100 Days With Hermes Agent in 21 Minutes transcript

You see people online using Hermes to run their business. It finds them leads, it writes briefs, it watches the internet, sends them updates on their phone, >> [snorts] >> runs little agents in the background. Then you install it and ask it to summarize a PDF. That gap is what this video is about. So, after 100 days with Hermes, I want to show you the actual bridge. How you go from asking Hermes random questions to building repeatable loops, Telegram workspaces, [music] sub agent teams, event triggers, and a mission control dashboard you can open from anywhere in the world.

By [snorts] turning one boring task at a time into a system that runs without [music] you. Let's get started. The first mistake that I've learned throughout my first 100 days is using Hermes like a smarter search box. Asking it for things like "Hey Hermes, give me ideas. Summarize this, research that, write a draft about this." I mean, that is pretty useful and it's a big, massive, major reason for AI agents being useful, but that or those types of tasks don't compound because essentially you get an answer to your question, but the work disappears.

The better move is to turn the task into a repeatable loop. Here's the difference. If I say "Give me YouTube ideas," Hermes can give me YouTube ideas. But if I say "Every time I ask you to give me YouTube ideas, check my posted videos, check my rejected ideas, check my Notion content board, check current demand, check competitor outliers, then tell me the one video I I film next, why it matters now. What proof I need and what the first 30 seconds should show.

See, that's not a prompt anymore. That's an entire workflow. Hermes is checking for sources. It is applying rules. It's making decisions. It is returning something I can act on, something that is actionable. And that is the first real upgrade. Do not ask what can Hermes answer for me. Ask what decisions do I keep making manually? Because that is usually where the loop is. For me, one loop is reaction opportunities. I do not want to wake up, scroll X, scan AI news, check what is fresh, think through whether it matters, and then decide if I should post.

So, Hermes can do that for me every day, every couple of hours. It can check for fresh AI stories. It can check expose by me providing it with a rock API. It can check for product launches, filter for YouTube relevant topics. It can prioritize things from the last hour, or skip stale topics and things that it finds are duplicates. A massive pro tip, by the way, do the thing manually first. Make sure that the loop works manually first.

For example, for my YouTube video ideation, I've made sure that Hermes can fetch me every single individual piece of the puzzle. I've made sure that it can use and fetch all of the information and data that it needs from the sources it requires. That I made sure that it knows how to use that data to come up with video ideas. Then I made sure that the video ideas are actually good and actual signals. Once I confirmed all that, then I schedule it as a cron, which is just a fancy word for a repeatable job, something that happens on an occurrence, every day, every couple of hours, you you choose.

You can say like every morning check what matters, every Friday audit video ideas, every day scan competitors, and crons should make sense to you. I mean, check these sources, follow these rules, ignore these things, send me this output, run it on a schedule. This is how you go from asking Hermes for help to having Hermes report back. And this works for almost any job. A founder can summarize new leads every morning.

A creator can scan video opportunities every week. A developer can open PRs daily. A salesperson can find follow-ups they might have forgot. The value is not in having Hermes do the task once. The value is that it can turn the task that grunt work that you find yourself having to do every day into a repeatable operating system. But, the second you start creating loops, you hit the next problem. Everything gets noisy if all the work lives in one place.

My first Hermes setup was basically just one giant junk drawer. I would talk to Hermes about my YouTube ideas, my X posts, my business strategy, my personal tasks, just random questions, and it was all in the same chat. And granted, that can feel a lot simpler, especially when you're starting out, until it becomes impossible to tell what anything was for. The fix was not a more complicated app, it was Telegram topics.

I stopped treating Telegram like one conversation with an AI, and I started treating it like separate different workspaces. I mean, I have one topic that is dedicated to YouTube. I It's all I talk about with Hermes about. This is where one of my sub-agents also live, called Nova, but we'll get into that later. One topic is X. That one is built for me to understand what is happening around X. I mean, have I been offline the entire day?

Do I need a quick refresher? Can I ask Hermes to fetch sources for one of my tweets that I'm writing or putting out? Another topic is general, and I strongly recommend you have a general topic where it's a sort of catch-all topic that you can ask any question that you have that doesn't really fit into your other topics. One topic is React, which sends me reaction opportunities for things I can talk about on X. This is especially helpful for me if I've been offline or on meetings for an entire day and have not had time to see what is happening with the AI market.

