Lately I've noticed most discussion around AI coding tools focuses on which assistant or terminal agent people use, but not much on the actual architecture decisions behind that, things like framework, hosting, database, and auth choices that affect cost and security down the line.
For context, my current default stack is Next.js on the frontend, Supabase for database and auth, Vercel for hosting, and Stripe for payments. I picked it mainly for speed of shipping and because it keeps infra costs predictable early on, but I'm not sure it's the best call for security or scaling past MVP stage.
A few things I'm curious about:
Do you settle on a default stack before prompting your AI agent, or does the agent end up influencing your stack choice?
What's been your biggest regret, cost, security, or scaling wise, with a stack you picked early on?
Any stack you'd actively avoid for a new SaaS in 2026?
I launched Foyer here last month. It's a small app that turns ambient sound into a place. You sit in the middle of a black canvas as a point of light, and each sound is a glowing orb you can drag around yourself: a hearth, rain, a stream, a city somewhere in the distance. Pull one closer and it gets louder. Slide it to the left and it moves to your left ear. It's real binaural audio, so with headphones on it feels like you're sitting inside the room instead of listening to a track.
