All decision model projects

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

Stanley: a Jev-first coding CLI where Jev routes requests to deterministic workflows and an agent only writes new workflows when none fits.

Local PR reviewer that has Jev prioritise each change P0-P2 so humans read the important hunks first, with plain-language explanations.

Applies a qualitative codebook to open-ended survey answers and reviews with Jev, exporting uncertain rows for human review.

Multi-agent Codex factory: Jev decides task shape, decomposition and routing, and failures are classified, not blindly retried.

Live race labelling 1,000 app reviews with four typed Jev questions versus Gemini 3.8 Flash JSON output.

Claude Code compaction plugin where Jev decides per old tool result whether to keep it verbatim or move it to a drawer file.

Desktop GUI and CLI for asking Jev Noul, Choice and Score questions by hand and reading the probabilities.

Codex search plugin that runs ripgrep and keeps only passages Jev judges relevant to the question.

Cloudflare app that labels a YouTube creator's Shorts with Laya or Jev to find which hooks drive views and score new hooks.

Web app that reads a two-person chat and labels each message's emotion, intent and reply quality to estimate interest.

Codex computer-use skill where Jev picks the next on-screen element, action, completion and risk from text candidates.

Gateway that batches agent control questions through Jev and calls a generative LLM only when policy says generation is needed.

Offline-by-default demo of six Jev decision workflows: model tiering, prompt screening, tool-call risk, reranking and more.

Depth-crawling research agent where Jev makes every per-page relevance and next-link decision and an LLM only plans and writes.

Experiment where Jev turns a one-sentence brief into a coherent design system for a whole dashboard console.

Long-document search that walks a PageIndex tree, asking Jev Choice which page or branch answers the question, with no embeddings.

Local dashboard to watch Jev play Freedoom via ViZDoom, showing choices, probabilities, latency and cost with spending bounds.

Camera-only MuJoCo quadrotor where Jev makes 2.5 Hz tactical judgments while code keeps flight control and a safety veto.

Undocumented app that uses Jev to classify text and pick an emoji reaction.

Generative painting canvas where Jev chooses paint materials and palettes for regions of 105 procedural sketches.

Jev plays Chrome Dino and a local shooter arena from structured state, with speculative jump/duck questions and code-owned execution.

Figma plugin that splits a one-sentence design instruction into small Jev choice questions, then code draws the result.

Flappy Arena races Jev against GPT-6 Luna on the same seeded Flappy Bird course, each choosing flap or wait live.

Experimental plugin wiring Jev into coding-agent harnesses to pick skills, tools, models and browser moves, starting with OpenCode.

Eight zero-dependency examples applying Jev to mechanical and electrical engineering: CAD routing, FEM triage, DFM, BOM alignment.

Game agent claiming to combine local Laya reflexes with Jev strategy to play PC and Android games via screen capture and real inputs.

Visual lab where Jev plays Super Mario Bros., Kung Fu and Doom through a plugin system, with code owning buttons and timing.

Self-hosted LLM gateway with semantic cache, privacy sandbox and a 'Jev classifier' tiering requests across cheap and frontier models.

Three.js box steered by plain-language instructions: an LLM plans steps, Jev decides move, turn and jump in real time.