---
title: "Jev Wiki — Master Index"
type: index
tags: [index]
created: 2026-09-17
updated: 2026-09-21
confidence: high
sources: []
summary: "Catalog of every page in the wiki, one line each, grouped by section. Generated by scripts/build.mjs."
---

# Jev Wiki — Master Index

> **TL;DR** 88 content pages (plus this index and the log) about Jev, TypeSafe AI's System One model. Snapshot of upstream sources: 2026-09-17. Model: jev-1.13.0; typesafe-sdk 0.6.0; @typesafe-ai/sdk 0.6.0. New here? Read [[guides/agent-integration-playbook]] first, then [[reference/http-api]] or the SDK reference, then [[concepts/jaggedness-jev-1-13]].

This file is generated from page frontmatter by `node scripts/build.mjs`; edit the pages, not this list. Maintenance log: [[log]].

## Guides (6)

| Page | Summary | ~Tokens | Updated | Conf. |
|---|---|---|---|---|
| [[guides/agent-integration-playbook\|Playbook for LLM agents building with Jev]] | Seven-step playbook for an agent told 'use Jev for X': decide, decompose, shape state, write questions, call, consume, handle errors, test. | 7.0k | 2026-09-20 | high |
| [[guides/choosing-a-primitive\|Choosing between Choice, Score, Noul]] | Decision table mapping question shape to Choice, Score or Noul, the anti-patterns for each, and how to decompose a complex judgment into several primitives. | 3.4k | 2026-09-17 | high |
| [[guides/quickstart\|Quickstart: first call in HTTP, Python, JS]] | Get a key at console.typesafe.ai, export TYPESAFE_API_KEY, and make your first POST /v1/systemone call in curl, Python, or TypeScript. | 3.6k | 2026-09-17 | high |
| [[guides/smart-home-demo\|Smart home assistant demo walkthrough]] | TypeSafe's smart home demo: one speculative fan-out per utterance routes device commands, while an LLM handles compound splitting and conversational fallback. | 2.3k | 2026-09-17 | medium |
| [[guides/testing-and-evaluation\|Testing and evaluating a Jev workflow]] | Measure accuracy, calibration, repeatability, latency and cost on your own labelled set; pick thresholds from confidence buckets; regression-test jaggedness. | 4.3k | 2026-09-21 | high |
| [[guides/writing-instructions-and-criteria\|Writing instructions and criteria that Jev reads correctly]] | How to phrase instructions and criteria for each question type, with before/after rewrites for literal reading, negation, numbers and dates, plus an edge-case testing loop. | 4.6k | 2026-09-17 | high |

## Ideas (community) (12)

| Page | Summary | ~Tokens | Updated | Conf. |
|---|---|---|---|---|
| [[ideas/community-repos\|Community repos: what people built and how they use Jev]] | Index of 58 third-party Jev repos, one line each, split across two domain pages, plus reusable designs and a vetting checklist. | 2.6k | 2026-09-21 | medium |
| [[ideas/consult\|Consult guide: could Jev help this project?]] | Procedure for an agent asked 'here is my project, could Jev help?': what to read (10-15k tokens), how to find and filter decisions, and the shortlist format to return. | 2.0k | 2026-09-21 | medium |
| [[ideas/field-reports\|Field reports: independent evaluations, critiques, open replicas]] | What independent testers measured in Jev's first week: repeatable bounded decisions, weak standalone browser control, and probe-measured order and option-set sensitivity. | 3.4k | 2026-09-21 | medium |
| [[ideas/measurements\|Measurements, access routes and open replicas]] | Numbers measured with Jev — cost, latency, calibration, token accounting, vendor harness figures — plus access routes and replica trust notes. Every figure is one run; re-measure yours. | 3.0k | 2026-09-21 | medium |
| [[ideas/overview\|Ideas section overview]] | One-screen map of the community-tier ideas section: which index or domain page to open for which question, and how far to trust them. | 0.8k | 2026-09-21 | medium |
| [[ideas/patterns\|Decision patterns from the community (with fit verdicts)]] | Index of all 37 community decision patterns (ID, primitive, fit verdict, page), routing by project type to one of four domain pages, retrofit order, and anti-patterns. | 2.4k | 2026-09-21 | medium |
| [[ideas/patterns-agents\|Patterns: agent internals, context and coding agents]] | P01-P11 plus P35-P37: community decision patterns for agent loops, model and security routing, context, memory, coding agents and self-compiling workflows, each with a fit verdict. | 4.4k | 2026-09-21 | medium |
| [[ideas/patterns-business\|Patterns: marketing, sales, GTM, content, support and ops]] | Eleven community decision patterns for GTM, content, support and ops — lead scoring, next-best action, churn, draft QA, SEO, triage, approvals — each with a fit verdict. | 4.5k | 2026-09-21 | medium |
| [[ideas/patterns-data\|Patterns: judging, search, documents, real-time and markets]] | P15-P18 and P24-P27: community decision patterns for judging, moderation, search and ranking, corpus labelling, documents, transcripts, devices and markets, with fit verdicts. | 3.0k | 2026-09-21 | medium |
| [[ideas/patterns-interface\|Patterns: browser, computer use, voice and product UI]] | Community patterns where Jev picks the next on-screen action or labels items inside a product UI: browser agents, site-exposed tools, desktop/mobile/voice control, in-UI classifiers (P12-P14, P34). | 1.3k | 2026-09-21 | medium |
| [[ideas/repos-agents\|Repos: coding agents, orchestration, memory, browser and computer use, integrations]] | 32 community repos that put Jev inside a coding agent, an orchestrator, a browser or computer-use loop, or an MCP/CLI integration surface. | 4.4k | 2026-09-21 | medium |
| [[ideas/repos-apps\|Repos: data, documents, judging, real-time, markets, business apps, replicas]] | 23 community repos that point Jev at rows, documents, media, live simulations, markets, business questions — plus the open replicas of the interface. | 3.8k | 2026-09-21 | medium |

