I'm Yash.
Four things I'm building, all live.
At Voltade I put AI agents into real businesses on Volty, from the first call to the day it answers their customers. After hours I build Catchline, an iOS app that tells weightlifters the one thing to fix in their lift, and Ragnarok, the gym OS my CrossFit gym runs on. And I run marketing and automation at The Bon Pet, the fresh pet food brand I co-founded. Engineer for five years before any of this.
View Projects About Me Email Me
Press ⌘K to explore.
Featured Projects
An AI helpdesk: one inbox for WhatsApp, web chat and email, with an AI agent that replies to customers and takes actions in the tools they already use. Live since June 2026 and built mostly by Carl and Yiyuan. My part: I take client deployments from first call to go-live and build what each one needs. About 40 businesses are live on it, and the inbox went from ~2,000 customer messages a week in August to ~35,000 in October.
White-label, multi-tenant gym operating system I build: member app, coach programming, Telegram briefings, MindBody and push. Ragtag, a 500+ member CrossFit gym, runs on it day to day and logs 1,000+ workouts a week; first commit to gym-wide production in seven weeks, now 1,500+ commits and still shipping weekly. No second gym yet.
Fresh, gently cooked food for cats and dogs, sold online in Singapore. I co-founded it in 2023 and run marketing: 43 n8n workflows for WhatsApp lifecycle and win-back, the email programme, our own Reels, and an ops CLI and dashboards. 4.9/5 from 381+ reviews.
An iOS app for weightlifters. Film a side-on rep and it tells you the one thing to fix in your snatch, clean or jerk, and why. Pose estimation and bar tracking find the fault; rules written by coaches pick the cue, not a chatbot. Built solo, live on the App Store since 18 Oct 2026. It started life as Parallax, a couples app nobody used.
Start here
I shipped a couples app in eight days. Eight people signed up, the last on 14 July, and nobody has answered a daily drop since the 16th.
Templates handle the common 80%. The remaining 20% is every customer's actual business. Here's what that 20% looked like for one bakery, one day, five bugs.
We built a no-code agent builder so SMEs could build their own agents. Almost nobody did. Why Studio failed, and what we built instead.