Jev: Typed Probabilistic Decisions
Jev is a model that provides typed probabilistic decisions instead of generating text, designed for routing, scoring, and real-time agents.
Use casesRouting
Jev routing use cases
Routing projects use Jev to send work to the right model, tool, or path — fast typed decisions instead of free-form generation.
Jev: Typed AI Agent Decisions
Jev is an AI model that takes shared state and typed questions, providing direct code-usable answers with choices, scores, and probabilities, enabling efficient decision-making for AI agents.
JEV x Automation Room
This project explores giving an AI model, JEV, a programmable robotic environment to reason about tasks, allowing it to observe the consequences of different decisions in a simulated workspace.
Jev: AI Agent Decision Orchestration
Jev acts as a decision-making layer for AI agents, choosing the next move by splitting intelligence from execution and enabling parallel processing of decisions.
JevNQL
JevNQL compiles natural-language questions into optimized relational and semantic query plans.
Intelligent Model Routing Benchmark
This project benchmarks three approaches for intelligent model routing: LLM, Decision Model (Jev @typesafeai), and Semantic Similarity, finding the decision model to be the most promising.
Jev Integration in Hermes Agent
This project integrates Jev (TypeSafe AI), a novel 'System One' frontier model for structured decision-making, into the Hermes Agent, enabling advanced capabilities like model routing, memory filtering, and skill selection.
Jev: An Independent Index for Decision Making
Jev is a model that takes program state and typed questions as input, returning calibrated yes/no answers, choices, or scores with low latency, designed to handle decision-making tasks separate from text generation.
TypeSafe AI Releases Jev TypeSafe AI released Jev on September 15 2026 as a machine native AI mo
Jev uses Choice Score and Noul question primitives to return structured responses with probabilities.
TypeSafe AI Jev Decision Engine
Jev is an AI decision engine that evaluates typed schemas directly in a single forward pass, bypassing the text generation of LLMs for faster and more reliable routing choices.
Corent's Brain Jev Integration
Corent's brain now utilizes Jev to make decisions about model selection and routing for incoming requests, based on workload, cost, and expected quality, before output generation.
AI Triage for Healthcare Intake
This project moves the decision-making step in AI triage for healthcare intake from an LLM to Jev, utilizing 25 typed questions to process decisions quickly and affordably.
Cross-Provider Skill and CLI for JEV Decision Model
This project provides a cross-provider skill and command-line interface (CLI) enabling Claude Code, Codex, and OpenCode agents to utilize the JEV decision model from @typesafeai.
Jev Ticket Routing
Jev, by @typesafeai, processes support tickets, making decisions on team assignment, urgency, and mood, and routes them correctly, escalating to humans when confidence is low.
Jev Confidence Control Plane
This project uses Jev confidence scores to control a system's execution path, routing simple cases to a cheap path, uncertain cases to an LLM, and failures to human intervention or stoppage.