## Concepts (13)

| Page | Summary | ~Tokens | Updated | Conf. |
|---|---|---|---|---|
| [[concepts/advanced-structure\|Structured instructions, options, levels, criteria]] | instructions, Choice option descriptions, Score levels and Noul true/false all accept JSON: string, object, array or null (EntryType). | 3.4k | 2026-09-17 | high |
| [[concepts/choice\|Choice questions]] | Choice picks one option from a fixed set: send type/instructions/criteria, get back choice, probabilities over every option, and confidence. | 4.6k | 2026-09-17 | high |
| [[concepts/confidence\|Confidence vs probability]] | confidence is a 0-1 statistic derived from an answer's probabilities distribution; Choice and Score carry it, Noul does not. | 2.3k | 2026-09-17 | high |
| [[concepts/how-to-build\|How to build software with System One]] | Build a normal software workflow and insert System One only where AI is needed: narrow typed questions, composed in code. | 6.3k | 2026-09-17 | high |
| [[concepts/jaggedness-jev-1-13\|Jev 1.13 jaggedness: known failure modes]] | Nine documented failure modes of jev-1.13 — literal reading, math, dates, indirection, big states, adversarial text, contradictions, invariants, generation — with the mitigation for each. | 3.3k | 2026-09-17 | high |
| [[concepts/machine-learning-primer\|AI primer: why calibrated decision models]] | Why TypeSafe post-trains with RLCD for calibrated decisions instead of RLHF/RLVR for generated text. | 1.7k | 2026-09-17 | high |
| [[concepts/noul\|Noul (yes/no) questions]] | Noul asks one yes/no question and returns a single number, the probability that the answer is yes; criteria are optional true/false clarifications. | 2.3k | 2026-09-17 | high |
| [[concepts/primitives\|Primitives: Choice, Score, Noul]] | The three Jev question types (Choice, Score, Noul), the typed answers they return, how to pick one, and how to batch many questions in one request. | 3.0k | 2026-09-17 | high |
| [[concepts/score\|Score questions]] | Score rates a state against an ordered array of described levels and returns a probability-weighted position, the legend, per-level probabilities, and confidence. | 5.1k | 2026-09-17 | high |
| [[concepts/state\|State: what you send Jev]] | State is the content Jev evaluates: a string, JSON object, or array of text, shared by every question in one request. | 1.7k | 2026-09-17 | high |
| [[concepts/system-one\|System One Models]] | System One models make fast, typed, calibrated decisions software can consume directly; Jev is TypeSafe's first one. | 2.8k | 2026-09-17 | high |
| [[concepts/use-case-map\|Use-case map by industry]] | Scannable map of where Jev fits: five capability categories, eighteen industry/function areas, and ten decision shapes. | 3.2k | 2026-09-20 | high |
| [[concepts/workflow-evals\|Workflow evals: how TypeSafe measures Jev]] | TypeSafe's four workflow evals: same harness for every model, reference labels from GPT-6 Astra + Claude Fable 5.1, source of 193.6x/444.6x. | 4.0k | 2026-09-17 | high |

