All decision model projects

Cloudflare Workers AI model page for typesafe/jev, a provider-maintained integration that accepts state and typed questions.

Official TypeSafe docs page explaining how Jev's confidence is derived from the probability distribution and how to set thresholds.

Official TypeSafe cookbook recipes for guardrails, re-ranking, RAG passage classification, citation checks and more with Jev.

Databricks blog post introducing ai_decide, an AI Function that classifies, scores and chooses over governed data.

Official TypeSafe cookbook pattern: extract dates with typed questions and do validation and arithmetic in code.

Official TypeSafe cookbook example for checking whether source context actually supports a claim.

TypeSafe's published eval methodology and per-model results for System One decision workflows.

Curator note summarising migration from Jev's preview evaluation endpoint to the stable POST /v1/systemone API.

OpenRouter cookbook recipe gating agent tool calls with deterministic checks plus Jev Noul probabilities and fixed thresholds.

TypeSafe's official reference for the POST /v1/systemone request and response contract used by Jev.

TypeSafe's launch post for System One models and Jev, covering the interface, RLCD training, pricing, demos and caveats.

TypeSafe's documentation of where Jev 1.13 is known to fail: counting, dates, indirection, distractors, adversarial state and more.

Sayora write-up comparing Jev with production embeddings for picking the right website page to answer caller questions.

Blog review of a scheduler's pre-publish check where Jev answers four yes/no questions per social caption, compared with blind Fable labels.

Bilingual site cataloguing 500+ open-source Jev projects, gated by Jev itself, plus sixteen design patterns from real code.

Independent directory of about 950 projects built on the open Laya decision model, browsable by platform and use case.

Directory of Jev builds, guides and posts with each author's reported cost and speed, plus free Jev-powered tools.

TypeSafe docs page listing Jev version IDs, aliases, request limits, rate limits and pricing for /v1/systemone.

Ollama blog post: Ollama serves the /v1/systemone decision endpoint locally since 0.35, starting with nimble and tev1 models.

OpenRouter provider listing for typesafe/jev-1.13 alongside the moving typesafe/jev-latest alias.

TypeSafe cookbook showing how to evaluate many typed questions over one shared state in a single Jev request.

TypeSafe docs page on decision patterns: speculative fan-out, confidence-gated routing, composite scoring and intent routing.

TypeSafe docs page defining Jev's three question types, Choice, Score and Noul, and what each returns.

TypeSafe's official quickstart page: the shortest path from an API key to a first typed Jev decision.

TypeSafe's official cookbook for a two-stage skill-suggestion workflow that selects a skill and can reject the shortlist.

TypeSafe cookbook on why repeated Jev calls can differ, showing how an abstention rule raises repeat agreement.

TypeSafe AI's homepage: product overview of the Jev System One model and early-access waitlist.

Workflow design article: one Jev Noul asks whether a domain name refers to a protected brand, with the TLD kept out of the input.

macOS voice agent where Jev picks each step's operation and target control, escalating to an LLM agent when unsure.

DeepSeek Harness preset where Jev answers an agent's open end-of-turn questions, steering it on only above confidence and safety thresholds.