~/wiki
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 Playbook for LLM agents building with Jev first, then HTTP API: POST /v1/systemone and GET /v1/models or the SDK reference, then Jev 1.13 jaggedness: known failure modes.
This file is generated from page frontmatter by node scripts/build.mjs; edit the pages, not this list. Maintenance log: Activity log.
Guides (6)
| Page | Summary | ~Tokens | Updated | Conf. |
|---|---|---|---|---|
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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. |
|---|---|---|---|---|
| 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 |
| 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 |
| 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 |
| 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 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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. |
|---|---|---|---|---|
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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. |
|---|---|---|---|---|
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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. |
|---|---|---|---|---|
| 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 |
| 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 |
| 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 |
| 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 | 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. |
|---|---|---|---|---|
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 | 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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. |
|---|---|---|---|---|
| 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 |
| 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 |
| 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 |
| 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. |
|---|---|---|---|---|
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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: Legal: MCA, DPA, privacy, data retention
- access: Measurements, access routes and open replicas
- adapter: system-one-adapter: LLM-backed drop-in for TypeSafeClient
- advanced: Structured instructions, options, levels, criteria
- agent: Playbook for LLM agents building with Jev
- agent-skill: The typesafe-ai agent skill and Claude Code plugin
- agents: Cookbook: Skill suggestion, Patterns: agent internals, context and coding agents
- answers: Primitives: Choice, Score, Noul, Python SDK responses, answers, usage, models
- anthropic: system-one-adapter: LLM-backed drop-in for TypeSafeClient
- api-key: Quickstart: first call in HTTP, Python, JS
- api-keys: console.typesafe.ai (console + playground)
- architecture: How to build software with System One, System One Models, Patterns overview
- autoformat: Cookbook: Structure recovery (autoformat)
- autoresearch: Cookbook: Autoresearch feature discovery
- batching: Cookbook: Parallel questions
- beam-search: Cookbook: Hierarchical classification
- benchmarking: system-one-adapter: LLM-backed drop-in for TypeSafeClient
- benchmarks: Workflow evals: how TypeSafe measures Jev, Blog: Lies, Damned Lies, and Benchmarks, Field reports: independent evaluations, critiques, open replicas, Measurements, access routes and open replicas
- blog: Blog: Lies, Damned Lies, and Benchmarks, Blog: The Bitterest Lesson, Blog: Introducing System One Models & Jev (2026-09-15), Blog: AI: too good to be true, too bad to be useful (2026-06-19)
- bm25: Cookbook: Re-ranking
- breaking-changes: Migrating from /preview/evaluation to /v1/systemone
- browser-agents: Patterns: browser, computer use, voice and product UI
- browser-use: Patterns: agent internals, context and coding agents, Repos: coding agents, orchestration, memory, browser and computer use, integrations
- calibration: Confidence vs probability, AI primer: why calibrated decision models, System One Models, Testing and evaluating a Jev workflow
- cascade: Cookbook: SDE cascade
- catalog: Cookbooks overview
- catboost: Cookbook: Autoresearch feature discovery