## Reference (18)

| Page | Summary | ~Tokens | Updated | Conf. |
|---|---|---|---|---|
| [[reference/agent-skill\|The typesafe-ai agent skill and Claude Code plugin]] | Install, update, and invoke the typesafe-ai agent skill (Claude Code plugin typesafe 0.5.7, MIT), plus a faithful digest of the guidance SKILL.md gives agents. | 5.2k | 2026-09-21 | high |
| [[reference/environment-variables\|TYPESAFE_* environment variables across SDKs]] | Exactly four TYPESAFE_* environment variables are read by the SDKs: API_KEY, BASE_URL, DEFAULT_MODEL, LOG_LEVEL — both SDKs read all four. | 2.8k | 2026-09-17 | high |
| [[reference/http-api\|HTTP API: POST /v1/systemone and GET /v1/models]] | Complete wire contract for POST https://api.typesafe.ai/v1/systemone and GET /v1/models: auth, request body, question and answer shapes, usage, errors. | 5.0k | 2026-09-17 | high |
| [[reference/javascript-sdk\|JavaScript/TypeScript SDK: install, client, choice/score/noul]] | @typesafe-ai/sdk 0.6.0: install, TypeSafeClient config and defaults, systemOne(), choice/score/noul builders, APIPromise, models.list(), logging. | 6.9k | 2026-09-17 | high |
| [[reference/javascript-sdk-changelog\|JavaScript SDK changelog]] | @typesafe-ai/sdk releases: 0.5.7 initial public release, 0.6.0 (2026-09-15) makes Score.criteria an ordered sequence — the one breaking change. | 1.8k | 2026-09-17 | high |
| [[reference/javascript-sdk-errors\|JavaScript SDK error classes, RetryPolicy, RequestOptions]] | Error hierarchy of @typesafe-ai/sdk 0.6.0, status-to-class mapping, RetryPolicy defaults (2 retries, 500ms/5s backoff, 0.25 jitter) and RequestOptions. | 5.2k | 2026-09-17 | high |
| [[reference/javascript-sdk-types\|JavaScript SDK interfaces and type aliases]] | Every interface, type alias and exported variable in @typesafe-ai/sdk 0.6.0, with per-property type/required/default tables and generics examples. | 6.0k | 2026-09-17 | high |
| [[reference/legal-and-data\|Legal: MCA, DPA, privacy, data retention]] | Developer-facing summary of TypeSafe's MCA, DPA, and Privacy Policy: no training on Input, telemetry carve-out, retention, sub-processors, acceptable use, no uptime SLA. | 5.1k | 2026-09-17 | high |
| [[reference/migrating-to-v1\|Migrating from /preview/evaluation to /v1/systemone]] | Every delta between the preview evaluation endpoint and the stable v1 API, with before/after examples, plus the typesafe-client to typesafe-sdk rename table. | 3.7k | 2026-09-17 | high |
| [[reference/models-and-pricing\|Models, aliases, pricing, rate limits, context]] | Jev 1.13 model ID, aliases, $42/Btok pricing with free output tokens, 250k tok/s and 1,200 rpm limits, 64k/32k context rule, and text-only input. | 2.7k | 2026-09-17 | high |
| [[reference/openapi-schemas\|OpenAPI component schemas]] | Every component schema in TypeSafe's OpenAPI 3.1.0 document (info version 0.2.0): properties, types, requiredness, constraints, and examples. | 4.8k | 2026-09-17 | high |
| [[reference/python-sdk\|Python SDK: install, clients, system_one()]] | typesafe-sdk 0.6.0: install, TypeSafeClient/AsyncTypeSafeClient constructor params, system_one() kwargs, models resource, env vars, logging, and the full export list. | 5.7k | 2026-09-17 | high |
| [[reference/python-sdk-changelog\|Python SDK changelog]] | typesafe-sdk release history: 0.0.1a0 placeholder, 0.5.7 initial public release (2026-09-14), 0.6.0 (2026-09-15) with the Score.criteria breaking change. | 1.8k | 2026-09-17 | high |
| [[reference/python-sdk-questions\|Python SDK question types (Noul, Choice, Score)]] | Every field of Noul, Choice and Score in typesafe-sdk 0.6.0, their TypedDict equivalents, JSONContent typing, client-side validation, and the 0.6.0 Score.criteria breaking change. | 3.1k | 2026-09-17 | high |
| [[reference/python-sdk-responses\|Python SDK responses, answers, usage, models]] | SystemOneResponse fields and the .nouls/.choices/.scores views, every answer attribute, Usage, request_id and raw_http_response, plus ListModelsResponse and ModelMetadata. | 3.4k | 2026-09-17 | high |
| [[reference/python-sdk-retries-errors\|Python SDK retries, exceptions, constants]] | RetryPolicy fields and defaults, which statuses and exceptions are retried, backoff and Retry-After handling, the full exception hierarchy with attributes, timeouts, and public constants. | 4.7k | 2026-09-17 | high |
| [[reference/rate-limits-and-errors\|HTTP status codes, rate limits, retry semantics]] | One table mapping every HTTP status to its meaning, Python exception, JS error class, retryability, and the recommended client action. | 3.6k | 2026-09-17 | high |
| [[reference/system-one-adapter\|system-one-adapter: LLM-backed drop-in for TypeSafeClient]] | system-one-adapter answers typesafe_sdk questions with an OpenAI or Anthropic LLM instead of Jev, so you can compare cost, speed, and intelligence on the same code. | 5.0k | 2026-09-17 | high |

## Patterns (5)

| Page | Summary | ~Tokens | Updated | Conf. |
|---|---|---|---|---|
| [[patterns/composite-scoring\|Composite scoring]] | Break a ranking judgment into independent Score dimensions, normalize each to 0–1, and combine them with weights your code owns and can retune. | 2.1k | 2026-09-17 | high |
| [[patterns/confidence-routing\|Confidence-gated routing]] | Treat confidence as a second decision axis: one floor below which nothing is automated, then a per-action threshold sized to the consequences of being wrong. | 2.2k | 2026-09-17 | high |
| [[patterns/fan-out\|Speculative fan-out]] | Put every question your decision tree could need into one call, including speculative ones, and let code discard the irrelevant answers. | 2.2k | 2026-09-17 | high |
| [[patterns/intent-routing\|Intent routing]] | Classify the request with one cheap Jev call, then invoke the cheapest adequate handler: deterministic code, a specialist LLM, or a human. | 2.6k | 2026-09-17 | high |
| [[patterns/overview\|Patterns overview]] | Catalog of TypeSafe's four architectural patterns — fan-out, confidence routing, composite scoring, intent routing — and when to reach for each. | 1.8k | 2026-09-17 | high |

