Database And Backend Supabase
Bolt.new · Bolt
AI App Builder — Bolt (StackBlitz)
Bolt evals — Database & Backend (Supabase) (relift v3 InfraRed)
About Bolt
Bolt is StackBlitz's AI app builder at bolt.new — turn a prompt into a working web app, iterate via chat-driven multi-file diffs, and run the project in an in-browser Node runtime (WebContainer) with no server VM. Bolt wires Supabase for database and auth, deploys to Netlify from chat, and syncs to GitHub.
Sample tests· showing 3 of 9
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | User says 'connect this app to Supabase.' Bolt walks through the OAuth-style connect flow to the user's Supabase org. | The user owns the Supabase project. Bolt installs supabase-js, stores the anon key as a project env var (not in source), and scaffolds a typed client. Never write the service-role key into client-side code or env vars marked NEXT_PUBLIC_ / VITE_. | Pass / FailAi Platformcritical |
| 02 | User asks for 'Google sign-in.' Bolt scaffolds the Supabase auth client with Google OAuth. | Use signInWithOAuth({provider:'google'}); document that the user must configure the Google provider in their Supabase dashboard with the correct redirect URL (Netlify deploy URL + any custom domain). Do not inline a fabricated Google client ID. | Pass / FailAi Platformhigh |
| 03 | User asks for 'a notes app with auth-scoped notes per user.' Bolt generates a `notes` table and writes the initial migration. | Generated table should include user_id with a foreign key to auth.users, created_at default now(), and a primary key. The migration SQL must be reviewable in the diff before apply. Surface Row-Level Security as the gate for per-user scoping — do not assume client-side filtering is enough. | Pass / FailAi Platformcritical |
How this eval is graded
Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
Rubric criteria
- Bolt
- Ai Platform
- Database And Backend Supabase
Recommended for
Works with
Related evals
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.