to be is cron jobs. A lot of your cron jobs run-in the background.
13:17And much like laws and rules, very easy to make new ones. It's very hard to take them away. And so what I find is if you need to improve the performance of your agent, one of the best things you can do is just eliminate and clean up old cron jobs.
13:31If you're in the desktop app and you click the cron button right there, you actually see a really nice list of all your cron jobs. And what I like to do is every so often, I go in and I just find which ones I don't really need anymore, and I click pause on them. So you can come in any that you're not really using, pause it.
13:49And what happens is is when these crons run, it slows down your agents. So if you have tons of cron jobs going, and I bet you forgot about a lot of the ones you scheduled, make sure to just go in every once in a while, once a week, pause any ones you're not really using. You'll instantly get a performance boost on your agent, also save usage and money.
14:10A lot of these take up a lot more tokens than you think. So always clean up your crons, and the easiest way to do that is through the desktop app experience. The next massive tip I have for you, and this is an important one for anyone who has multiple devices.
14:22So if you have a computer and a phone or if you have Mac minis or if you have DGX sparks, any if you have anything more than just one device, you need to install Tailscale. It is completely free. I am not sponsored by Tailscale whatsoever.
14:37I just absolutely love this application. Basically, what it does is it creates a private network for all your devices, which allows your Hermes agent to then be able to move across all your devices.
14:50This is great if you're running local AI models. This is great if you do vibe coding. This is great if you have a job and you do work and you like to move documents around between all your computers.
15:00You can easily go in and just say, hey, Hermes. Go over to this other device and do something. So if I wanna say, let me know which local models I have running on the DGX Spark, I can hit enter on that.
15:14And now my Hermes agent will go from the Mac Studio it's on right now, go over to my DGX Spark, which is also on Tailscale, and be able to tell me what's running on there. So as you can see, it's SSH ing over to my other device.
15:26It's checking on the models running. And if I wanted to go and go and, like, run a new local model, download something new on there, run it for me, it can go and do that for me. It saves me so much time because I don't need to plug all my devices into monitors.
15:42I just have my Mac Studio plugged in the monitor. My other computers, my five other computers I have, they're not connected to monitors. I just have my Hermes agent go over to those computers and run them for me.
15:54This is where your Hermes agent really turns into, like, your own AI employee because it's basically just on your other computers for you doing whatever work you need to do. If I'm ever on the go and I have a presentation on my other computer and it's not on my laptop, say, hey, Hermes. Go on my other computer.
16:08Click and drag it over here and send it to me. It'll bring the documents in between computers. You need to have Tailscale.
16:15It basically allows your Hermes to run your entire fleet of devices, has some other benefits too. If you're vibe coding and you have your app running on local host on, like, your main computer, you can have it if everyone's on the same Tailscale network.
16:28You can access your local host from your phone so you can test your apps out on the go if you want. So many benefits of Tailscale. It's completely free.
16:37There's there I think there is a paid version. I don't even know what's on it. I've just been using pay I've just been using free forever, so make sure to check that out.
16:44My eighth lesson learned is around reverse prompting. Hermes agent is so powerful that we can't even really comprehend everything it can do.
16:54But this prompt I'm gonna give you down below that reverse prompts Hermes agent helps you figure out how it can help your life the most. Every morning, I do a morning interview with my Hermes agent where I basically tell it to ask me a bunch of questions. What my priorities are for that day, what tasks I'm working on, what stresses me out at the moment, what's on my plate.
17:14It then takes all those things and then figures out what it can take off my plate for me, what tasks it can do for me, what it can automate, what it needs my permission to do, and starts doing those things for me. Every day, I learn more and more about what Hermes agent can do for me and and what it can take off my plate.
17:32You need to be doing this morning interview every single morning. It takes about five minutes, but it saves you tons of time after because it helps your Hermes agent figure out what it can do for you.
17:44I promise you're not getting the most out of Hermes agent. I promise you're gonna be automating so much more of your life. You just need to be able to figure out what those things are, and reverse prompting is the way you figure it out.
17:56And this prompt that has your agent interview you is the best way to reverse prompt. So take this prompt, run it every single morning. I promise you'll find two to three new jobs for your Hermes agent to do that will be super helpful for you.
18:09And the ninth tip I got for you, this is an important one. After you do your morning brief and it gives you a bunch of tasks it can do, put those tasks in your Kanban board for the agent to take over and actually do for you. This is the best way to stay organized on your tasks.
18:27All you need to do to see this Hermes Kanban board is go in, type Hermes dashboard into your terminal, whether you're using Ghosty or just your built in terminal to your computer. Type Hermes dashboard.
18:38It will pop open this website. You click on Kanban board in the bottom left, and you have this nice Kanban board where you can add in tasks, move them over, assign them to your agent. And so all the tasks your agent comes up with from your morning interview, you can put it in here, and it'll start taking care of it for you.
18:55This is an amazing way to stay organized with the tasks your agent has, with the tasks you have. You put them in here. You're good to go.
19:01You can organize your day really, really nicely. Those are my nine lessons learned. If you learned anything at all, leave a like down below, subscribe, and turn on notifications.
19:10All I do is make amazing videos about AI. Let me know down below what do you wanna see next. Mean, you wanna see more Claude code videos, maybe a Fable five video, or more tips on Hermes agent.
19:21Let me know down below. Hope this was helpful. See you in the next video.
The Hook
The bait, then the rug-pull.
The video opens with a blunt binary: run an AI agent right and it becomes a full-time employee; run it wrong and it's a glorified chatbot. What follows is nine lessons pulled from 100+ hours of daily use — which model to trust when real money and real tasks are on the line, why a single agent is never enough, and the free networking tool that lets one agent operate an entire fleet of machines unattended.
Named ideas worth stealing.
00:14list
Nine Hermes Agent Lessons
- Choose the right model (Opus > ChatGPT 5.5+ > GLM 5.2)
- Run at least two agent profiles for failover
- Don't over-isolate the agent with separate hardware/accounts
- Match the platform to the task (desktop / chat app / iMessage)
- Use chat-app table formatting for scheduled briefs
- Clean up stale cron jobs regularly
- Install Tailscale for cross-device operation
- Run a daily reverse-prompt interview
- Triage agent-suggested tasks into a Kanban board
The video's own structure: nine sequential, standalone habits accumulated from 100+ hours of daily agent use.
Steal forany 'what I learned running an AI agent daily' listicle or onboarding checklist
How they asked for the click.
VERBAL ASK
19:10subscribe
“Leave a like down below, subscribe, and turn on notifications.”
Standard end-card ask stacked with a direct request for topic suggestions on the next video.
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.