## Cookbooks (19)

| Page | Summary | ~Tokens | Updated | Conf. |
|---|---|---|---|---|
| [[cookbooks/autoformat\|Cookbook: Structure recovery (autoformat)]] | Rebuild Markdown from de-formatted plain text in two requests: Nouls stitch hard-wrapped lines, then Choices classify each block; code renders every character from the input. | 4.5k | 2026-09-17 | high |
| [[cookbooks/autoresearch-feature-discovery\|Cookbook: Autoresearch feature discovery]] | An LLM proposes Jev questions, Jev answers them per row to build numeric columns, CatBoost trains and reports back: 38 questions after five rounds reach 1.77 held-out RMSE on wine scores. | 4.7k | 2026-09-17 | high |
| [[cookbooks/citation-check\|Cookbook: Double-checking citations]] | One Choice question decides whether a quote's surrounding section supports, contradicts, or says nothing about an LLM's claim; a string match catches fabricated quotes first. | 2.8k | 2026-09-17 | high |
| [[cookbooks/classification-using-confidence\|Cookbook: Classification using confidence]] | Classify SEC filings into 75 SIC industry groups with one Choice; when confidence < 0.9, report the broader division instead — 40% correct becomes 70%, at no extra call. | 2.9k | 2026-09-17 | high |
| [[cookbooks/classifying-rag-passages\|Cookbook: Classifying RAG passages]] | Four Noul questions per retrieved query-passage pair, routed by ordered thresholds, decide what reaches the generator as evidence, as conflict, or not at all. | 3.6k | 2026-09-17 | high |
| [[cookbooks/consistency-choice\|Cookbook: Self-consistency — choices]] | Runs an 8-Choice moderation rubric 15 times across Jev and six LLM conditions; a 0.60 top-probability floor lifts Jev's decision agreement from 90.8% to 99.2% at 74.2% automation. | 4.3k | 2026-09-17 | high |
| [[cookbooks/consistency-noul\|Cookbook: Self-consistency — nouls]] | Runs a 14-Noul claims rubric 15 times against Jev and six LLM conditions; Jev's mean probability std dev is 0.0102 at 111ms per call, and an uncertain band routes 0.30-0.70 to a human. | 3.7k | 2026-09-17 | high |
| [[cookbooks/date-extraction\|Cookbook: Date extraction]] | Seven Choice questions read a date's parts off a document in one call; code does all the calendar math and gates on the weakest part's confidence. | 3.9k | 2026-09-17 | high |
| [[cookbooks/entity-alignment\|Cookbook: Knowledge graph entity alignment]] | One three-level Score decides merge / curate / leave-unlinked for 450 candidate entity pairs, with three Nouls riding along to tell the curator which field disagrees. | 3.0k | 2026-09-17 | high |
| [[cookbooks/function-calling\|Cookbook: Function calling]] | Map typed Python functions to Jev Choice/Noul questions so a natural-language command becomes a validated call with a per-argument confidence. | 2.9k | 2026-09-17 | high |
| [[cookbooks/hierarchical-classification\|Cookbook: Hierarchical classification]] | Walk a deep taxonomy to a leaf by asking one Choice per sibling set, and keep K paths alive with a geometric-mean beam search instead of a greedy walk. | 2.9k | 2026-09-17 | high |
| [[cookbooks/llm-guardrails\|Cookbook: Guardrails for LLMs]] | Screen every LLM input and output with one Jev request: four hazard Nouls plus a severity Score, then route pass / review / block / support on thresholds you own. | 3.1k | 2026-09-17 | high |
| [[cookbooks/overview\|Cookbooks overview]] | Catalog of all 18 TypeSafe cookbooks — goal, primitives and domain each — plus how a cookbook is structured and why the published pip line does not work. | 3.4k | 2026-09-17 | high |
| [[cookbooks/parallel-questions\|Cookbook: Parallel questions]] | Batching 13 questions about one 54k-character document into a single Jev call was 12.2x cheaper and 10.0x faster than 13 single-question calls, with identical answers. | 3.1k | 2026-09-17 | high |
| [[cookbooks/pre-parsed-value-extraction\|Cookbook: Pre-parsed value extraction]] | A recall-tuned regex finds candidate spans, a Jev Choice over those exact spans picks the one the question asks for, and code copies it verbatim and normalizes it. | 2.7k | 2026-09-17 | high |
| [[cookbooks/rerank\|Cookbook: Re-ranking]] | BM25 builds a 30-candidate shortlist per CLERC query, then one Noul per query-candidate pair re-sorts it: top-1 rises 5% to 18%, top-10 38% to 62% for $0.0645. | 2.6k | 2026-09-17 | high |
| [[cookbooks/sde-cascade\|Cookbook: SDE cascade]] | Extract with a cheap model, verify every field with a battery of Jev Nouls framed so true means wrong, and escalate to a reasoning model only when a flag fires. | 4.0k | 2026-09-17 | high |
| [[cookbooks/semantic-find\|Cookbook: Line-by-line search]] | Tag a document's lines with ids, rank them with one Choice over those ids, and pair it with a Noul that says whether the document answers the query at all. | 2.4k | 2026-09-17 | high |
| [[cookbooks/skill-suggestion\|Cookbook: Skill suggestion]] | Two Jev requests per agent turn — rank 182 skills then re-read the top three — cut wrong skill loads from 16.8% to 7.3% and needless loads from 9.8% to 4.0%. | 3.8k | 2026-09-17 | high |

## Syntheses (4)

| Page | Summary | ~Tokens | Updated | Conf. |
|---|---|---|---|---|
| [[syntheses/faq\|FAQ for agents and developers]] | Forty answers about Jev — what it is, the API, the SDKs, design, confidence, limits and pricing, company and legal — each linked to the page carrying the detail. | 4.9k | 2026-09-17 | high |
| [[syntheses/glossary\|Glossary]] | 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. | 4.7k | 2026-09-17 | high |
| [[syntheses/jev-vs-llm-structured-outputs\|Jev vs LLM JSON mode / structured outputs]] | What Jev gives you that an LLM in JSON mode does not (and vice versa), a row-by-row comparison, when to pick each, how to combine them, and how to benchmark the pair honestly. | 4.3k | 2026-09-17 | medium |
| [[syntheses/version-timeline\|Versions and timeline (models, SDKs, API, company)]] | Every datable fact in the wiki on one axis: company, model versions, API, both SDKs, the plugin and adapter, legal documents, repo commits, and where the dates disagree. | 4.0k | 2026-09-17 | medium |

