jevbooks

← All projects

typesafe-ai-uptech-bagel-policy

ctsstc/typesafe-ai-uptech-bagel-policy · Homepage

Bagel order rulings under Uptech Studio Bagel Policy using Jev.

Content Moderation31%Runner-up: Scoring & RankingQuestionnaire

What it is

A React SPA and Cloudflare Pages Function that takes a bagel order and returns a ruling under the Uptech Studio Bagel Policy. Made by an Uptech employee, not an official Uptech product.

How it uses Jev

Jev answers 8 typed questions about the bagel, cream cheese, worst topping, sandwich status, sun-dried tomatoes, input kind, abuse, and office scandal. Raw probabilities are mapped in code via toPolicyResult to set the verdict tier and flags.

Primitives:choicescorenoul

Technique worth stealing

Map raw Jev probabilities to policy tiers in code so thresholds and copy change without new inference.

Try it

pnpm i && cp .env.example .env && pnpm dev, open http://localhost:5173

View on GitHub

judged by Jevjev-1.13.0

Evidence

Each line is one question put to Jev about the README. ≥ 0.60 reads as yes, ≤ 0.40 as no; in between Jev is not making a call.

  • Jev-centricyes0.78
  • Shows a System One patternno0.14
  • Handles uncertaintyno0.04
  • Measuredno0.04
  • Runnableunclear0.60
  • Worth recommendingno0.25
  • Model replicano0.09
  • Problem scopescore on a 0–2 scale0.09
  • About Jevyes0.98

Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 23 Sept 2026.