- changelog: JavaScript SDK changelog, Python SDK changelog
- checklist: Playbook for LLM agents building with Jev
- choice: Choice questions, Primitives: Choice, Score, Noul, Cookbook: Structure recovery (autoformat), Cookbook: Double-checking citations, Cookbook: Classification using confidence, Cookbook: Self-consistency — choices, Cookbook: Date extraction, Cookbook: Function calling, Cookbook: Hierarchical classification, Cookbook: Pre-parsed value extraction, Cookbook: Line-by-line search, Cookbook: Skill suggestion, Choosing between Choice, Score, Noul, Python SDK question types (Noul, Choice, Score)
- citation-check: Cookbook: Double-checking citations
- claims: Workflow evals: how TypeSafe measures Jev, Blog: Introducing System One Models & Jev (2026-09-15), Press and third-party coverage, TypeSafe AI (company), FAQ for agents and developers
- classification: Choice questions, Cookbook: Classification using confidence, Cookbook: Hierarchical classification, Intent routing
- claude-code: The typesafe-ai agent skill and Claude Code plugin
- client: JavaScript/TypeScript SDK: install, client, choice/score/noul, Python SDK: install, clients, system_one()
- coding-agents: Repos: coding agents, orchestration, memory, browser and computer use, integrations
- community: Community repos: what people built and how they use Jev, Measurements, access routes and open replicas, Ideas section overview, Decision patterns from the community (with fit verdicts), Repos: coding agents, orchestration, memory, browser and computer use, integrations, Repos: data, documents, judging, real-time, markets, business apps, replicas
- company: TypeSafe AI (company)
- comparison: Jev vs LLM JSON mode / structured outputs
- composable-ai: Manifesto: Composable AI — Build Prod, Not God
- composition: How to build software with System One, Composite scoring
- computer-use: Patterns: browser, computer use, voice and product UI
- confidence: Choice questions, Confidence vs probability, Score questions, Cookbook: Double-checking citations, Cookbook: Classification using confidence, Cookbook: Date extraction, Confidence-gated routing
- configuration: TYPESAFE_* environment variables across SDKs
- consistency: Cookbook: Self-consistency — choices, Cookbook: Self-consistency — nouls, Testing and evaluating a Jev workflow
- console: console.typesafe.ai (console + playground)
- constants: Python SDK retries, exceptions, constants
- consult: Consult guide: could Jev help this project?
- context: State: what you send Jev, Patterns: agent internals, context and coding agents
- context-length: Models, aliases, pricing, rate limits, context
- cookbook: Cookbook: Structure recovery (autoformat), Cookbook: Autoresearch feature discovery, Cookbook: Double-checking citations, Cookbook: Classification using confidence, Cookbook: Classifying RAG passages, Cookbook: Self-consistency — choices, Cookbook: Self-consistency — nouls, Cookbook: Date extraction, Cookbook: Knowledge graph entity alignment, Cookbook: Function calling, Cookbook: Hierarchical classification, Cookbook: Guardrails for LLMs, Cookbooks overview, Cookbook: Parallel questions, Cookbook: Pre-parsed value extraction, Cookbook: Re-ranking, Cookbook: SDE cascade, Cookbook: Line-by-line search, Cookbook: Skill suggestion
- cost: Cookbook: Parallel questions, Speculative fan-out
- coverage: Press and third-party coverage
- criteria: Structured instructions, options, levels, criteria, Writing instructions and criteria that Jev reads correctly
- critiques: Field reports: independent evaluations, critiques, open replicas
- culture: Founders and team
- curl: Quickstart: first call in HTTP, Python, JS
- data: Repos: data, documents, judging, real-time, markets, business apps, replicas
- data-retention: Legal: MCA, DPA, privacy, data retention
- date-extraction: Cookbook: Date extraction
- dates: Versions and timeline (models, SDKs, API, company)
- decision: Choosing between Choice, Score, Noul
- decision-guide: Jev vs LLM JSON mode / structured outputs
- decision-mapping: Consult guide: could Jev help this project?