## Entities (11)

| Page | Summary | ~Tokens | Updated | Conf. |
|---|---|---|---|---|
| [[entities/blog-antibenchmaxxing\|Blog: Lies, Damned Lies, and Benchmarks]] | 2026-09-11 post against benchmaxxing, ending in TypeSafe's commitment to publish no standard benchmark table and to retire dated eval snapshots. | 1.7k | 2026-09-17 | high |
| [[entities/blog-bitterest-lesson\|Blog: The Bitterest Lesson]] | 2026-09-10 post arguing the ML priority order is doing the right task > data > compute > algorithms, using InstructGPT vs GPT-3 as the proof. | 1.4k | 2026-09-17 | high |
| [[entities/blog-introducing-system-one\|Blog: Introducing System One Models & Jev (2026-09-15)]] | Digest of TypeSafe's launch post: System One vs LLM comparison table, price/speed claims, the evidence section, and the caveats the post states itself. | 2.6k | 2026-09-17 | high |
| [[entities/blog-too-good-to-be-true\|Blog: AI: too good to be true, too bad to be useful (2026-06-19)]] | Stub: the body of this 2026-06-19 TypeSafe post was not captured (JS-rendered); only title, date, category, and the homepage teaser are known. | 0.7k | 2026-09-17 | low |
| [[entities/github-repos\|typesafe-ai GitHub organisation and repos]] | The github.com/typesafe-ai org: two SDKs, the agent skill marketplace, the System One adapter, plus infra repos and two forks. | 2.3k | 2026-09-20 | high |
| [[entities/jev\|Jev (model)]] | Jev is TypeSafe's first System One model: text in, typed decisions with calibrated probabilities out, $0.042/MTok input, 64k context, 70-500 ms. | 1.6k | 2026-09-17 | high |
| [[entities/manifesto\|Manifesto: Composable AI — Build Prod, Not God]] | TypeSafe's manifesto argues the bottleneck is composability, not intelligence, and lays out a three-step plan to make AI a dependable software primitive. | 1.7k | 2026-09-17 | high |
| [[entities/press-and-coverage\|Press and third-party coverage]] | Outlet-by-outlet digest of Jev's launch coverage (2026-09-15/16), separating TypeSafe's claims from each outlet's own assertions and caveats. | 3.5k | 2026-09-17 | medium |
| [[entities/team\|Founders and team]] | TypeSafe AI's three founders (Diogo Almeida CEO, Sasha Sheng COO, Erik Gafni CTO), the team's stated culture and values, and the SDK maintainers. | 1.6k | 2026-09-21 | high |
| [[entities/typesafe-ai\|TypeSafe AI (company)]] | TypeSafe AI, Inc. is a San Francisco frontier AI lab that left stealth on 2026-09-15 with $40M led by DCVC and Jev, its first System One model. | 2.5k | 2026-09-17 | high |
| [[entities/typesafe-console\|console.typesafe.ai (console + playground)]] | console.typesafe.ai is TypeSafe's Web Interface: log in with Google or an email code, try Jev in the Playground, and mint API keys. | 1.1k | 2026-09-17 | medium |

