jevbooks

← All projects

decision-kernel

Agentic-Guides/decision-kernel

Judgment API: TypeSafe Jev on Cloudflare Workers for triage, urgency, spam, tone, risk.

What it is

Decision Kernel exposes TypeSafe Jev as a fast, calibrated, low-cost judgment API for small SaaS, support teams, and agent developers. It classifies text into triage, urgency, spam, tone, and risk, and provides an agent-safety gate for actions.

How it uses Jev

Jev makes decisions on text for /classify (triage, urgency, spam, tone, risk) and on action, cost, goal, and lastActions for /guard (spend, off_goal, duplicate, undoable, last_ok, lead_real). Results are returned as calibrated probabilities and used in code to route or gate actions.

Primitives:choicescorenoul

Technique worth stealing

Use a decision model for typed, calibrated answers instead of LLM prose when possible answers are known.

Try it

curl -X POST https://decision-kernel.pickaxe.workers.dev/classify -H "Content-Type: application/json" -d '{"text":"my app keeps crashing when I try to export my data, please help"}'

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-centricyes0.91
  • Shows a System One patternyes0.76
  • Handles uncertaintyno0.12
  • Measuredunclear0.48
  • Runnableyes0.84
  • Worth recommendingunclear0.41
  • Model replicano0.13
  • Problem scopescore on a 0–2 scale1.99
  • About Jevyes0.97

Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 20 Sept 2026.