- decision-table: Playbook for LLM agents building with Jev
- decomposition: How to build software with System One
- deduplication: Cookbook: Knowledge graph entity alignment
- definitions: Glossary
- demo: Smart home assistant demo walkthrough
- design: How to build software with System One
- dispatch: Cookbook: Function calling
- documents: Patterns: judging, search, documents, real-time and markets, Repos: data, documents, judging, real-time, markets, business apps, replicas
- dpa: Legal: MCA, DPA, privacy, data retention
- entity-alignment: Cookbook: Knowledge graph entity alignment
- environment-variables: TYPESAFE_* environment variables across SDKs
- errors: HTTP API: POST /v1/systemone and GET /v1/models, JavaScript SDK error classes, RetryPolicy, RequestOptions, Python SDK retries, exceptions, constants, HTTP status codes, rate limits, retry semantics
- evals: Workflow evals: how TypeSafe measures Jev, Blog: Lies, Damned Lies, and Benchmarks, Blog: Introducing System One Models & Jev (2026-09-15), Press and third-party coverage
- evaluation: Cookbook: Self-consistency — nouls, Testing and evaluating a Jev workflow
- evaluations: Field reports: independent evaluations, critiques, open replicas
- examples: Community repos: what people built and how they use Jev
- exceptions: HTTP status codes, rate limits, retry semantics
- extraction: Cookbook: Pre-parsed value extraction, Cookbook: SDE cascade
- failure-modes: Jev 1.13 jaggedness: known failure modes
- fan-out: Cookbook: Parallel questions, Smart home assistant demo walkthrough, Speculative fan-out, Patterns overview
- faq: FAQ for agents and developers
- feature-engineering: Cookbook: Autoresearch feature discovery
- field-reports: Field reports: independent evaluations, critiques, open replicas
- fit-verdicts: Patterns: marketing, sales, GTM, content, support and ops, Decision patterns from the community (with fit verdicts)
- founders: Founders and team
- function-calling: Cookbook: Function calling
- funding: TypeSafe AI (company)
- github: typesafe-ai GitHub organisation and repos
- glossary: Glossary
- gtm: Patterns: marketing, sales, GTM, content, support and ops
- guardrails: Cookbook: Guardrails for LLMs
- guide: Choosing between Choice, Score, Noul, Writing instructions and criteria that Jev reads correctly
- hiring: Founders and team
- http-api: HTTP API: POST /v1/systemone and GET /v1/models, Migrating from /preview/evaluation to /v1/systemone, OpenAPI component schemas, HTTP status codes, rate limits, retry semantics
- ideas: Consult guide: could Jev help this project?, Ideas section overview, Patterns: agent internals, context and coding agents, Patterns: marketing, sales, GTM, content, support and ops, Patterns: judging, search, documents, real-time and markets, Patterns: browser, computer use, voice and product UI, Decision patterns from the community (with fit verdicts)
- ideation: Use-case map by industry
- index: Cookbooks overview, Decision patterns from the community (with fit verdicts), Jev Wiki — Master Index, Glossary
- industry: Use-case map by industry
- input: State: what you send Jev
- install: Python SDK: install, clients, system_one()
- installation: The typesafe-ai agent skill and Claude Code plugin
- instructgpt: Blog: The Bitterest Lesson
- instructions: Structured instructions, options, levels, criteria, Writing instructions and criteria that Jev reads correctly
- integration: Playbook for LLM agents building with Jev
- integrations: Community repos: what people built and how they use Jev, Repos: coding agents, orchestration, memory, browser and computer use, integrations
- intent: Intent routing
- jaggedness: Jev 1.13 jaggedness: known failure modes, Writing instructions and criteria that Jev reads correctly
- javascript: Quickstart: first call in HTTP, Python, JS, JavaScript SDK changelog, JavaScript SDK error classes, RetryPolicy, RequestOptions, JavaScript SDK interfaces and type aliases, JavaScript/TypeScript SDK: install, client, choice/score/noul
- javascript-sdk: TYPESAFE_* environment variables across SDKs
- jev: System One Models, Blog: Introducing System One Models & Jev (2026-09-15), Jev (model), Models, aliases, pricing, rate limits, context
- jev-1-13: Jev 1.13 jaggedness: known failure modes
- json: State: what you send Jev
- json-mode: Jev vs LLM JSON mode / structured outputs
- latency: Cookbook: Parallel questions, Speculative fan-out
- launch: Blog: Introducing System One Models & Jev (2026-09-15)
- legal: console.typesafe.ai (console + playground), Legal: MCA, DPA, privacy, data retention