## Tags

- **acceptable-use**: [[reference/legal-and-data]]
- **access**: [[ideas/measurements]]
- **adapter**: [[reference/system-one-adapter]]
- **advanced**: [[concepts/advanced-structure]]
- **agent**: [[guides/agent-integration-playbook]]
- **agent-skill**: [[reference/agent-skill]]
- **agents**: [[cookbooks/skill-suggestion]], [[ideas/patterns-agents]]
- **answers**: [[concepts/primitives]], [[reference/python-sdk-responses]]
- **anthropic**: [[reference/system-one-adapter]]
- **api-key**: [[guides/quickstart]]
- **api-keys**: [[entities/typesafe-console]]
- **architecture**: [[concepts/how-to-build]], [[concepts/system-one]], [[patterns/overview]]
- **autoformat**: [[cookbooks/autoformat]]
- **autoresearch**: [[cookbooks/autoresearch-feature-discovery]]
- **batching**: [[cookbooks/parallel-questions]]
- **beam-search**: [[cookbooks/hierarchical-classification]]
- **benchmarking**: [[reference/system-one-adapter]]
- **benchmarks**: [[concepts/workflow-evals]], [[entities/blog-antibenchmaxxing]], [[ideas/field-reports]], [[ideas/measurements]]
- **blog**: [[entities/blog-antibenchmaxxing]], [[entities/blog-bitterest-lesson]], [[entities/blog-introducing-system-one]], [[entities/blog-too-good-to-be-true]]
- **bm25**: [[cookbooks/rerank]]
- **breaking-changes**: [[reference/migrating-to-v1]]
- **browser-agents**: [[ideas/patterns-interface]]
- **browser-use**: [[ideas/patterns-agents]], [[ideas/repos-agents]]
- **calibration**: [[concepts/confidence]], [[concepts/machine-learning-primer]], [[concepts/system-one]], [[guides/testing-and-evaluation]]
- **cascade**: [[cookbooks/sde-cascade]]
- **catalog**: [[cookbooks/overview]]
- **catboost**: [[cookbooks/autoresearch-feature-discovery]]
- **changelog**: [[reference/javascript-sdk-changelog]], [[reference/python-sdk-changelog]]
- **checklist**: [[guides/agent-integration-playbook]]
- **choice**: [[concepts/choice]], [[concepts/primitives]], [[cookbooks/autoformat]], [[cookbooks/citation-check]], [[cookbooks/classification-using-confidence]], [[cookbooks/consistency-choice]], [[cookbooks/date-extraction]], [[cookbooks/function-calling]], [[cookbooks/hierarchical-classification]], [[cookbooks/pre-parsed-value-extraction]], [[cookbooks/semantic-find]], [[cookbooks/skill-suggestion]], [[guides/choosing-a-primitive]], [[reference/python-sdk-questions]]
- **citation-check**: [[cookbooks/citation-check]]
- **claims**: [[concepts/workflow-evals]], [[entities/blog-introducing-system-one]], [[entities/press-and-coverage]], [[entities/typesafe-ai]], [[syntheses/faq]]
- **classification**: [[concepts/choice]], [[cookbooks/classification-using-confidence]], [[cookbooks/hierarchical-classification]], [[patterns/intent-routing]]
- **claude-code**: [[reference/agent-skill]]
- **client**: [[reference/javascript-sdk]], [[reference/python-sdk]]
- **coding-agents**: [[ideas/repos-agents]]
- **community**: [[ideas/community-repos]], [[ideas/measurements]], [[ideas/overview]], [[ideas/patterns]], [[ideas/repos-agents]], [[ideas/repos-apps]]
- **company**: [[entities/typesafe-ai]]
- **comparison**: [[syntheses/jev-vs-llm-structured-outputs]]
- **composable-ai**: [[entities/manifesto]]
- **composition**: [[concepts/how-to-build]], [[patterns/composite-scoring]]
- **computer-use**: [[ideas/patterns-interface]]
- **confidence**: [[concepts/choice]], [[concepts/confidence]], [[concepts/score]], [[cookbooks/citation-check]], [[cookbooks/classification-using-confidence]], [[cookbooks/date-extraction]], [[patterns/confidence-routing]]
- **configuration**: [[reference/environment-variables]]
- **consistency**: [[cookbooks/consistency-choice]], [[cookbooks/consistency-noul]], [[guides/testing-and-evaluation]]
- **console**: [[entities/typesafe-console]]
- **constants**: [[reference/python-sdk-retries-errors]]
- **consult**: [[ideas/consult]]
- **context**: [[concepts/state]], [[ideas/patterns-agents]]
- **context-length**: [[reference/models-and-pricing]]
- **cookbook**: [[cookbooks/autoformat]], [[cookbooks/autoresearch-feature-discovery]], [[cookbooks/citation-check]], [[cookbooks/classification-using-confidence]], [[cookbooks/classifying-rag-passages]], [[cookbooks/consistency-choice]], [[cookbooks/consistency-noul]], [[cookbooks/date-extraction]], [[cookbooks/entity-alignment]], [[cookbooks/function-calling]], [[cookbooks/hierarchical-classification]], [[cookbooks/llm-guardrails]], [[cookbooks/overview]], [[cookbooks/parallel-questions]], [[cookbooks/pre-parsed-value-extraction]], [[cookbooks/rerank]], [[cookbooks/sde-cascade]], [[cookbooks/semantic-find]], [[cookbooks/skill-suggestion]]
- **cost**: [[cookbooks/parallel-questions]], [[patterns/fan-out]]
- **coverage**: [[entities/press-and-coverage]]
- **criteria**: [[concepts/advanced-structure]], [[guides/writing-instructions-and-criteria]]
- **critiques**: [[ideas/field-reports]]
- **culture**: [[entities/team]]
- **curl**: [[guides/quickstart]]
- **data**: [[ideas/repos-apps]]
- **data-retention**: [[reference/legal-and-data]]
- **date-extraction**: [[cookbooks/date-extraction]]
- **dates**: [[syntheses/version-timeline]]
- **decision**: [[guides/choosing-a-primitive]]
- **decision-guide**: [[syntheses/jev-vs-llm-structured-outputs]]
- **decision-mapping**: [[ideas/consult]]
- **decision-table**: [[guides/agent-integration-playbook]]
- **decomposition**: [[concepts/how-to-build]]
- **deduplication**: [[cookbooks/entity-alignment]]
- **definitions**: [[syntheses/glossary]]
- **demo**: [[guides/smart-home-demo]]
- **design**: [[concepts/how-to-build]]
- **dispatch**: [[cookbooks/function-calling]]
- **documents**: [[ideas/patterns-data]], [[ideas/repos-apps]]
- **dpa**: [[reference/legal-and-data]]
