Early experimentation using Jev to rethink harness UX
an agent platform wires Jev into its LLM harness as a callable tool for search, approvals and context, reporting 2,000 expense reports categorized in 20 seconds for five cents.
何を判断するか
CHOICE
Picks one option from a fixed set
SCORE
Rates against ordered levels
NOUL
Answers a yes / no question
Inferred from this project's own one-line summary in the community list — it reads as a CHOICE decision. Read the source to confirm.
インフラ / SDK / 連携の他のプロジェクト
jev-mcp (jkudish)proof-of-concept MCP server that puts Jev claim verification, content screening, and candidate ranking behind standard MCP tools.eveVercel's eve engine ships Jev as the default evaluation model (`typesafe-ai/jev`) in its experimental evaluate path.AI CLIVercel Labs CLI that can run Jev as the evaluation model for its `evaluate` command.jev-mcp (blakestone-x)MCP server exposing Jev classify, score, check, match, and screen as tools for any agent, with confidence on every answer.