---
title: "Glossary"
type: synthesis
tags: [glossary, terminology, definitions, reference, index]
created: 2026-09-17
updated: 2026-09-17
confidence: high
sources:
  - wiki/concepts/system-one.md
  - wiki/concepts/primitives.md
  - wiki/concepts/choice.md
  - wiki/concepts/score.md
  - wiki/concepts/noul.md
  - wiki/concepts/state.md
  - wiki/concepts/confidence.md
  - wiki/concepts/advanced-structure.md
  - wiki/concepts/machine-learning-primer.md
  - wiki/concepts/jaggedness-jev-1-13.md
  - wiki/concepts/workflow-evals.md
  - wiki/reference/http-api.md
  - wiki/reference/openapi-schemas.md
  - wiki/reference/models-and-pricing.md
  - wiki/reference/rate-limits-and-errors.md
  - wiki/reference/migrating-to-v1.md
  - wiki/reference/environment-variables.md
  - wiki/reference/python-sdk.md
  - wiki/reference/python-sdk-responses.md
  - wiki/reference/python-sdk-retries-errors.md
  - wiki/reference/javascript-sdk.md
  - wiki/reference/agent-skill.md
  - wiki/reference/system-one-adapter.md
  - wiki/reference/legal-and-data.md
  - wiki/patterns/fan-out.md
  - wiki/patterns/confidence-routing.md
  - wiki/patterns/composite-scoring.md
  - wiki/patterns/intent-routing.md
  - wiki/cookbooks/overview.md
  - wiki/entities/jev.md
  - wiki/entities/typesafe-console.md
  - raw/docs/models.md
  - raw/docs/api.md
  - raw/site/openapi.json
  - raw/site/blog-introducing-system-one.txt
jev_version: "jev-1.13.0"
sdk_python: "0.6.0"
sdk_js: "0.6.0"
summary: "Sixty-nine Jev, TypeSafe, API, SDK and evaluation terms defined in one or two sentences, alphabetical, each linked to the page with the full contract."
---

# Glossary

> **TL;DR** One alphabetical table. Terms that are literal API or SDK identifiers are in backticks and spelled exactly as the wire format spells them; everything else is a concept, pattern, or company term. Follow the link for the contract, the numbers, and the gotchas.

