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?
CEO of Kednus here, we're building AI-native intelligence & compliance tooling, so I live in the tension between shipping fast and answering 200-question security reviews.
Here's what I keep running into: enterprise and regulated buyers (finance, healthcare, gov) LOVE the AI demo, then the procurement process asks where your SOC 2 is, how you isolate tenant data, and whether a human reviews model outputs before they trigger decisions.
Mine once created a reminder for a meeting that didn't exist, then flagged it three days in a row. I only caught it because I kept trying to remember who I was supposed to be meeting.
The interesting part is I still use it for the same task; I've just learned which of its confident moves to double-check. It feels a bit like working with a sharp new hire who's still finding their footing.
When did you first notice your AI agent needed a second look, and did you stop using it or just build a workaround like I did?