The magic is not Telegram or even Hermes. The magic is that every workspace starts having a job. Every Telegram topic is a completely separate workspace. When I message Hermes in the YouTube topic, Hermes does not need to guess what mode it's in. It doesn't need to load a specific context and store away another type of context. It is already in the YouTube room. And that changes the quality of the output you get immediately.

Because the more powerful your agent becomes, the more dangerous messy context becomes. If I'm asking for a video idea, I do not want the agent thinking about my grocery list, a code bug, and some random email from yesterday. >> [snorts] >> I want it inside the content workspace using the content rules and content agents or sub agents. That is the practical setup I would recommend. Start with three topics. One for your main work, one for content or research, and one for admin administrative stuff.

Then give each topic a simple operating rule. For content, the rule might be before suggesting anything, check what I already posted, what I rejected, what is currently trending, and whether I can actually make it. For admin, the rule might be organize the task, draft the response, but ask before sending anything externally. Now, Hermes is not just answering messages. It is working inside the right room. That is the second upgrade.

Chats become workspaces. But, workspaces only solve where the work happens. They do not solve who does the work. That is where sub agents change the setup for me. Let's go to mistake number three. And I know one Hermes agent can do a lot. And that is the trap. Because when something can do a lot, you start giving it everything. Research the market. Check competitors. Inspect notion. Find title ideas. Write the hook. Summarize the hundreds of decisions that I have to make every day.

I mean, it can do that, but it will get very messy very quickly. And that's what happened with me. I noticed that the better pattern is sub agents. Think of the main agent as being the main operator. The one who coordinates with all of your other employees. It does not need to personally inspect every detail. It needs clean reports from specialists. Then, it needs to make the final call. For example, if I want Hermes to pick my next video, I can split the work.

One sub agent checks my posted and filmed pipeline. One sub agent checks competitor outliers. One sub agent checks current demand. The main agent reads the reports and decides what I should actually film. Now, the work is a lot cleaner. The context is cleaner. The decision ends up also being a hundred times better. Just try it and you'll see. And this is where you can use hack number one in this hack number three because once you define how that workflow looks like, then you can turn it into a repeatable cron or a repeatable skill.

Meaning, every time you ask for, say, a YouTube idea, it doesn't have to say guess and start from scratch. It already knows, all right, let's deploy our three sub agents. One does this, one does that, one does that, so on and so forth. You get the idea. However, this is also where a lot of people get agents wrong. More agents does not automatically mean better. More focused agents means better. Each agent needs a specific lane.

I love to give this analogy, but you don't want your plumber to be your dentist. Or maybe he's a very talented plumber who also had or happened to take a degree in dentistry. I don't I mean, hey. Don't judge him. But, that is why I built highly specialized agents like Nova and Sage. Nova is my YouTube agent. She has a wealth of knowledge and skills. She's trained on finding and checking YouTube trends, comparing video outliers, comparing competitor posts, and finding the best video ideas, and helping me through my research, ideation, everything I need for YouTube.

And I've open-sourced her, meaning you can download and install her for free. I'll leave the link in the description. And Sage is my X and content strategy agent, which is basically the same thing as Nova, but dedicated for X. I've also open-sourced him, and he is free to download and install. And I'll include the link in the description for both. Hooray! You can copy their structure or turn them into your own specialized agents.

But the point is not my exact agents. The point is the pattern. Your YouTube agent should not be the same as your coding agent. And your coding agent should not be the same as your personal admin agent. And your plumbing agent should not be the same as your dentist agent. Anyway, starting to feel like I'm going in circles around here. Different job means different tools, mean different memories, means different permissions.

The list goes on and on. That is how you stop building one overpowered assistant and start building a team. And once you have a team, the next question becomes obvious. How does the team know when to act? This is where event triggers come in. Cron handles time. Webhooks handle events. I know what you're thinking. What is he talking about? That sounds way too technical. But let me explain this to you because the idea is simple.

Crons are repeatable events, as we discussed. Things like do this every single morning. But a webhook says do this when something happens. That is the difference between crons and webhooks. Crons repeat something after every passing of a certain amount of time and webhooks do something when something happens. And listen to me because the second one, webhooks, is where Hermes starts to feel alive. Here's an example. I have a Notion content board.

When I move a video idea to film tab, that movement triggers work. It triggers a webhook. The second a video moves to to film, Hermes can validate it. It starts researching it. Did I already post something that is too similar? Is there current demand for that video idea that I just moved? What is the strongest title for that video? Should I film this now, later, or just kill it, abandon it? That is the difference between a database and a control service.