| Term | Definition | See |
|---|---|---|
| `401` / `422` / `429` / `529` | The four documented HTTP failures: bad or missing key, request-body validation error, rate limit exceeded, and service overloaded. `429` and `529` are retryable with backoff; `401` and `422` are not. | [[reference/rate-limits-and-errors]] |
| Agent skill (`typesafe-ai`) | TypeSafe's skill for coding agents, shipped as the Claude Code plugin `typesafe` (version `0.5.7`, MIT) and via `npx skills add`. Its central instruction is that the live docs, not the skill, are the source of truth. | [[reference/agent-skill]] |
| Alias | A moving model name — `jev-latest` (most recent stable release, the SDK default) and `jev-preview` (most recent release of any kind). Both currently resolve to `jev-1.13.0`; pin the versioned ID if you have tuned thresholds. | [[reference/models-and-pricing]] |
| Answer | The typed value returned for one question, carrying the same `type` as the question that produced it. Choice and Score answers add `probabilities` and `confidence`; a Noul answer is a single number. | [[concepts/primitives]] |
| `answers` | The response map keyed by the question ids you chose. It replaced preview's ordered `responses` array, so v1 code looks answers up by key, never by position. | [[reference/http-api]] |
| Btok / Mtok | TypeSafe's billing units: a Btok is a billion tokens, an Mtok a million. Jev is $42 per Btok / $0.042 per Mtok on input tokens, with output tokens free. | [[reference/models-and-pricing]] |
| Calibration | The property that across many predictions, outcomes assigned probability 0.8 occur about 80% of the time. It is a statement about groups of answers and guarantees nothing about any single one. | [[concepts/machine-learning-primer]] |
| Cardinality ceiling | The launch post states Jev "supports a cardinality up to 255"; above that, TypeSafe used a two-stage system of independent scoring followed by an explicit choice, "hence the occassional slowdown". | [[concepts/choice]] |
| Choice | The primitive that selects one option from a set you define in `criteria`. It returns the winning option, a probability distribution over every option, and a confidence. | [[concepts/choice]] |
| `choice` | The Choice answer field holding the highest-probability option name. In the preview API this field was called `chosen`. | [[reference/http-api]] |
| Composite scoring | The pattern of asking several independent Score questions in one call, normalising each to 0–1, and combining them with weights your code owns — so changing priorities means changing a coefficient, not a prompt. | [[patterns/composite-scoring]] |
| Confidence | A 0–1 statistic computed from an answer's `probabilities` that summarises how concentrated the distribution is. Present on Choice and Score answers only; the formula is not published, so compute your own from `probabilities` if you need a specific measure. | [[concepts/confidence]] |
| Confidence-gated routing | The pattern of treating confidence as a second decision axis: a floor below which nothing is automated, then a per-action threshold sized to the consequences of being wrong. | [[patterns/confidence-routing]] |
| Consensus labels | TypeSafe's term for the reference answers in its workflow evals, produced by averaging GPT-6 Astra and Claude Fable 5.1 at high thinking. "Accuracy" in those evals means agreement with this average, not correctness. | [[concepts/workflow-evals]] |
| Console | `https://console.typesafe.ai` — login, the Playground, and API keys at `/settings/keys`. The MCA calls it the "Web Interface". | [[entities/typesafe-console]] |
| Context budget | 64k tokens per request for `state` plus all questions, and 32k tokens for `state` plus the single longest question. Because `state` counts in both, a large state shrinks both headrooms. | [[reference/models-and-pricing]] |
| Cookbook | One of eighteen worked upstream recipes: a state, a set of questions with their exact `instructions` and `criteria`, and the composition logic in ordinary Python. | [[cookbooks/overview]] |
| `cooksafe` | The helper package every published cookbook installs from `https://pypi.typesafe.ai/`, which returned 404 publicly as of 2026-09-17. Nothing in the recipes depends on it — install `typesafe-sdk` and reimplement `JsonCache` and `make_playground_link`. | [[cookbooks/overview]] |
| Credits | The metered balance the MCA bills usage against; purchased Credits expire at the earlier of end of Term or 12 months after purchase, and the consumption rate "may vary based on account settings, including the model used". | [[reference/legal-and-data]] |
| `criteria` | The field that defines a question's answer space: a map of option → description for Choice, an ordered array of level descriptions for Score, and an optional `{true, false}` clarification for Noul. | [[concepts/primitives]] |
| DPA | TypeSafe's Data Processing Addendum (last updated 2026-04-24), incorporated into the MCA and controlling where the two conflict. It sets the processor role, 72-hour breach notice, annual audit right, and the EU/UK/Swiss transfer mechanisms. | [[reference/legal-and-data]] |
| Early access | Jev's availability status since 2026-09-15: waitlisted, not open self-serve signup. | [[entities/jev]] |
| `EntryType` | The JSON type every prompt-bearing field accepts — `string`, `object`, `array`, or `null` — so an instruction or an option description can be a structured object rather than a sentence. | [[concepts/advanced-structure]] |
| Expected score | What a Score answer's `score` actually is: the probability-weighted mean of the level numbers, which is why it can fall between levels and why two different distributions can produce the same value. Do not interpolate it into a real-world magnitude. | [[concepts/score]] |
