taste-lint

⚡ Catch spec drift on every commit: check your code against your Markdown specs with TypeSafe AI's Jev model.

Natural-language linter combining ast-grep selectors with Jev verdicts to catch misleading names, stale comments, and tests that miss their stated behavior, with fixture-calibrated cutoffs and diff-aware review.

Guardrails for Pi built on pi-typesafe that steer the agent instead of interrupting you: Jev judges irreversible and off-task tool calls, detects stuck loops, checks unverified done claims, flags slop

A small second eval for shadcn-ui/lint that uses TypeSafe's Jev to judge the linter's own output.

Vercel's open agent framework, which ships Jev as the default evaluation model in its experimental evaluate path.

Instinct: describe a case in free text and Jev picks the UI from a fixed catalog without generating a line of code or copy.

Jev MCP server: a decision layer for coding agents, built on TypeSafe Jev (System One model). Ship gates, risk checks, file triage that keeps files out of context, and a safe headless browser, with calibrated confidence. For Claude Code, Codex, Cursor.

Zod validates the shape, Jev validates the meaning: semantic checks on request bodies become calibrated probabilities you threshold in code.

Catch breaking API behavior hidden in OpenAPI prose with deterministic checks and TypeSafe JEV System One semantic review.