Getting the transcript
Reading the captions from YouTube. A video nobody has opened here before takes 10 to 30 seconds; this page fills in on its own.
Getting the transcript
Reading the captions from YouTube. A video nobody has opened here before takes 10 to 30 seconds; this page fills in on its own.

Sharbel A. · @sharbelxyz
This video has no Most replayed graph yet: YouTube shows one only once a video has enough views. These are the moments viewers replayed most in Sharbel A.'s most watched videos.
Most replayed moment at 13:32
3.9x that video's typical replay level
built-in memory, which is great. Here is how I would think about memory providers. Memo is interesting if you want a dedicated memory layer for personalized AI agents. It focuses on extracting, storing, linking, and retrieving memories efficiently. Their
Said at 13:25
Most replayed moment at 6:37
5.8x that video's typical replay level
trading strategy. Tests it. If it's better, it keeps it. If it's worse, it discards it and tries again. So, that's exactly what I built. Okay, here's the system we have at play. I gave it two years of crypto data,
Said at 6:31
Most replayed moment at 1:53
3.7x that video's typical replay level
let's install it together. Okay, so for step one, we need to actually start by installing Bullpen's CLI so that we can actually do everything that we want to do. And for that, let's first open Claude and put in the dangerously skip
Said at 1:47
The graph counts replays. It does not show where viewers stopped watching.
Words
1,369
Runtime
8:30
Speaking pace
161wpm
Reading time
6min
161 words per minute, between the 160 25th percentile and the 181 median of 349 measured videos. That distribution comes from the 349-video hook study.
Opening (first 30 seconds)
I built a viral web app in one day and I have zero coding experience. Zero. I used the app I built to write the tweet that announced [music] it. That tweet hit 118,000 views. 10,000 people visited the app in the first 24 hours. Four weeks later, my app is still getting 500 visitors a day with zero promotion, zero follow-up tweets. People finding it on their own. [music] And the funny part, I didn't plan for any of this.
81 words, the words spoken in the first 30 seconds at 161 words per minute.
Free, no signup. See how the first 30 seconds hold attention, with rewrites.
Sentence shape
| Measure | This transcript |
|---|---|
| Sentences | 114 |
| Average words per sentence | 12.0 |
| Longest sentence | 64 words |
| Questions asked | 6 |
| Sentences containing a number | 15 |
Most used terms
Filler phrases
21 in total: like 6 · literally 6 · actually 3 · I mean 2 · kind of 2 · sort of 1 · uh 1.
A literal whole-word count of the same phrase list the Prepublish browser extension uses, so a phrase inside another word is not counted and a phrase used in its ordinary sense still is. It is a count and not a judgement.
Free, no account. See where attention is likely to drop, with a rewrite for each weak line. The free check shows the scores and the one issue costing the most. Or run it on the words above first.
Free · No login · See a sample audit first if you prefer.
What this transcript is
Every word below is the caption track YouTube publishes for this video, pulled from the video itself and reproduced unchanged. It is not Prepublish's writing, not a summary, and not a re-transcription: it is the video's own published captions. English captions, generated automatically by YouTube, in the video’s original language. Source: the video on YouTube. A channel that would rather this page did not exist can ask for its removal through the contact page, and it is removed.
I built a viral web app in one day and I have zero coding experience. Zero. I used the app I built to write the tweet that announced [music] it. That tweet hit 118,000 views. 10,000 people visited the app in the first 24 hours. Four weeks later, my app is still getting 500 visitors a day with zero promotion, zero follow-up tweets. People finding it on their own. [music] And the funny part, I didn't plan for any of this.
Hi, I'm Charbel. I run Unfungible, an agency that helps businesses scale using AI agents in Open Claw. So, you can start saving on cost while getting more work done than ever before. If that's something you want for your business, head to our website and book a call with us today. A few weeks ago, X did something interesting. They released their For You algorithm to the public. They didn't post a blog post, they didn't just post a screenshot, they released the entire code out to everyone to see. 15,000 lines of code.
So, I decided to feed everything to my Open Claw and ask it what any of it meant. And what it came back to me with was actually insane. It turns out every single one of your tweet gets kind of scored on a bunch of different metrics, whether you have a good hook, whether you have a good call to action, whether you have a visual, how many people end up engaging on your tweet in the first 30 minutes, how many people end up clicking your profile after reading your tweet.
There's about 15 different categories that your tweet, every one of your tweet, gets scored on. And logically, the higher your score, the more likely you are for your post to go viral, for it to be pushed on other people's For You page. So, I remember I'm reading this breakdown that Open Claw is giving me and I had a thought. I thought to myself, "Hmm, what if this was an app?" What if there was an app where I could paste my tweet into it, and it could use that same scoring system that X uses to determine whether or not to push your post on other people's For You page, and you get to see that score before you hit publish?