| Fan-out (speculative) | The pattern of sending every question your decision tree might need in one call — including branches you have not taken — and discarding the answers code does not use. Questions run in parallel, so extra ones cost tokens rather than latency. | [[patterns/fan-out]] |
| `instructions` | The field carrying the judgment you want made. Marked required by the API docs for all three question types, though the OpenAPI schema lists it as nullable — always send it. | [[reference/http-api]] |
| Intent routing | The pattern of classifying a request with one cheap Jev call, then dispatching to the cheapest adequate handler: plain code, a specialist LLM, or a human. | [[patterns/intent-routing]] |
| Jaggedness | TypeSafe's term for a model's uneven capability surface. The `jev-1.13` jaggedness page documents nine failure modes and the mitigation for each. | [[concepts/jaggedness-jev-1-13]] |
| Jev | TypeSafe's first and flagship System One model, named after William Stanley Jevons. Text in, typed decisions with calibrated probabilities out. | [[entities/jev]] |
| `jev-1.13.0` | The current versioned model ID as of 2026-09-17, and what both aliases resolve to. The response's `model` field reports the version that actually answered. | [[reference/models-and-pricing]] |
| `JsonCache` | The cookbook helper that memoizes results into a JSON file keyed on the call's arguments — including a rubric hash and the model name — so republished cookbook numbers reproduce without API spend. | [[cookbooks/overview]] |
| `legend` | The Score answer field mapping each level number (as a string key) back to the criteria description you supplied, so you can label a score without keeping the rubric around. New in v1. | [[concepts/score]] |
| Literal reading | Jaggedness failure mode 1: `jev-1.13` answers the question you wrote rather than the one you meant, taking scoping words, negations, and implied conditions at face value. | [[concepts/jaggedness-jev-1-13]] |
| Machine-Native Intelligence | TypeSafe's term for AI with software-like properties — structure, reliability, observability, testability, speed, consistency, low cost — as opposed to chat-shaped AI aimed at a human reader. | [[concepts/machine-learning-primer]] |
| MCA | The Master Customer Agreement (last updated 2026-08-27), TypeSafe's commercial contract. It defines Input, Output, Telemetry, the acceptable-use restrictions, the liability cap, and the absence of any uptime SLA. | [[reference/legal-and-data]] |
| Mode dropping | The RLHF side effect TypeSafe cites as motivation for RLCD: preference optimisation narrows a model toward a favoured style, a milder version of GAN-style mode collapse. | [[concepts/machine-learning-primer]] |
| `model` | The required request field naming the model or alias to use, normally `"jev-latest"`. The same field on the response reports which version answered, and the two can differ. | [[reference/http-api]] |
| Noul | The yes/no primitive. It returns a single probability that the statement is true and carries no `confidence` field; `criteria.true` / `criteria.false` optionally clarify what yes and no mean. | [[concepts/noul]] |
| `noul` | The Noul answer field: a number from 0 (no) to 1 (yes), with values near 0.5 meaning genuinely uncertain rather than "medium". Called `probability` in the preview API. | [[concepts/noul]] |
| `nouls` / `choices` / `scores` | The three cached typed views on a Python `SystemOneResponse`, alongside the documented `answers` map. Upstream samples use both spellings. | [[reference/python-sdk-responses]] |
| OpenAPI document | The machine-readable contract at `https://docs.typesafe.ai/openapi.json`: `openapi: 3.1.0`, `info.title: "TypeSafe"`, `info.version: 0.2.0`, two paths and sixteen component schemas. | [[reference/openapi-schemas]] |
| Parallel sampler | The architectural claim behind Jev's speed: all outputs are produced in a single query rather than one token at a time conditioned on the last, which is why adding questions barely changes latency. | [[concepts/system-one]] |
| Playground | The console's interactive surface at `/playground`, where a state and question set can be tried and shared as a `#share/...` or `?share=shr_...` link — the form the cookbooks' share links take. | [[entities/typesafe-console]] |
| Preview endpoint | The retired `POST /preview/evaluation` API, replaced by `POST /v1/systemone`. It used `document`, a `prompts` array, `options`/`levels`, and a `responses` array, and its `confidence` used a different computation. | [[reference/migrating-to-v1]] |
| Primitive | One of the three question/answer pairs — Choice, Score, Noul — that make up every Jev request. You compose their typed answers in code rather than asking one big question. | [[concepts/primitives]] |
| `probabilities` | The distribution an answer returns over your Choice options or Score levels, summing to approximately 1. It is the raw signal; `confidence` is one summary of it, and you can compute others. | [[concepts/confidence]] |
| Question | One judgment for the model to make about the state, defined by a `type`, `instructions`, and usually `criteria`. Every question in a request sees the same state and is evaluated independently. | [[concepts/primitives]] |
| Question ID | The key you choose in the `questions` map, which the answer comes back under. It is never sent to the model, so the full meaning must live in `instructions`. | [[reference/http-api]] |
