Jev.aitools.fyi

Command Palette

Search for a command to run...

Demo
Product profile
Updated 2026-09-21

JevRLS

Paste Supabase pg_policies output and compare Jev, GPT, and Gemini on the same RLS leak rubric with latency and cost side by side.

by @CarolMonroe

Overview

JevRLS (jevrls.lovable.app) accepts pasted pg_policies output and scores each policy for leaks. Carol Monroe's showcase runs Jev beside GPT and Gemini with the same decision rule, surfacing who flags issues, latency, and cost together.

Problem: Supabase Row Level Security policies are easy to miswrite and expensive to audit with a full LLM call per policy line.

Built for: Supabase developers and security reviewers who want side-by-side model comparisons on the same RLS rubric.

First indexed on Jev Directory: 2026-09-21

Creator and team

Name
Carol Monroe
Handle
@CarolMonroe
“Paste your @supabase RLS policies and watch Jev race gpt and gemini on them. Same rubric, same decision rule, side by side: who flags the leaks, how fast, at what cost.”

How Jev is used

Role in the product flow
Per-policy security verdict on pasted Supabase RLS text
Primitives
Choice
State in
pg_policies style policy dump pasted into the Lovable app.
Decision out
Plain-words verdict per policy; site meta cites about one second per policy with Jev (marketing copy on jevrls.lovable.app).
  1. Paste policies into JevRLS
  2. Run identical rubric across Jev, GPT, and Gemini
  3. Compare leak flags, latency, and cost columns

Carol's demo is a benchmarking UI, not a hosted database scanner. Jev handles the fast structured judgment while GPT and Gemini run under the same decision rule so differences show up in flags and price, not prompt hacks. Treat Lovable deployment as the product home until a repo is published separately.

Features and stack

Features

  • Side-by-side Jev vs GPT vs Gemini on one rubric
  • Supabase RLS focused paste workflow
  • Public demo at jevrls.lovable.app
  • Showcase video embed on Jev Directory

Stack

  • Lovable app
  • TypeSafe Jev
  • Comparison models per UI

Demo

Showcase clip with the same lightbox player as the homepage. Click to play.

Carol Monroe@CarolMonroe

JevRLS races your RLS policies

Paste pg_policies, watch Jev, GPT, and Gemini flag the same Supabase leaks side by side. Same rubric, same stopwatch, fewer quiet data holes.

productsecuritydatabase

FAQ

Does JevRLS connect to my Supabase project?
The public app evaluates pasted policy text. It does not require live database credentials in the showcase flow Carol described.
Which primitives does Jev use?
Carol's clip describes leak flags on a shared rubric; site marketing cites fast per-policy verdicts. Treat outputs as structured policy judgments rather than free-form essays.

Related learn guides

Original Jev guidance that pairs with this product pattern.

  • Jev use cases

    The patterns builders actually search for: moderation, routing, triage, RAG verify, and agent gates.

  • Jev vs LLM classification

    When to gate with System One probabilities instead of asking a chat model to label things.

Related products

Hand-picked neighbors with rich profiles or overlapping tags.

Agent toolingJavaScript2
Semantic MCP firewall powered by Jev, screens every tool call, tool result, and tool description with calibrated System One verification.
agent toolingmcpguardrails
ApplicationsJavaScript
Demo
Pre-install security gate for npm lifecycle scripts using TypeSafe System One.
applications
ApplicationsTypeScript
FeaturedDemoMCP
classifier.
applicationsclassificationmoderation
By Rishit