Agent skill · pedronauck
jev-engineering
Design and build use cases, POCs and production systems with TypeSafe's Jev decision model (System One): choose a design mode and a use-case archetype, build decision state, write typed questions, combine Jev with generative models, durable workflows, retrieval and perception tools, aggregate and gate in code, keep failures and costs visible, evaluate and roll out; covers the jev-1.14 danger-zone features (images, Box, long context). Use when building anything with Jev, from a first POC to a product, or when reviewing an existing Jev integration. Ships dependency-free reference clients (TypeSafe API, OpenRouter Decisions, Vercel AI Gateway) and a POC skeleton. For primitives and live docs alone use TypeSafe's typesafe-ai skill; not for generic LLM prompting.
What it needs
About 7k tokens when loaded.
What this skill does
Jev Engineering Jev judges the text (and, behind a danger-zone header, the images) you send against the criteria you write and returns typed answers with probabilities: Noul (P of yes), Choice (option + distribution + confidence), Score (expected level + distribution + confidence), and on jev-1.14 Box (one bounding box + confidence). It does not generate text, count, do arithmetic, read dates as quantities, establish truth, confer permission, or prove that a side effect happened. Everything else is ordinary software you own: state builders, candidate lists, arithmetic and dates, policy and thresholds, workflows, execution and verification. Generative models write artifacts and literals; Jev routes before and checks after. That division is what makes use cases like editorial studios, diagnostic banks, obligation trackers, dossiers, corpus atlases, rule packs, memory judges, signal observatories and agent loops cheap, fast and inspectable. Facts to design around (jev-1.13 and jev-1.14, checked live 2026-11-02; re-check https://docs.typesafe.ai/models.md when they matter) --- --- Models jev-1.14.0 (released 2026-10-14: small gains everywhere, largest in non-English) and jev-1.13.0, same price and limits. 1.14 is the newest release; jev-latest and jev-preview both → 1.14.0, and no preview build exists today. The docs state no deprecation dates. OpenRouter slug typesafe/jev-1.14; Gateway lists typesafe-ai/jev-1.14.0. typesafe/jev-router on OpenRouter is a chat model, not a Decisions model Request state (string or JSON) + a map of typed questions evaluated independently against the same state in one call; no question sees another's answer; optional assets map of images referenced from state, instructions or criteria Limits TypeSafe API: 32k tokens for state + longest question, 64k for state + all questions, 262k for both with the long-context header. OpenRouter Decisions: ~262k per request with no header and no 32k/64k split (measured 2026-11-02). …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills pedronauck/jev-engineering