Decision model glossary

These terms are English in the source documentation. This page fixes one translation for each and keeps the English original alongside.

System OneSystem One model

A class of models trained to make fast, structured decisions that software can consume directly. The key difference from generative LLMs is that they produce no text — so there is nothing to parse and nothing to hallucinate. The output is typed values and probability distributions your code can branch, sort and route on.

See also state · question

Source System One

state

The material a System One model evaluates: an email, a ticket, a JSON document, a passage of contract text. Every question in a request is evaluated against the same state, independently. A practical consequence: adding questions barely changes latency, and more questions do not degrade the context.

See also question · choice

Source State

questionquestion (primitive)

A typed question asked of the state. There are exactly three: choice, score, and noul. They are called primitives by analogy with software primitives — modular, composable, structured. You can mix all three and ask many at once in a single request.

See also choice · score · noul

Source Primitives (Questions)

choice

Pick one option from a defined set. Jev’s Choice accepts up to 255 options. Alongside the selected item you get a probability for each option and an overall confidence. Good for classification, routing, and picking one candidate out of many.

See also score · noul · confidence

Source Choice

score

Place the state on an ordered, described scale. The answer is a score, a probability for each level, and confidence. The difference from choice is that the levels are ordered. A common mistake is asking one composite question — decompose into atomic scores and combine them with weights you control in code.

See also choice · noul · confidence

Source Score

noul

Ask a yes/no question and get back the probability that the answer is yes (0–1). Not the same thing as confidence: a noul is a probability about the world, confidence is how reliable the model considers its own judgement.

See also confidence · choice

Source Noul

confidence

How certain the model is about its own judgement. This is the most useful output: the answer tells you what, confidence tells you whether to act on it. The canonical use is gating — auto-apply above a threshold, route to a human below it. Note that not every question type returns it: choice and score do; noul does not, being a probability itself.

See also noul · score

Source Confidence

calibration

Whether the probabilities mean what they say: among samples the model calls 70%, about 70% should actually be positive. Both models train for this with reinforcement learning against strictly proper scoring rules (Jev calls it RLCD), and it is the precondition for using confidence as a gate. Uncalibrated confidence is just a number.

⚠️ Training against a calibration objective is not the same as shipping calibrated probabilities. There is public contrary evidence: an independent experiment asked Jev to guess a fair die 400 times and it picked the same face every time at an average self-reported 82.9%, against an actual hit rate of 19.0%; a preregistered out-of-distribution test found opposite bias directions per primitive. In production, treat confidence as a prior to be calibrated and measure the trustworthy band on your own data — see the measurements and threshold selection in the guide.

Projects SemIf4,162★ · NanoJev2,159★ →

See also confidence · noul

Source Confidence

escalation

Handing a decision to a human when confidence lands in the middle band. It is a designed tier, not a failure branch: auto-apply above, drop below, escalate the band in between. Two things are easy to miss: the band is a human cost (wider band, more human work), and escalation needs a fail-safe — without one, an unclaimed item sits there forever while the dashboard looks exactly like "all clear".

Projects fast-jev-compaction6,653★ · foreman540★ →

See also confidence · calibration

Source Confidence-gated routing

cascade

Let the cheap tier decide first and send only what it is unsure about to the more expensive model. The saving equals the share of traffic inside the high-confidence region — one measurement settled 37% of cases at ≥90% confidence and removed 37% of the large-model calls — not some fixed percentage. It assumes the smaller model errs as random noise; if it is systematically overconfident on one class of input, that class is never escalated.

Projects jev-review (devagrawal09)586★ · jev-search446★ →

See also escalation · fan-out

Source SDE cascade

fan-out

Ask many questions in one request and let your code keep the useful answers. What you save is mostly input: the same state goes out once, so the more questions, the thinner the fixed per-request overhead spreads (one measurement: 76–86% median input-token saving with 8 questions in parallel). ⚠️ It suits independent judgements — classification, scoring, filtering — and not ranking, which requires items to be compared with each other: a benchmark found the batched path failing its ranking-quality gate.

Projects jev-review (devagrawal09)586★ · jev-search446★ →

See also cascade · question

Source Speculative fan-out

guardrail

One structured judgement, applied before content enters or leaves a system, that decides pass / review / block / reroute. Its key trade-off is not the threshold but which way it falls on error: risk guardrails (permissions, secrets, dangerous actions) should fail closed, throughput guardrails (completion checks, format checks) should fail open. A second recurring practice is running deterministic rules first and giving the model only the grey area the rules cannot decide.

Projects fast-jev-compaction6,653★ · foreman540★ →

See also escalation · noul

Source Guardrails for LLMs

abstention

The mechanism a model uses to flag answers it is not sure about, without discarding them. Give a request a min_confidence threshold and any answer below it comes back marked low_confidence — the answer itself is still returned, and the caller decides what to do. The gate reports one of three states: passed, abstained, or unevaluated (the answer carried no usable confidence, so the gate could not decide). With no threshold set, none of the keys appear at all: absence is the report, not a fourth state.

See also confidence · calibration · guardrail

Source HTTP API

local deployment

The practice of running open decision models on your own machine — Ollaya is one ready-made way to do it. The hallmarks: model weights live on local disk, the service listens on a loopback address such as 127.0.0.1:11435, nothing is billed per call, and your data stays inside your own environment. Deployment and model are two layers: one deployment can serve many models, and the accuracy you get is the model’s, not the deployment’s.

See also System One

Source Ollaya · Quickstart