- **entity-alignment**: [[cookbooks/entity-alignment]]
- **environment-variables**: [[reference/environment-variables]]
- **errors**: [[reference/http-api]], [[reference/javascript-sdk-errors]], [[reference/python-sdk-retries-errors]], [[reference/rate-limits-and-errors]]
- **evals**: [[concepts/workflow-evals]], [[entities/blog-antibenchmaxxing]], [[entities/blog-introducing-system-one]], [[entities/press-and-coverage]]
- **evaluation**: [[cookbooks/consistency-noul]], [[guides/testing-and-evaluation]]
- **evaluations**: [[ideas/field-reports]]
- **examples**: [[ideas/community-repos]]
- **exceptions**: [[reference/rate-limits-and-errors]]
- **extraction**: [[cookbooks/pre-parsed-value-extraction]], [[cookbooks/sde-cascade]]
- **failure-modes**: [[concepts/jaggedness-jev-1-13]]
- **fan-out**: [[cookbooks/parallel-questions]], [[guides/smart-home-demo]], [[patterns/fan-out]], [[patterns/overview]]
- **faq**: [[syntheses/faq]]
- **feature-engineering**: [[cookbooks/autoresearch-feature-discovery]]
- **field-reports**: [[ideas/field-reports]]
- **fit-verdicts**: [[ideas/patterns-business]], [[ideas/patterns]]
- **founders**: [[entities/team]]
- **function-calling**: [[cookbooks/function-calling]]
- **funding**: [[entities/typesafe-ai]]
- **github**: [[entities/github-repos]]
- **glossary**: [[syntheses/glossary]]
- **gtm**: [[ideas/patterns-business]]
- **guardrails**: [[cookbooks/llm-guardrails]]
- **guide**: [[guides/choosing-a-primitive]], [[guides/writing-instructions-and-criteria]]
- **hiring**: [[entities/team]]
- **http-api**: [[reference/http-api]], [[reference/migrating-to-v1]], [[reference/openapi-schemas]], [[reference/rate-limits-and-errors]]
- **ideas**: [[ideas/consult]], [[ideas/overview]], [[ideas/patterns-agents]], [[ideas/patterns-business]], [[ideas/patterns-data]], [[ideas/patterns-interface]], [[ideas/patterns]]
- **ideation**: [[concepts/use-case-map]]
- **index**: [[cookbooks/overview]], [[ideas/patterns]], [[index]], [[syntheses/glossary]]
- **industry**: [[concepts/use-case-map]]
- **input**: [[concepts/state]]
- **install**: [[reference/python-sdk]]
- **installation**: [[reference/agent-skill]]
- **instructgpt**: [[entities/blog-bitterest-lesson]]
- **instructions**: [[concepts/advanced-structure]], [[guides/writing-instructions-and-criteria]]
- **integration**: [[guides/agent-integration-playbook]]
- **integrations**: [[ideas/community-repos]], [[ideas/repos-agents]]
- **intent**: [[patterns/intent-routing]]
- **jaggedness**: [[concepts/jaggedness-jev-1-13]], [[guides/writing-instructions-and-criteria]]
- **javascript**: [[guides/quickstart]], [[reference/javascript-sdk-changelog]], [[reference/javascript-sdk-errors]], [[reference/javascript-sdk-types]], [[reference/javascript-sdk]]
- **javascript-sdk**: [[reference/environment-variables]]
- **jev**: [[concepts/system-one]], [[entities/blog-introducing-system-one]], [[entities/jev]], [[reference/models-and-pricing]]
- **jev-1-13**: [[concepts/jaggedness-jev-1-13]]
- **json**: [[concepts/state]]
- **json-mode**: [[syntheses/jev-vs-llm-structured-outputs]]
- **latency**: [[cookbooks/parallel-questions]], [[patterns/fan-out]]
- **launch**: [[entities/blog-introducing-system-one]]
- **legal**: [[entities/typesafe-console]], [[reference/legal-and-data]]
- **levels**: [[concepts/score]]
- **limitations**: [[concepts/jaggedness-jev-1-13]]
- **limits**: [[concepts/state]], [[entities/jev]]
- **llm**: [[syntheses/jev-vs-llm-structured-outputs]]
- **llm-fallback**: [[guides/smart-home-demo]]
- **llm-orchestration**: [[patterns/intent-routing]]
- **log**: [[log]]
- **login**: [[entities/typesafe-console]]
- **manifesto**: [[entities/manifesto]]
- **markdown**: [[cookbooks/autoformat]]
- **marketing**: [[ideas/patterns-business]]
- **measurements**: [[ideas/measurements]]
- **methodology**: [[concepts/workflow-evals]], [[entities/blog-antibenchmaxxing]]
- **migration**: [[reference/migrating-to-v1]]
- **mission**: [[entities/manifesto]]
- **model**: [[entities/jev]]
- **models**: [[reference/http-api]], [[reference/models-and-pricing]], [[reference/python-sdk-responses]]
- **moderation**: [[cookbooks/consistency-choice]], [[ideas/patterns-data]]
- **needs-reingestion**: [[entities/blog-too-good-to-be-true]]
- **noul**: [[concepts/noul]], [[concepts/primitives]], [[cookbooks/autoformat]], [[cookbooks/autoresearch-feature-discovery]], [[cookbooks/classifying-rag-passages]], [[cookbooks/consistency-noul]], [[cookbooks/entity-alignment]], [[cookbooks/function-calling]], [[cookbooks/llm-guardrails]], [[cookbooks/pre-parsed-value-extraction]], [[cookbooks/rerank]], [[cookbooks/sde-cascade]], [[cookbooks/semantic-find]], [[cookbooks/skill-suggestion]], [[guides/choosing-a-primitive]], [[reference/python-sdk-questions]]
- **npm**: [[reference/javascript-sdk-changelog]]
- **onboarding**: [[syntheses/faq]]
- **open-source**: [[entities/github-repos]]
- **openai**: [[reference/system-one-adapter]]
- **openapi**: [[reference/openapi-schemas]]
- **overview**: [[ideas/overview]]
- **packages**: [[entities/github-repos]]
- **parsing**: [[cookbooks/date-extraction]]
- **patterns**: [[concepts/use-case-map]], [[cookbooks/overview]], [[ideas/patterns-agents]], [[ideas/patterns-business]], [[ideas/patterns-data]], [[ideas/patterns-interface]], [[ideas/patterns]], [[patterns/composite-scoring]], [[patterns/confidence-routing]], [[patterns/fan-out]], [[patterns/intent-routing]], [[patterns/overview]]
- **playbook**: [[guides/agent-integration-playbook]]
- **playground**: [[entities/typesafe-console]]
- **plugin**: [[reference/agent-skill]]
- **positioning**: [[entities/manifesto]]
- **press**: [[entities/press-and-coverage]]
