Claude Code + decision models

Agent skill that tells you when you need an eval and how to build it, with an opt-in lane routing closed-label residue to Jev.

Browser driver where Jev makes every decision and agent-browser performs every action, benchmarked against Claude Code on 10 tasks.

Claude Code plugin that routes each prompt, step and subagent to the cheapest capable Claude model with effort caps and a live band.

Pre-registered audits of AI judges that measure how many decisions a judge can take alone at a given error rate, with calibration.

CLI and MCP server giving coding agents Jev-powered semantic search, focused reads and list picking in about a second for about a cent.

OpenAI/Anthropic-compatible Go gateway where Jev or Laya rates topic, complexity, risk and privacy to pick the cheapest adequate LLM.

Web search CLI for agents that has Jev score results and scraped chunks against the query and goal, passing only relevant ones on.

Benchmark of Jev on 159 community-reconstructed questions from Indonesia's SNBT 2025 university entrance exam, all responses published.

Code Mode for MCP where retrieval shortlists tools and Jev picks one or says none fits, benchmarked on several tool-use suites.

Independent benchmark asking whether Jev can replace an LLM reranker, on natural-language search over 6,245 YC companies, with a live demo.

Field guide site on decision models built from two Jev projects: a code, decision model, LLM, human cascade from ELI5 to engineering.

Claude Code and Codex skills powered by Jev, published with a calibration curve measured on 4,995 real agent decisions.

X post showing a Claude plugin that asks Jev to review redundant tool calls in about a second.