Zack G

Hey everyone, I'm Zack.

Background in sales, recently got into vibe coding, and now I spend my time building websites and turning them into actual businesses using what I learned carrying a quota.

Right now I'm helping develop Cinder, a real-time call navigation tool that keeps reps on track from opener to close without getting in the way. Building it because most sales tools are made by people who've never actually sold anything, and it shows.

Here to meet other builders, learn from people further along than me, and check out what everyone's working on. If you're in sales or building for sales, say hi.

Have you ever wanted your high-end laptop to sound like a 1998 Honda Civic with a blown-out subwoofer? Probably not, but now you can!

Blown Speaker Simulator is a novelty Chrome extension built to test the absolute limits of Chrome's Manifest V3 and the Web Audio API. It captures your active tab's audio, isolates the low-end frequencies, and applies heavy digital distortion in real-time.

How it works under the hood: Since MV3 service workers don't support AudioContext natively, the extension uses chrome.tabCapture to send the media stream to a persistent Offscreen Document. Down in that layer, a BiquadFilter isolates and boosts the bass (+28dB), and a WaveShaperNode applies real-time clipping without perceptible latency.

I built this entirely with the help of AI, experimenting to see if I could create a complex audio graph without any prior audio engineering background.

Hey guys,

Quick question for those of you dealing with AI architecture and scaling.

Right now, we rely pretty heavily on n8n at our startup. It s been amazing for moving fast, tying APIs together, and automating workflows. But looking ahead, I'm trying to figure out the long-term play.

At what exact point does it make sense to move away from n8n (and paying for third-party LLM APIs) to actually build out a specialized, local RAG on physical hardware?