An insurance claim triage tool that classifies loss type, scores documentation completeness, and flags fraud indicators in a first-notice-of-loss narrative, routing claims without denying any or setting a payout.
Terminal agent for Polymarket's BTC Up or Down five-minute markets. Roughly every five seconds it asks Jev whether BTC finishes UP or DOWN versus the window open, then abstains or buys once and holds to resolution. Defaults to dry-run; live orders are opt-in.
An Apache-2.0 0.8B decision model that returns calibrated probabilities for yes/no, choice and score questions on CPU. Distributed as GGUF for llama.cpp and served behind a Jev-style /v1/systemone API, so existing Jev clients mostly need only a new base URL.
A pre-release Python framework for predictions on mixed text and tabular data: Jev Noul and Score questions turn text columns into numeric features, then a tabular foundation model such as TabPFN learns from labeled rows in context. Offers hosted and fully local backends.
x402 risk-check provider that scores agent counterparties before payment: OFAC, phishing and drainer feeds, transaction simulation, drainer-kit fingerprints and a Jev model reading context for injected instructions, issuing an ES256-signed attestation per verdict.
Proof of concept that flags suspicious purchase orders in SAP S/4HANA: ABAP computes risk indicators, a Fiori Elements app sends seven typed questions to Jev via OpenRouter, and ABAP applies thresholds to rate each order. Runs in shadow mode only.
Proof-of-concept multi-agent AI hedge fund that trades on paper: LLM investor agents analyse stocks, and a native JevLLM adapter lets an agent run on Jev's typed decisions through the same JSON contract the chat providers use. Educational only; no real trades.
Graph RAG framework over Milvus vector search with no graph database required: Jev Noul judgments select graph relations and rerank full source passages alongside vector-search candidates, reaching 86.07% average Recall@5 on 1,000 MuSiQue and 1,000 2Wiki queries in the two-stage evaluation.
Veris tests Jev as a semantic turn-detection gate for one Pipecat voice agent from its VAmoS Pro Bench, with labels complete, short, and long. Interruptions fell from 52% to 11% of caller turns across noise conditions, but task completion barely moved and median replies slowed from 2.1 s to 4.6 s.
Three AI trading bees race each other on OKX perpetual futures. Every decision comes from Jev picking one move from the moves that are legal right now, and every order then passes a risk layer written in plain code. Paper by default, with real market prices.
OpenRouter's Banking77 run: 3,080 support utterances, 77 intents, Jev 1.13 against Claude Opus 5 on the same one-line criteria, with latency, cost, and a confidence cascade.
An intraday trading bot for the Nifty 50: Jev ranks names every 15 seconds through the Vercel AI Gateway, and code sizes positions, stops, and flatten times.
A roughly 10,000-call black-box investigation that reconstructs Jev's likely architecture: a shared state prefix, isolated question branches, and direct probability readouts.
A two-hour recorded run of 50 financial workflows with saved outputs, baselines, and failures, from ledger integrity to AML triage and sanctions matching.
Live Hyperliquid desk across five isolated wallets where each tick packages the book, tape, and position as state and Jev answers Choice questions for long/short, open/close/hold, and leverage; hold sends no order. A missing private key means a dry run.
A community Rails integration built on the typesafe-sdk Ruby gem that adds Rails configuration, persisted usage and cost telemetry, and persistence-backed confidence policies for Choice and Score answers.
A self-hosted AI trading platform that can put Jev in front of strategy and Quick Trade entry orders as an auditable PASS/REJECT gate, with LLM fallback and deterministic bypasses for exits and protective orders.
An Android overlay that reads visible WeChat, QQ, and X conversations through accessibility, asks Jev for intent, danger, and the best action, then drafts three replies and fills one in without ever sending it.
A Codex Computer Use plugin that adds bounded Jev decision loops: Codex scopes the task and defines allowed actions, Jev picks an operation and compatible target in one request, and Computer Use performs the click, fill, scroll, or shortcut.
A curated list of public projects and practices built on Jev: 212 entries across 13 categories, from classification and routing to agent decisions, calibration, infra/SDKs, and finance, with explicit inclusion rules.
A Windows WeChat side panel that reads the visible conversation with local RapidOCR, has Jev judge intent and tension and rank three reply candidates, then fills the chosen one into the input box; sending is always manual.
An on-demand crypto decision-support terminal that ingests 50-1,000 tweets through a two-tier statistical pipeline, then has Jev's System One answer four typed questions and return a decision card with entry ranges, stop losses, and targets without executing trades.
A Python multi-agent stock research workspace covering 12 markets with optional JEV trading decisions: configure a TypeSafe key, select the JEV decisions-only strategy, and get buy/sell/hold, probabilities, and confidence without a research report.
Turn natural language into typed function calls: closed-set arguments become Choice questions, optional ones become Noul questions, and 54 questions ship in one request for a trading assistant.
A plain-English guide to Choice, Score, and Noul with Python and curl examples, confidence-gated branching for support, moderation, and fintech, plus a skeptical read of the benchmarks.
A video demo of a bot that asks Jev to decide buy or sell from a live price feed, then places real orders on Kuru's on-chain order book on Monad every 300ms block.