Calibration and threshold setting with decision models

One YAML task to classify, route, score or verify text with rules, Jev, NanoJev or an OpenAI-compatible model, with cost records.

Records the full distribution of every Jev answer by state, question and model, so thresholds can move over history with no new calls.

Unix-pipeable CLI for Jev and other System One models: ask questions, gate shell commands via exit codes, calibrate thresholds.

Auto mode for Pi: deterministic policy first, then Jev judges escalated bash/write/edit calls, failing closed when undecidable.

TypeScript library for typed semantic decisions via Zod schemas or native batches, defaulting to Jev, with confidence-gated policies.

Bilingual turtle-soup (lateral-thinking) puzzle site where Jev acts as host, judging player questions and grading solutions.

MCP server and agent skill for designing Jev judgments: question linting, batch evaluation, threshold calibration and reranking.

Monitoring proxy and client that records Jev answer probabilities and alerts on version changes, drift, edge crowding or accuracy drops.

Multiplayer GitHub triage dashboard where Jev answers kind, severity, urgency, duplicate and next step per issue.

Bun-based MCP server wrapping Jev with compact answers and a code-computed act, review or abstain verdict.

web4kit starter site whose home page is planned per visitor by a System One model (Jev or local LAYA), with calibrated fallback to rules.

Offline linter and agent skill that checks Jev requests for badly designed questions before they come back confidently wrong.

Experimental lab for semantic business gates: each gate is an independent Jev Noul that code maps to NO, REVIEW or YES by threshold.

Adapter that turns existing LLMs into Jev-style decision functions with option scores, optional calibration and review thresholds.

Decision sidecar and Copilot CLI pre-turn hook that mimics Jev choice, noul and score using Azure Foundry Cohere Rerank.

Decision engine that combines Jev probability distributions with loss matrices to decide when a clarifying question is worth asking.

Natural-language SQLite interface where code proposes options, Jev chooses among them, and a compiler builds deterministic SQL.

CLI, MCP server and skill for issue triage where Jev predicts issue kind, affected module and whether information is sufficient.

Decision-first CSV cleaning: code proposes repairs, Jev scores action, applicability and risk, a fixed policy applies or abstains.

Neo4j demos using Jev as a calibrated judge in GraphRAG pipelines, starting with entity resolution and a review queue.

Browser Minesweeper demo where Jev answers 'is this cell a mine?' for every frontier cell in one request, with an exact solver as fallback.

Python library to batch, gate, trace and calibrate thousands of typed Jev decisions, maximising questions per call.

Agent skill and CLI that chains Jev question design: find decision calls, check fit, draft, lint, calibrate thresholds and plan a cascade.

Autonomous PR review bot with typed Jev questions, deterministic approval gates and escalation of uncertain reviews to trusted owners.

Stdlib Python dispatcher turning typed function signatures into one batched Jev request, with a browser harness against ground truth.

Paper market-making system where code builds the state and policy while Jev answers six atomic judgments per 300 ms block.

Tool that lets code and agents ask Jev typed questions via reusable jevels, mapping answers to act, mark or fall_back.

Python sandbox turning Jev issue-category and reproduction judgments into testable routing proposals, with offline replay.

Playbook for using Jev as a cheap gate before expensive agent steps: confidence policy, question recipes, a skill and a router.

Two-tier macOS decision engine: a MiniLM encoder on the Neural Engine decides, escalating unsure cases to Apple's on-device model.