Best Sabrina Ramonov Quotes

I believe it's the best time ever to be a solopreneur and you can truly accomplish so much with what used to take millions of dollars in hiring a big team.

Now you can build a really profitable venture completely solo or if you want to hire a few folks, that's fine too.

And I just want people to walk away inspired with what's possible today.

I truly spend most of my time building my startup.

Which is why being labeled an influencer or creator is so jarring to me because I don't spend that much time, guys.

I will share my entire journey as a content creator and as an entrepreneur, and most importantly, how I've been able to scale myself solo without going insane.

I was very burnt out from my first startup, so the last thing I wanted to do was another startup.

That's why it's funny to be here today with Blotato.

I built Blotato to solve that problem.

But the very first version of Blotato, honestly, was just an n8n automation, really, that just took something and then repurposed it.

Up until the start of this year, I only made content one day a week.

In that one day a week, it would be 20 short form videos, one long form YouTube video, and then text only content like newsletter, tweets and stuff.

I just checked my Facebook randomly and it was four and a half million organic views in the past 30 days.

And this was entirely automated.

People were commenting and messaging me like, why are you not sending anything?

And I didn't even realize I was blowing up on it.

I actually still cringe when people label me an influencer.

In Silicon Valley, that's not a nice thing to say.

I have a technical background.

I built and sold an AI company.

Being an influencer was not on my to-do list.

I personally don't think I'm a particularly good content creator.

I just don't even retake videos.

There are videos I just burped in the middle and I'm just gonna leave that in there.

This is my first TikTok video ever.

I so didn't want to be on camera.

I wore sunglasses the entire video and this took me four hours.

I took my first AI class in 2011 in school.

What people don't understand is I thought I was late to AI in 2011.

It was mind blowing to me to see ChatGPT with a single sentence you could do what used to take us a team of machine learning scientists, PhDs, and five different natural language processing models.

I've used Opus and similar tools and their automated clipping is not super great for educational videos.

It misses important context.

And then the short doesn't make sense anymore.

I think what's been missing is the intelligence of here's what should be included, here's what should be cut out.

My background's in computer science and physics from Berkeley.

I took my first AI class in 2011 in school and we were doing some basic things with reinforcement learning and Python.

I just remember thinking, wow, this is so cool.

Right after college, I was so interested in this space, I started an AI company that prioritized basically real time speech recognition, natural language processing on live calls.

I hired a team of machine learning PhDs.

I raised a couple million in venture capital.

I was the founder and CEO.

And it was really, really, really tough.

People kept asking me, can I do that?

How can I do that?

But without the automation part, I just want you to do it for me.

The key to that was combining AI and automation.

I got to go focus on the product, all this fun stuff I want to do, but I need to keep scaling myself in terms of content creation and marketing.

They don't have an MCP or API for creating automation.

So I'm actually using Claude Chrome.

And basically it knows what to do in there.

I have a base template automation and then Claude Chrome will clone it for each one of these keywords.

That way it doesn't have to create it from scratch.

It'll clone the base template, change the keyword and drop the link.

I've definitely noticed posts perform a lot better on Instagram and Facebook if you have a fresh lead magnet for each one.

Because what I was doing, I was super lazy.

I just said comment Sabrina on every single video.

But the posts performing really well now just have a unique lead magnet every time.

It's really stark, the difference in performance.

That's why I ended up building that ManyChat automation to help with that side of the process.

But it's the very last step.

I was successful on Instagram before doing that.

I want it so that every time I publish a long-form YouTube video, it will just do this automatically so I don't even have to do it.

Before I would say it was almost entirely n8n, and now it's about 50-50 Claude Code and n8n.

Even for n8n, I don't even touch it.

I use the Claude Code MCP n8n tool, and it just creates and fixes all the automations.

It can even check the execution logs, figure out why an automation broke in that instance, and then try to fix it and patch it up.

I can't use the desktop app after being in Claude Code.

It feels very limiting and then the conversation just stops.

I really encourage even non-technical folks to dive into Claude Code.

It's pretty awesome once you get over the initial learning curve.

My process is literally I'll just film the 20 TikTok videos, airdrop them to my MacBook and then I'll do slash cross post.

That knows to find all the videos I just downloaded today.

It transcribes all of them and then it writes platform specific captions for each one.

I look it over and then it will schedule them all out for the week.

You can build the skills really customized to your use case in business.

Every single one of these is highly customized to my actual workflow.

I actually filmed myself vibe coding the first version.

It's on YouTube.

The playlist is called Build SaaS with AI.

This was before Lovable launched.

I used Cursor before it had Composer, which is its agent that actually edits the files for you.

Vibe coding is terrific to get to that MVP, but if you decide to double down and commit, then it's like, okay, let's refactor the code, figure out how to properly architect this.

I've largely thrown away or refactored a lot of that code.

It just wasn't very high quality code, but it was excellent for an MVP.

I didn't expect this agent stuff to go mainstream so quickly.

When I started making YouTube videos, I made videos on agents.

This was in late 2024, and it was just not good.

It did not work very well.

You can just talk to the AI agent to make these videos instead of having to edit everything in CapCut and drag and drop.

For my highest quality tutorials, it's always going to be long form on my YouTube and Substack newsletter.

I started creating four YouTube videos a week instead of one.

My YouTube videos are usually filmed in the evening when I'd normally be binge watching Netflix.

So it's actually not that bad in terms of workload.

A lot of the news I see for AI is just reporting.

This is what happened, this is what happened, and that's it.

I wanted to spin on this more like a documentary, an edutainment documentary.

If you look at what I actually watch on YouTube, it's Hormozi and Gary Vee.

They have huge teams.

Now I go back and watch my own videos because I'm like, this is pretty cool.

I also do a lot of shorts.

One pro tip is motion is really appealing.

I'll do green screen where I'm just literally just filming, scrolling up and down on my newsletter.

That's all it is.

I don't watch my own content cause it's like, well, I already know it.

And it's even worse on YouTube cause it's really hard to sit through a 60 minute unedited, unpolished YouTube video.