JevPromptCoach

TypeSafe Jev semantic guardrails for Claude Code

Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim.

Every tool call your agent makes, checked before it runs. A Claude Code plugin that uses TypeSafe AI's Jev to verify each pending tool call against the session plan, then allows it, asks you, or blocks it. Proof of concept

React components that resolve which component to render, how to order a list, and whether to show an affordance — from calibrated judgments returned by TypeSafe's Jev.

Score how well a resume matches a job description using Jev (TypeSafe AI). Next.js app that returns typed, explainable match scores instead of generated text.

Not every coding task needs your best model. Experimental Jev-powered model routing for Claude Code — V3 prototype runs today, V4 routes at the task boundary.

Official agent skill for Claude Code, Codex, and compatible agents: primitives, patterns, and how to structure evaluations.

Claude Code plugin that scores review findings, debug hypotheses and design options with TypeSafe's Jev — calibrated probabilities instead of one more opinion.

A 3D Magic 8 Ball you shake and let go, where Jev answers your question as a Choice over the 20 classic answers and the page shows its probability for each one, running on Convex through the Convex AI Gateway.