Hey Hunters! 👋 I’m Ashish, the creator of Guardrails. We’ve all seen AI agents generate code at lightning speed, but we also know the "Vibe Coding" problem: the agent eventually misses a security guard, creates technical debt, or ignores your architectural standards. I built Guardrails to fix this. It’s a set of strictly enforced architectural patterns that you drop into your project. It converts the AI from a loose "black box" into a disciplined builder that follows your "Building Code." What’s inside? ✅ Next.js Suite: Auth-guarded Server Actions, RSC-first patterns, and Metadata enforcement. ✅ React + Vite Suite: HttpOnly cookie security, PrivateRoute patterns, and WCAG accessibility. ✅ One Command: npm create guardrails sets everything up in 10 seconds. We're starting with Next.js and React, but Remix and Svelte are on the way. I'd love to hear your feedback on which "Guardrails" you need most! Build fast. Ship secure. 🛡️

Forum Threads

p/guardrails-2

•

5mo ago

Stop Vibe Coding: How do you enforce architecture with AI agents?

We ve all experienced it. You point an AI agent (Cursor, Claude, Gemini) at a task, and in 30 seconds, you have a functional feature. It feels like magic. It s the peak of "Vibe Coding."

But then the reality of the "drift" sets in.

If you aren't careful, the agent eventually: Skips a security guard (auth/rate-limiting). Mixes up Client and Server components. Ignores your specific Data Access Layer patterns. Creates technical debt that you have to clean up later.

I ve started looking at it through the lens of The Architect vs. The Builder.

View all

Guardrails

Stop "Vibe Coding" and start engineering with AI

Stop "Vibe Coding" and start engineering with AI

Forum Threads

Stop Vibe Coding: How do you enforce architecture with AI agents?

Forum Threads

Stop Vibe Coding: How do you enforce architecture with AI agents?