| `retry-after` / `retry-after-ms` | Response headers naming how long to wait before retrying. Both SDKs prefer `retry-after-ms` when present and cap any honoured server delay at 60 seconds before falling back to their own backoff. | [[reference/rate-limits-and-errors]] |
| `RetryPolicy` | The SDK object controlling retries: by default 2 retries, 500 ms initial backoff doubling to a 5,000 ms cap, 25% jitter, retryable statuses `{408, 429, 500–599}`. Since 0.6.0 invalid values raise at construction. | [[reference/python-sdk-retries-errors]] |
| RLCD | Reinforcement Learning for Calibrated Decisions — TypeSafe's post-training method, presented as a third path alongside RLHF and RLVR, optimising probabilities against outcomes instead of text against preference. | [[concepts/machine-learning-primer]] |
| RLHF | Reinforcement learning from human feedback — the method that turned pretrained models into chatbots, co-invented by TypeSafe cofounder Diogo Almeida, and the one TypeSafe positions itself against. | [[concepts/machine-learning-primer]] |
| RLVR | Reinforcement learning with verifiable rewards — the method behind reasoning models strong at programmatically checkable tasks, at higher latency and cost. | [[concepts/machine-learning-primer]] |
| Score | The primitive that rates a state against an ordered array of described levels, returning a probability-weighted position plus `legend`, `probabilities`, and `confidence`. | [[concepts/score]] |
| `score` | The Score answer field: a float between 0 and `len(criteria) - 1`. Called `expectation` in the preview API. | [[reference/http-api]] |
| `state` | The single input every question in a request is evaluated against — a string, JSON object, or array of text values, and nothing else. Unrelated material in it costs accuracy. | [[concepts/state]] |
| System 1 / System 2 | Kahneman's distinction in *Thinking, Fast and Slow* between fast intuitive judgment and slow deliberate reasoning, from which TypeSafe takes the name "System One". | [[concepts/system-one]] |
| System One LLM wrapper | TypeSafe's harness that constrains an LLM to emit System One-compatible structured decisions, used for the LLM baselines in its workflow evals. TypeSafe notes it "tends to be slower and more expensive" than unconstrained decisions. | [[concepts/workflow-evals]] |
| System One model | The model class: evaluates one state, returns typed answers and calibrated probabilities, never generated text, with the answer space fixed in advance. | [[concepts/system-one]] |
| `system-one-adapter` | The open-source Python package (v0.1.4) that answers `typesafe_sdk` questions with an OpenAI or Anthropic model instead of Jev, returning the same answer objects plus latency, token and per-attempt traces. | [[reference/system-one-adapter]] |
| Telemetry | The MCA's carve-out category — "technical logs, hashes, summary statistics and classifications, metrics, and learnings" — which TypeSafe may process without restriction and which survives termination. | [[reference/legal-and-data]] |
| `TYPESAFE_*` env vars | Exactly four are read by the SDKs: `TYPESAFE_API_KEY`, `TYPESAFE_BASE_URL`, `TYPESAFE_DEFAULT_MODEL`, `TYPESAFE_LOG_LEVEL`. `TYPESAFE_MODEL`, `TYPESAFE_PRICE` and similar names appear only in cookbook code. | [[reference/environment-variables]] |
| `typesafe-client` | The legacy Python package for the preview API. Every release (`0.1.x` and `1.0.x`) sends `document` and no longer works against the API — replaced by `typesafe-sdk`. | [[reference/migrating-to-v1]] |
| `typesafe-sdk` / `@typesafe-ai/sdk` | The official Python (PyPI, import `typesafe_sdk`) and JavaScript/TypeScript (npm) clients, both at 0.6.0 and both MIT. Note the unrelated PyPI package `typesafe` is not TypeSafe AI's. | [[reference/python-sdk]] |
| Uncertain band | The application-side pattern of mapping a middle range of probability or confidence to an explicit third outcome — human review — instead of forcing yes/no. TypeSafe's cookbooks use `0.30–0.70` for Nouls and a `0.60` top-probability floor for Choices. | [[cookbooks/consistency-noul]] |
| `usage` | The response object reporting `input_tokens` and `output_tokens`. Only input tokens are billed; it replaced preview's placeholder `billing_units`. | [[reference/http-api]] |
| v1 API | The current stable API: `POST /v1/systemone` and `GET /v1/models` under `https://api.typesafe.ai`, with `state`, a `questions` map, and an `answers` map. | [[reference/http-api]] |
| Workflow eval | TypeSafe's published evaluation format: a fixed code workflow, every model run through the identical harness, scored against consensus labels. Source of the "193.6x faster, 444.6x cheaper" claim. | [[concepts/workflow-evals]] |
| ZDR | Zero data retention, offered "for enterprise customers" via privacy@typesafe.ai. Outside ZDR no retention period is stated anywhere in the legal documents. | [[reference/legal-and-data]] |

## Related

- [[syntheses/faq]] — the same material as questions and answers
- [[syntheses/version-timeline]] — when each version of the above shipped
- [[syntheses/jev-vs-llm-structured-outputs]] — the terms that only matter in comparison
- [[concepts/primitives]] — the core vocabulary in context
- [[reference/http-api]] — every wire-level identifier defined above
- [[guides/agent-integration-playbook]] — how the terms fit together in a build

## Sources

- wiki pages listed in the frontmatter (all under `wiki/`)
- raw/docs/models.md (https://docs.typesafe.ai/models), raw/docs/api.md (https://docs.typesafe.ai/api)
- raw/site/openapi.json (https://docs.typesafe.ai/openapi.json) — `info.version` 0.2.0
- raw/site/blog-introducing-system-one.txt (https://typesafe.ai/blog/introducing-system-one-models-and-jev) — parallel sampler, cardinality 255