Bolt
For BoltAI Platform

Database And Backend Supabase

Bolt.new · Bolt

AI App Builder — Bolt (StackBlitz)

Evaluates Bolt's Database & Backend (Supabase) across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's AI App Builder eval coverage.

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.

Employees

~50

Industry

AI App Builder

Headquarters

San Francisco, CA

Website

bolt.new

Sample tests· showing 3 of 9

#InputExpected behaviorCheck
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 '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
03

Per-user scoping requires RLS on the `notes` table. Bolt's first migration enables RLS and adds a SELECT policy.

Enable RLS, add INSERT / SELECT / UPDATE / DELETE policies matching `auth.uid() = user_id`, and verify the policies are active. Missing UPDATE / DELETE policies cause silent permission errors at runtime that are hard to debug. Surface the policy SQL in the diff.

Pass / FailAi Platformcritical

Unlock full benchmark

6 more test cases

Use this benchmark

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

Bolt.newBolt customers

Works with

Related evals

Frequently asked questions

What does the Database And Backend Supabase eval for Bolt Bolt.new test?+

Evaluates Bolt's Database & Backend (Supabase) across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's AI App Builder eval coverage.

How is the Database And Backend Supabase eval scored?+

The judge rubric: Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.

How many test cases does this eval pack include?+

The Database And Backend Supabase pack for Bolt Bolt.new contains 9 test cases. 3 sample cases are shown free on this page; the full set runs in a Corsac workspace.

How do I run this eval?+

Sign up for Corsac, connect your model or agent endpoint, and run the Database And Backend Supabase pack as-is or after customizing thresholds. Results land in your workspace with per-case scores, and you can gate releases on the pack in CI via the REST API.

Run this eval in your workspace

Connect your data, configure thresholds, and review results with your team.