Notion is not just where the ideas live. Notion becomes the button that starts the workflow. It becomes the trigger to a chain of events and work. And you can use this yourself anywhere you want. Uh let me give you some ideas. A form gets submitted, Hermes researches the lead. A GitHub PR opens, Hermes reviews the risk. A customer pays, Hermes adds it to the daily summary. A file gets uploaded, Hermes extracts the useful parts.

You receive an email, Hermes reads it and summarizes it to you and comes up with a draft of what you could reply to. The setup is pretty simple. You can get as wild as you want with the ideas. All you need to do is create a webhook route in Hermes. And super simple, by the way. Don't let this intimidate you. You can literally ask your Hermes, Hermes, how do we create webhook triggers? And it will guide you. Or it will do it for you if you have it connected to like a super smart model.

It will connect to the app itself. Uh the only thing you'll need to do on your end is, you know, tell it what you need from it. And then whenever that event happens, Hermes runs the workflow every single time. And if the app does not support a clean webhook, you can still get close with a polling cron. What in the world is a polling cron? It's a cron that keeps polling, did this event happen every 5 minutes? It didn't.

Okay, never mind. I won't do anything. Oh, now it did in the next 5 minutes. Oh, it just did. All right, let's run the cron. Or simply put, Hermes can check every few minutes, compare what changed, and only act when the right thing happens. The bigger lesson is this, stop making yourself the trigger for Hermes to wait for you to ask for things, and let your tools, your emails, your data trigger Hermes. That is when your system starts working even when you are not thinking about it, even when you're not working.

But once you have loops, topics, sub-agents, and triggers, you run into the final problem. You cannot manage a real system from a chatbot forever. You need a place to see the machine. On to mistake number five. Chat is good for commands. Chat is bad for visibility. If Hermes is doing real work, I need to know what is happening, what is running, what finished, what failed, where are the different things that I need and ask for in order to be productive on a day-to-day basis.

This is why I highly recommend that you build yourself a mission control. Mission control is the dashboard layer. It's your information layer. Think of you opening Jarvis and you see all of this information and you're like, "Wow, this is so cool and futuristic." This is your mission control. For me, it is a live Vercel website connected to my workflows. Uh I have set up Google authentication Gmail authentication so that I can log in to it through my Gmail.

That way, you know, some random person can't just find the website link and log in to him itself and control my entire life or ruin my entire life. And what this also means is I can open it on my phone. I can log in and I can control Hermes straight from my phone. I can have every single thing that I need right on my phone. And the great thing about that is I can start using it anywhere I am in the world. I don't need to be next to my local machine, in case you're running Hermes on a local instance.

I don't need to be on my desktop if I'm out in the road, traveling, at the gym, something done, or I'm on holiday and I don't have my work equipment with me, I can still be productive by literally asking Hermes to do the thing for me. Mission controls give you the confidence to let Hermes do more because you can actually see what it is doing. That is the difference between a toy setup and a real setup. A toy setup hides everything in chat.

A real setup gives you command, visibility, and approval. And if I were to download and install Hermes from scratch, I would build it in this order. One boring loop, one Telegram workspace, one specialist agent, one scheduled cron, and one event trigger. Then, mission control once the system gets too big for just chat. That is a great path for you to level up your Hermi skills and control. Answers become loops, chats become workspaces, one agent becomes many agents and a team.

Manual work becomes triggers and invisible work becomes your mission control. That is what 100 days with Hermi taught me. The point is not to use every feature. The point is to transfer your workflow into the system. That is when Hermi stops feeling like a chatbot. And that is when it becomes an operating layer to your entire life and a genuine point of improvement to your quality of life. So, if you want to start, don't overbuild.

Pick one task you already repeat over and over again and turn it into a loop. Run it through Hermi. Ask it to help you. Then, from there, add one layer at a time. Add workspaces, then once you've done that, add sub agents, then crons, then webhooks, then mission control. And if you want the specialist agents I showed, Sage and Nova, those are open source on my GitHub. I'll include the links below. If you want the template to my mission control, I'll also include the link to that below.

It's also open source and free for you to download. Feel free to copy them, modify them, or use them as templates. Uh but, the real lesson here is bigger than just those agents. Do not just ask Hermi to help. Teach it how your work runs. That is the leverage. And if you've enjoyed this video, make sure to subscribe because I've got a ton more like it on my channel and a ton more coming your way. Oh, would you look at that?

The YouTube algorithm gods really think you'll enjoy this video. So, I'll see you there.