And what if, just a crazy thought, you could get improvement suggestions for how you could make your post stand an even better chance at going viral? So, I did what any other person would do, and I opened Openclaw. I didn't write any line of code. I just described what I wanted it to build through a voice note. I told it, "I want to be able to paste a tweet. I want you to use Twitter's For You algorithm and the 15 signals that they use to score each and every one of our tweets, and get that score back to us after each and every tweet.
And I want you to also give me suggestions on how I could improve each and every one of my tweet. Give me specific areas that I need to improve. Give me the reason behind the score you're giving me." And I called it will it go viral.xyz, because that's literally the question everyone asks before they post. Will it go viral? Now, here's the thing about me. I have no idea how to code. I have never coded anytime in my life.
I wouldn't even know where to start, but I know how to describe what I want pretty well. I know how to spot when something is working well. I know how to say when something isn't working well. I know how to describe this needs to feel like X, or this needs to look like Y, or this needs to operate like Z. So, I described what I wanted, and Openclaw built everything for me. I tested it. We reiterated. I tested it again.
I gave it some more feedback until we reached our end goal. Pretty much like any conversation you would have with an actual web app developer. And within one day, literally one sitting, it was live. It was alive. And honestly, it worked better than I expected. Here's where it gets a little meta. Once the app was live, I needed to write a tweet to announce it. And I thought, wait, let me use the app itself to write the announcement tweet.
And so I did. I started writing a tweet say, I just built uh "Will it go viral app. Check it out, yo." And once I clicked analyze, obviously, it told me that tweet sucked. My first draft sucked. And it started telling me what was strong about it, what wasn't so strong about it, where I was losing score, and how to improve. And then a custom AI prompt that I could run it through. So, once I fixed everything that I could, it literally gave me this tweet right here.
Which if you analyze, viral potential. And that's literally the tweet that I ended up using. 118,000 views. 700 bookmarks. The app that's supposed to tell you if your tweet will go viral made my launch tweet go viral. I could not plan for that. Like I genuinely didn't think it would blow up the way that it did. But it did. And honestly, that's kind of the best product demo I've ever seen. Not because I planned some clever marketing stunt, but because the product actually did what it was supposed to do.
It made a tweet go viral. When that tweet blew up, the app got slammed. We literally got 10,000 visitors in the first 24 hours. That was insane. I mean, the first week we averaged about 4,000 visits, and then it sort of normalized at around 500 visitors every single day. To this day, we're getting 500 visitors. I haven't promoted it since. I haven't done any follow-up tweets since that tweet, since that initial launch tweet, and we're still getting 500 visitors a day. 500 people a day are finding it, using it, sharing it with their friends, and the DMs are still coming in 4 weeks later.
People saying that they run every single tweet through it before they post. That it's made them better at copywriting. That their impressions are up. That's what happens when you build something that actually solves a real problem for real people. Here's what I want you to take away from this. The idea of will it go viral came from one single question. One single question that I asked myself. When I read a document, I asked myself, what if this was a tool?
That's it. That's the whole origin story. We're in the era of the idea guy, and I mean this in the absolute best way possible. Your ideas, the ones you've been sitting on, the ones that you haven't actioned because you don't know any developer, because developers cost a ton of money, because it feels too complicated, those ideas are now more accessible and actionable than ever. Ever. Open Claw doesn't care if you don't code.
It doesn't care if you've never shipped a product before. You give it a clear objective. You stay in the loop. You give it feedback, and it builds everything else. Look, I built a web app with zero technical background in one single sitting. It's been getting 500 visitors a day for 4 weeks. Stop sitting on your ideas. The tools are here. They're at your disposal. The only thing between you and your idea being real is execution.
And the best part about an app like this is it is forever alive. It is forever online. You can literally go check it out. Will it go viral.xyz? Go paste one of your tweets and see what you get. Have fun with it. And if you found this video valuable, building with open claw, shipping fast, seeing what's possible in a day instead of a year, then subscribe. You don't want to miss the next video. See you in the next video.
The words are the caption track's own and nothing is reworded or re-transcribed. Paragraph breaks are placed between sentences so the text reads as prose.
Free tools for your own script: paste a draft and see where it stands before you record it.
Paste your draft and see where viewers are likely to drop off, with a rewrite for each weak line.
Paste the first 30 seconds of your own draft for a hook score and rewrites.
Check your draft against YouTube's advertiser-friendly guidelines before you record it.
Read this channel's public videos and transcripts, and download a writing brief for it.