Building a One-Person Company Powered by AI

Jaejin Song — Wed, 18 Mar 2026 18:04:52 +0000

I thought going solo would mean freedom. Turns out, it just means being busy all the time.

When you're handling planning, development, and marketing all by yourself, there's never enough time. Six months in, here's an honest look at where I'm at.

What I Built in 6 Months

I left my job last September to build my own products.

The reason was simple — I wanted to ship things I actually owned, not build someone else's product.

In six months, I shipped two:

Vybbi — Automated spam detection and removal for YouTube and Instagram comments.

KWatch — A simple way to look up Korean stock market data.

There's a third one in the works, but it's not done yet.

The Honest Numbers

Two products in six months. That's slow.

Early on, there was a lot of trial and error. But the biggest bottleneck was doing everything alone.

Writing specs, writing code, doing design, running marketing, fixing bugs. Focus on one thing and everything else stalls.

Revenue over six months: $0. One product launched and nobody wanted it. The other never even got to the point where monetization was possible.

No regrets. But I knew that at this pace, things weren't going to work out.

The Thing That Changed

I'd been using Claude Code on the Pro plan for a while. It was helpful, but I wasn't really leaning into it.

Then I upgraded to Max and started studying how to actually use it well. The more I used it, the more I realized the efficiency gains weren't incremental — they were a step change.

While digging through articles and posts about AI workflows, I came across people who were using AI less like a tool and more like an employee.

They'd delegate tasks, set direction, and review the output — treating AI the way a founder manages a team, not the way a developer uses an IDE.

Think about it. A CEO doesn't tell an engineer which lines of code to write. They say "build this feature," the engineer figures out the implementation, and the CEO reviews the result and steers the direction.

Reading those stories, and reflecting on my own experience, I realized I could do the same thing.

I decide the idea and set the direction. AI handles the execution. I review and approve. That's it.

Right now, this only works for development and planning. Marketing, operations, monetization — I still have to do those myself. There's a long way to go, but the direction is clear.

Two Challenges

So here's what I'm committing to.

Challenge 1 — One-Person CEO with AI Employees

This is the end goal. I decide what to build, and AI executes everything — planning, development, marketing, operations.

I make decisions, review output, and approve. A one-person company where the team is AI. That's the system I'm going to build.

Challenge 2 — Ship One Product Per Month

The only way to prove this works is speed.

If someone who shipped 2 products in 6 months can start shipping 1 per month, something fundamentally changed. First one ships this March.

Next post will be a retrospective on that first launch. Win or lose, I'll write it up honestly.

If you want to follow along, keep an eye on this blog.

Thanks for reading.

Why Instagram Can't Get Rid of Spam Comments

Jaejin Song — Tue, 17 Mar 2026 17:46:02 +0000

If you've ever scrolled through Instagram comments on a popular account, you've probably seen them — spam comments promoting sketchy links, fake giveaways, or dubious services.

They show up everywhere. Celebrity accounts with millions of followers, niche hobby pages, even small creators. No matter where you go, spam comments are there.

But why? Instagram clearly has the resources to deal with this. So why do spam comments keep showing up?

How Instagram's Built-in Filter Works

Instagram does have a comment filter. You can go to Settings → Comments → Custom Keywords and manually add words you want to block.

The mechanism is straightforward: it hides comments that exactly match the keywords you've registered.

Here's the problem — you have to add each keyword one by one, and if the spam is written even slightly differently, the filter misses it entirely. Relying on exact keyword matching has a fundamental structural limitation.

How Spammers Beat the Filter

If you write the same word differently, the filter can't recognize it. Spammers exploit exactly this.

In English, this might look like:

Original	Variation
free gift	fr3e g1ft
click here	c.l.i.c.k h.e.r.e
discount	d¡scount

There are three main techniques:

Character substitution — Replacing letters with numbers or lookalike characters. free becomes fr3e. It reads the same to humans, but to the filter, it's a completely different string.

Space/punctuation insertion — Adding spaces or dots between characters. click here becomes c.l.i.c.k h.e.r.e. Humans can still read it, but the filter sees a different word.

Invisible characters — Inserting zero-width Unicode characters in the middle of words. These are invisible to the eye but break string matching entirely.

When you block free gift, spammers just switch to fr3e g1ft. Block that too, and they find another variation. It's an endless game of whack-a-mole.

Why No One Has Solved This

There are comment management services out there — CommentGuard, NapoleonCat, and others. But most of them rely on the same keyword-matching approach, just with a nicer UI on top.

For English spam, keyword matching works reasonably well since variations tend to be simpler. But for languages like Korean, spammers use far more sophisticated evasion techniques — splitting characters into their component parts (Korean characters are composed of individual consonants and vowels), inserting spaces within words, and using Unicode tricks.

Global services have little incentive to tackle these language-specific patterns. The result? Tools priced at $29–79+/month that still can't catch non-English spam effectively.

So I Built One Myself

I got tired of watching spam flood the comments section.

The core idea is simple: instead of comparing text as-is, normalize it first. No matter how spammers disguise a word — character substitution, space insertion, Unicode tricks — normalization strips it back to the original form. Then the comparison catches it.

That's how vybbi.io was born — an automated spam detection and removal service for YouTube and Instagram comments.

Right now, it focuses on spam detection. But the plan is to expand into catching negative and hateful comments using AI as well.

More on the journey coming soon. Thanks for reading!

Forem: Jaejin Song