Jev Korean

A PPO-trained reinforcement-learning decision brain for the CONNECT TYCOON company simulator from CONNECT AI LAB: it runs staffing, inventory, marketing, refund and security judgments and answers in the JEV request format with probabilities.

Korean-language Fastcampus seminar repo that teaches attaching Jev to a DeepAgents (LangGraph) shopping-mall support agent across 13 notebooks and a React sample app: tool selection, guardrails, risk gates and grounded RAG.

A Korean-language reinforcement-learning game that trains a company decision model: it reads a situation, a question and options, then answers with a choice plus probability and confidence, and asks a human when unsure. Built for a CONNECT AI LAB class; Apache-2.0, Python and Pygame.

A Korean Slidev course — 59 slides, 110 minutes plus deep-dive Q&A — with three standalone Jupyter notebooks that take Jev decision models from NLL/Brier/ECE calibration to training a Qwen-based Jev-compatible model with Unsloth and testing its HTTP API.

A small React web app where Jev, TypeSafe's System One API, estimates a name's age band and gender from naming trends across Korea, the US, Japan and China. A Vite server plugin keeps the API key server-side and the UI draws the returned band probabilities as bars.

25,418 Korean text-only evaluation items from 9 public datasets and 22 subsets, normalized to finite-choice decisions, with baseline results for ten model configurations.

Korean lecture-lab code for a three-part Jev course plus a CCTV extra: first calls, agent-specific routers for Claude Code, Codex, and OpenClaw, keyless replays, Colab notebooks, and OneJev video judgment.