- **pricing**: [[entities/jev]], [[reference/models-and-pricing]]
- **primitives**: [[concepts/choice]], [[concepts/noul]], [[concepts/primitives]], [[concepts/score]], [[guides/choosing-a-primitive]]
- **privacy**: [[reference/legal-and-data]]
- **probabilities**: [[concepts/choice]], [[concepts/confidence]]
- **probability**: [[concepts/noul]]
- **products**: [[entities/typesafe-ai]]
- **progressive-disclosure**: [[cookbooks/skill-suggestion]]
- **project-assessment**: [[ideas/consult]]
- **prompt-injection**: [[cookbooks/classifying-rag-passages]]
- **prompting**: [[guides/writing-instructions-and-criteria]]
- **provenance**: [[syntheses/version-timeline]]
- **python**: [[guides/quickstart]], [[reference/python-sdk-changelog]], [[reference/python-sdk-questions]], [[reference/python-sdk-responses]], [[reference/python-sdk-retries-errors]], [[reference/python-sdk]], [[reference/system-one-adapter]]
- **python-sdk**: [[reference/environment-variables]], [[reference/migrating-to-v1]]
- **questions**: [[concepts/primitives]], [[reference/python-sdk-questions]], [[syntheses/faq]]
- **quickstart**: [[guides/quickstart]]
- **rag**: [[cookbooks/classifying-rag-passages]]
- **ranking**: [[patterns/composite-scoring]]
- **rate-limits**: [[reference/models-and-pricing]], [[reference/rate-limits-and-errors]]
- **reference**: [[reference/http-api]], [[reference/javascript-sdk-types]], [[reference/javascript-sdk]], [[reference/openapi-schemas]], [[syntheses/glossary]]
- **regex**: [[cookbooks/pre-parsed-value-extraction]]
- **releases**: [[reference/python-sdk-changelog]], [[syntheses/version-timeline]]
- **reliability**: [[concepts/jaggedness-jev-1-13]]
- **replicas**: [[ideas/community-repos]], [[ideas/field-reports]], [[ideas/measurements]], [[ideas/repos-apps]]
- **repos**: [[entities/github-repos]], [[ideas/community-repos]], [[ideas/repos-agents]], [[ideas/repos-apps]]
- **rerank**: [[cookbooks/rerank]]
- **research-philosophy**: [[entities/blog-bitterest-lesson]]
- **responses**: [[reference/python-sdk-responses]]
- **retries**: [[reference/javascript-sdk-errors]], [[reference/python-sdk-retries-errors]], [[reference/rate-limits-and-errors]]
- **retrieval**: [[cookbooks/classifying-rag-passages]], [[cookbooks/rerank]]
- **rlcd**: [[concepts/machine-learning-primer]], [[concepts/system-one]]
- **rlhf**: [[concepts/machine-learning-primer]], [[entities/blog-bitterest-lesson]], [[entities/blog-too-good-to-be-true]]
- **rlvr**: [[concepts/machine-learning-primer]]
- **routing**: [[concepts/confidence]], [[ideas/overview]], [[patterns/confidence-routing]], [[patterns/intent-routing]], [[patterns/overview]]
- **rubric**: [[concepts/score]]
- **safety**: [[cookbooks/llm-guardrails]], [[patterns/confidence-routing]]
- **scaling**: [[entities/blog-bitterest-lesson]]
- **schemas**: [[reference/openapi-schemas]]
- **score**: [[concepts/primitives]], [[concepts/score]], [[cookbooks/autoresearch-feature-discovery]], [[cookbooks/entity-alignment]], [[cookbooks/llm-guardrails]], [[guides/choosing-a-primitive]], [[patterns/composite-scoring]], [[reference/python-sdk-questions]]
- **scoring**: [[patterns/overview]]
- **sdk**: [[entities/github-repos]], [[reference/javascript-sdk-changelog]], [[reference/javascript-sdk-errors]], [[reference/javascript-sdk-types]], [[reference/javascript-sdk]], [[reference/python-sdk-changelog]], [[reference/python-sdk-questions]], [[reference/python-sdk-responses]], [[reference/python-sdk-retries-errors]], [[reference/python-sdk]]
- **search**: [[cookbooks/semantic-find]], [[ideas/patterns-data]]
- **skills**: [[reference/agent-skill]]
- **smart-home**: [[guides/smart-home-demo]]
- **speculative**: [[guides/smart-home-demo]], [[patterns/fan-out]]
- **state**: [[concepts/state]]
- **structure**: [[concepts/advanced-structure]]
- **structured-outputs**: [[syntheses/jev-vs-llm-structured-outputs]]
- **stub**: [[entities/blog-too-good-to-be-true]]
- **support**: [[ideas/patterns-business]]
- **system-one**: [[concepts/system-one]], [[entities/jev]], [[reference/python-sdk]]
- **systemone**: [[reference/http-api]]
- **taxonomy**: [[concepts/advanced-structure]], [[cookbooks/classification-using-confidence]], [[cookbooks/hierarchical-classification]]
- **team**: [[entities/team]]
- **terminology**: [[syntheses/glossary]]
- **testing**: [[guides/testing-and-evaluation]]
- **third-party**: [[entities/press-and-coverage]]
- **thresholds**: [[concepts/confidence]], [[concepts/noul]], [[cookbooks/semantic-find]], [[guides/testing-and-evaluation]], [[patterns/confidence-routing]]
- **timeline**: [[syntheses/version-timeline]]
- **timeouts**: [[reference/python-sdk-retries-errors]]
- **token-budget**: [[ideas/consult]]
- **training**: [[concepts/machine-learning-primer]]
- **troubleshooting**: [[syntheses/faq]]
- **trust**: [[entities/blog-antibenchmaxxing]]
- **types**: [[reference/javascript-sdk-types]]
- **typesafe-ai**: [[entities/typesafe-ai]]
- **typescript**: [[reference/javascript-sdk-errors]], [[reference/javascript-sdk-types]], [[reference/javascript-sdk]]
- **ui**: [[ideas/patterns-interface]]
- **uncertainty**: [[cookbooks/consistency-choice]], [[cookbooks/consistency-noul]]
- **usage**: [[reference/python-sdk-responses]]
- **use-cases**: [[concepts/use-case-map]]
- **v1**: [[reference/migrating-to-v1]]
- **validation**: [[reference/openapi-schemas]]
- **verification**: [[cookbooks/citation-check]], [[cookbooks/sde-cascade]]
- **versions**: [[reference/javascript-sdk-changelog]], [[reference/python-sdk-changelog]], [[syntheses/version-timeline]]
- **weights**: [[patterns/composite-scoring]]
- **workflow**: [[concepts/how-to-build]]
- **workflows**: [[concepts/workflow-evals]]
- **yes-no**: [[concepts/noul]]