Hello, fellow Vibe Coders. I am a new Vibe Coder who left the handmade shoe industry in Korea to embark on a startup journey. I d like to share a record of the past two months or so.

As I am Korean, I am using Google Translate to generate the English text for each paragraph; I ask for your understanding.

1. In the two-plus months since I started using Claude Code, I have built nine simple apps; I released three of them on iOS and five on Android. This count includes projects I abandoned midway because they became too difficult.

2. The total number of downloads is just over 200, and I ve generated one paid subscription and $15 in AdMob revenue. These are the results from June through July. I hope this post will serve as a record of my early, modest beginnings.

1 min demo

Grab it here https://chatgpt.com/plugins/plug...

Solo dev here. We hand-made 137 animation groups per species, six species, 5,242 frames, for a habit app where the progress bar is a pixel pet.

Then our founder said: we made all those special animations and I never see a single one.

I assumed he was wrong. He wasn't. signature_move_played had fired once in the app's entire history. The cause was arithmetic, not art: a pool weight of 8 out of 108 with a selector ticking every 7 seconds meant a ~90 second expected wait. Our median session is 59.5 seconds. We had built twelve animations that a typical session could not reach.

Fixing it surfaced four more defects. But the one that still bothers me is meta: our own detectors produced ten false alarms during the work.

Wow! Thank you to everyone who supported SoundGate Guitar! Finishing at #2 exceeded our expectations.

For Vahe and me the best part of the day wasn't the ranking - it was the conversations in the comments. We loved seeing how many of you resonated with the need for a real-time practice companion rather than just another video library.

We took notes on every single comment. Here is the top feedback we received and what it means for our roadmap:

• New Instruments: A ton of you asked for Bass and Ukulele support so you can jam together. We are focused on perfecting the 6-string engine right now, but Bass is next in line!

• Advanced Technique Detection: We had great questions about expression detection. We are actively training our models to catch bends, slides, vibrato, and palm muting.

• Distortion & Amp Effects: Right now our engine is optimized for clean tones. Based on your feedback, we are prioritizing updates to handle distorted tones and heavy effects just as accurately.

• Android Support: We heard you! Right now we are fully native on Apple (SwiftUI), but we know we need to bring SoundGate to the Android ecosystem.

Most companies would never give a new employee unrestricted access to every system on their first day.

A new hire might get access to a few tools, a defined set of responsibilities, and additional permissions as trust is earned. Some actions require manager approval. Some systems are restricted entirely. That's not because the employee is untrustworthy. It's because access and responsibility usually grow together.

I've always found it interesting that AI agents are sometimes introduced with the opposite assumption. An agent gets connected to calendars, databases, internal documents, customer systems, and external tools all at once because technically it can use them.

The challenge is that capability and authorization aren't the same thing.

Everyone's shipping agents. Few teams have a clean answer for what happens after the demo works.

Tool calls go live. Budgets get fuzzy. Compliance asks for evidence you can't reconstruct from logs. Evals live in one tool, traces in another, and "governance" is still a Notion doc someone updates after an incident.

We're building Traccia around a simple loop for production agents:

Because building products has become much more accessible thanks to AI, launches have gotten more crowded too, and the day you pick can matter almost as much as the product itself.

I've already launched my tool, Murmell, once, and I'm gearing up for a second launch on Friday the 28th. This time around I'm putting a lot more thought into timing, not just readiness.

We ve been thinking about this a lot while building Traccia.

One behavior we ve seen with MCP workflows is an agent getting into repeated tool calls without making meaningful progress. The workflow hasn t necessarily failed it can just keep going.

That got us thinking about a different kind of agent monitoring: not just detecting errors, but defining boundaries on execution.

I spent last week doing the heavy lifting of building my very first Mac app to see if I could turn an idea into a functional tool for my own workflow.

Even Charlie gave his thumbs up

Took advantage of the @Glaze by Raycast awards to test my building skills!

Some days the feed feels like a blur of launch posts that all use the exact same buzzwords. I have started ignoring almost everything unless the name or tagline makes me curious in under two seconds.

