I built a sellable product in one conversation. Here's the thinking, not the code. A few weeks ago I built a Claude skill for my job at the shop. It opens the Chrome extension, reads every page of a repair order (tech notes, customer concerns, parts, phone calls, inspections), and writes the customer notes for me. I used it every day until it was boring. Then I asked a different question: how do I sell this? By the end of one long conversation I had a full build spec, pricing, two pitches, a tagline, and both shop systems mapped. Tomorrow it goes into Claude Code. Here's what I noticed about how I got there, because I think the process matters more than the product. 1. Build it for yourself first, and use it until it's boring. I didn't start with "what could I sell." I started with "this annoys me every day." The skill ran at my counter for weeks before the business existed. By the time I thought about selling it, I already knew it worked. 2. Be the customer. Every real decision came from the counter, not from a whiteboard. "The page refresh wipes my notes." "Not everyone writes like me." "I'm not going to make advisors handhold the software." "I'm not trying to tattle on anybody." You can't read that stuff. You have to have lived it. 3. Cut. Then cut again. Seat pricing, owner dashboards, per-advisor reports, extra confidence flags, bundling in another product. All of it got cut. Feature creep is the death of usability. The rule I kept coming back to: be smart by default, ask only when it's actually unclear. 4. Think in systems, not features. One skill became an adapter pattern that works on Tekmetric and Shop-Ware. Three products became a toolbox. The call log I built for this product is the thing my next product reads. You can see the next thing while building this one. You just don't build it yet. 5. Push back on the AI. I told it no three times today, clearly. It wanted a settings screen; I wanted a button. It said a competitor's AI was close; I said they're built to handle a sentence and we're built to handle a ticket. It made one of my shop's rules universal; I said that's our rule, not everyone's. AI is a sparring partner, not an oracle. The product is better because I argued.

Hey everyone! 👋 I’m building an AI startup called Pip, an AI accountability buddy that lives in your text messages. It helps you stay consistent with your goals, follow through on commitments, and actually get things done. You can tell Pip what you want to accomplish, set your own accountability rules, and choose what happens if you don’t follow through — whether that means notifying a friend or putting money on the line. Think of it as a friend who keeps you accountable and makes sure you follow through on what you said you’d do. We’re offering a free trial, and I’d love for you to try it out, explore the product, and share your feedback! It would mean a lot as we continue building and improving Pip. Try it here: https://www.textpip.com/go/ashrit Would love to hear what you think! 🙏🚀

I recently saw someone posting about using Claude for video generation. This is me giving it a single prompt and I wanted to show you what I got first try with no edits. Better prompts, better input, more thought out story boarding, and Claude would be huge for marketing and social media pieces

I’m just wrapping up the tail end of a 11 month coding project. I’m wondering if anyone out there needs something built? I’m about ready to take on another project, hopefully one that’s nowhere near that long, but I’m open to have conversations about the kinds of things you might need or want