AI Engineering

Lovable

Turn a sentence into a full-stack app with database and auth.

Published

What it does

Why it matters

Lovable cracked the "but the backend?" problem that limited earlier app builders. By generating against Supabase — real Postgres, real auth, real row-level security — the apps it produces aren't demos with fake data. They're structurally real products, which is why non-technical founders ship on it.

Engineering notes

  • Supabase as the backend. Postgres with RLS, auth, and storage generated coherently — the data layer is the strongest part of the output.
  • GitHub sync. Push the generated code to a repo and continue in your own editor — no lock-in to the platform.
  • Iteration via chat. Describe changes conversationally; the diffing is handled for you.

Limitations

  • You're inheriting an architecture you didn't design — review it before it grows.
  • Complex business logic and custom infrastructure still need engineers.
  • The ease of building can outpace the discipline of maintaining.

Related projects

AI Engineering

Bolt

Prompt, run, edit, and deploy full-stack apps in the browser.

StackBlitz's Bolt turns a text prompt into a working full-stack application — running live in the browser via WebContainers, editable in a real IDE, deployable in one click.

AI Engineering

v0

Generate UI with prompts, from the makers of Next.js.

Vercel's v0 turns text descriptions into working React components with shadcn/ui and Tailwind. The fastest path from 'I need a landing page' to deployable UI — and a glimpse of generative UI as a primitive.

AI Engineering

Claude Code

Anthropic's agentic coding tool that works in your terminal.

Claude Code brought the agent loop to the command line: it reads your codebase, plans changes, runs commands, and iterates — with you directing, not typing. The reference implementation of terminal-native AI engineering.

TypeScript

Canonical URL: https://notvibescoded.com/projects/lovable