My personal filter relies on looking at the problem statement instead of the feature list. If a product cannot explain what headache it solves without using marketing speak, I usually skip it. I also tend to check out indie solo projects or small teams over polished agency launches, since those tools are often focused on solving one hyper-specific problem well.

What is your personal rule for filtering through the noise? Do you follow specific hunters, browse narrow categories, or just scroll until something catches your eye?

When Snipplet launched here in August, the feedback was pretty consistent: people wanted it for their own city, not just trips, and they wanted creating and sharing a guide to take seconds, not minutes.

Both are done.

We re not building an open-source product ourselves, and that s exactly why we thought - let s talk about it =)

Open source can bring a lot to a product: transparency, community, trust, contributions, and sometimes a completely different way of building distribution.

But it also comes with its own challenges.

You re opening the code to everyone. Others can build on top of it, fork it, or even create competing products. And if the product is a business, there s also the question of how you actually monetize it ?

This is not going to be a post about "passive" income completely.

It s more about how you started making money without selling your time. Tho still investing a little bit of it.

Fable 5.1 is here and it builds small worlds

Anthropic s newest model just went live in the Happycapy model picker. The benchmark story is that it more than doubled its predecessor on frontier science. The better story is what it does with a free afternoon.

Did you know that Cluing is also available as a mobile app on the App and Play Store? We haven't talked about this much, but we currently have over 1k installations on Android alone
Our main idea was always to help you collect insights on the go and since we launched the app we've been seeing more and more of you using it to save things whenever inspo strikes
And if you are curious what you can do with the mobile app, here's the link for you to check it out:
https://help.cluing.io/en/articl...

Why did you pick the SaaS / the niche that you picked? Do you have a vision of something that should exist?

Did you have a personal problem that you solved for yourself and now turned into a SaaS?

Quick update for everyone who followed our launch here this community is the reason PeakRoutine exists past week one.

When we launched in June, we were TestFlight-only, and a lot of you asked the same thing: "when can I just download it normally?" That day's here. PeakRoutine is now live on the App Store: apps.apple.com/in/app/peakroutine/id6786086158

A while ago, I started a quick note titled "apps to check out." It has now grown into a massive list of around sixty items, and I have realistically tested maybe four of them.

It starts with good intentions you see an interesting launch, save the link so you do not lose focus during the day, and promise yourself you will test it over the weekend. Then the list just sits there accumulating dust while new tools keep getting added to the pile. At a certain point, it stops being a helpful reference and starts feeling like digital clutter you quietly ignore.

Is saving links like this an actual discovery process for you, or is it just another form of hoarding? If you actually clear out your list, how do you decide what is worth keeping?

We just shipped a HTML embed badge so you can directly route your users to the Yatko page of your repo, for a much simpler installation process. All from your README file!

Swap OWNER/REPO and drop it in HTML code block:

<a href="https://yatko.app/OWNER/REPO"><img alt="Get it on Yatko" src="https://yatko.app/badge.svg" height="54"></a>

This links your repo to the Yatko landing page (yatko.app/owner/repo), which still picks the right binary for each visitor s OS and arch.

We re now only 20 points away from becoming the #1 Product of the Day, and we d really love your support!

Meridian is an open-source tool for developers that automatically creates your worklog and daily summaries, helping you make sure your work doesn t go unnoticed.

If you have a minute, please check it out, support us on Product Hunt, and share your honest feedback.

https://www.producthunt.com/prod...

Daily rotation of 3 people to sponsor ; easier pick for your startup/brand!

Improved

• Find outgoing conversations faster with the new Sent filter in All Emails.

• One-time codes are detected more precisely and shown directly in email summaries.

• Notifications now use readable sender names and skip messages you ve already read or archived.

• Follow long conversations more easily with better collapsing of quoted replies, including Outlook threads.

• Enjoy more reliable email categorization when using local AI.

• Archived emails now stay out of automatic processing.

• Empty email views now clearly invite you to select a message.

Fixed

• Draft messages no longer show actions intended for regular email links.

Road to 1,000,000 Votap users - Day 78 | Current: 1466

Driven just finished its first Product Hunt launch, and one of the most valuable parts was reading the comments.

Not just the compliments, but the questions.

A few themes stood out:

1. Trust comes before automation