- levels: Score questions
- limitations: Jev 1.13 jaggedness: known failure modes
- limits: State: what you send Jev, Jev (model)
- llm: Jev vs LLM JSON mode / structured outputs
- llm-fallback: Smart home assistant demo walkthrough
- llm-orchestration: Intent routing
- log: Activity log
- login: console.typesafe.ai (console + playground)
- manifesto: Manifesto: Composable AI — Build Prod, Not God
- markdown: Cookbook: Structure recovery (autoformat)
- marketing: Patterns: marketing, sales, GTM, content, support and ops
- measurements: Measurements, access routes and open replicas
- methodology: Workflow evals: how TypeSafe measures Jev, Blog: Lies, Damned Lies, and Benchmarks
- migration: Migrating from /preview/evaluation to /v1/systemone
- mission: Manifesto: Composable AI — Build Prod, Not God
- model: Jev (model)
- models: HTTP API: POST /v1/systemone and GET /v1/models, Models, aliases, pricing, rate limits, context, Python SDK responses, answers, usage, models
- moderation: Cookbook: Self-consistency — choices, Patterns: judging, search, documents, real-time and markets
- needs-reingestion: Blog: AI: too good to be true, too bad to be useful (2026-06-19)
- noul: Noul (yes/no) questions, Primitives: Choice, Score, Noul, Cookbook: Structure recovery (autoformat), Cookbook: Autoresearch feature discovery, Cookbook: Classifying RAG passages, Cookbook: Self-consistency — nouls, Cookbook: Knowledge graph entity alignment, Cookbook: Function calling, Cookbook: Guardrails for LLMs, Cookbook: Pre-parsed value extraction, Cookbook: Re-ranking, Cookbook: SDE cascade, Cookbook: Line-by-line search, Cookbook: Skill suggestion, Choosing between Choice, Score, Noul, Python SDK question types (Noul, Choice, Score)
- npm: JavaScript SDK changelog
- onboarding: FAQ for agents and developers
- open-source: typesafe-ai GitHub organisation and repos
- openai: system-one-adapter: LLM-backed drop-in for TypeSafeClient
- openapi: OpenAPI component schemas
- overview: Ideas section overview
- packages: typesafe-ai GitHub organisation and repos
- parsing: Cookbook: Date extraction
- patterns: Use-case map by industry, Cookbooks overview, Patterns: agent internals, context and coding agents, Patterns: marketing, sales, GTM, content, support and ops, Patterns: judging, search, documents, real-time and markets, Patterns: browser, computer use, voice and product UI, Decision patterns from the community (with fit verdicts), Composite scoring, Confidence-gated routing, Speculative fan-out, Intent routing, Patterns overview
- playbook: Playbook for LLM agents building with Jev
- playground: console.typesafe.ai (console + playground)
- plugin: The typesafe-ai agent skill and Claude Code plugin
- positioning: Manifesto: Composable AI — Build Prod, Not God
- press: Press and third-party coverage
- pricing: Jev (model), Models, aliases, pricing, rate limits, context
- primitives: Choice questions, Noul (yes/no) questions, Primitives: Choice, Score, Noul, Score questions, Choosing between Choice, Score, Noul
- privacy: Legal: MCA, DPA, privacy, data retention
- probabilities: Choice questions, Confidence vs probability
- probability: Noul (yes/no) questions
- products: TypeSafe AI (company)
- progressive-disclosure: Cookbook: Skill suggestion
- project-assessment: Consult guide: could Jev help this project?
- prompt-injection: Cookbook: Classifying RAG passages
- prompting: Writing instructions and criteria that Jev reads correctly
- provenance: Versions and timeline (models, SDKs, API, company)
- python: Quickstart: first call in HTTP, Python, JS, Python SDK changelog, Python SDK question types (Noul, Choice, Score), Python SDK responses, answers, usage, models, Python SDK retries, exceptions, constants, Python SDK: install, clients, system_one(), system-one-adapter: LLM-backed drop-in for TypeSafeClient
- python-sdk: TYPESAFE_* environment variables across SDKs, Migrating from /preview/evaluation to /v1/systemone
- questions: Primitives: Choice, Score, Noul, Python SDK question types (Noul, Choice, Score), FAQ for agents and developers
- quickstart: Quickstart: first call in HTTP, Python, JS
- rag: Cookbook: Classifying RAG passages
- ranking: Composite scoring
- rate-limits: Models, aliases, pricing, rate limits, context, HTTP status codes, rate limits, retry semantics
- reference: HTTP API: POST /v1/systemone and GET /v1/models, JavaScript SDK interfaces and type aliases, JavaScript/TypeScript SDK: install, client, choice/score/noul, OpenAPI component schemas, Glossary
- regex: Cookbook: Pre-parsed value extraction
- releases: Python SDK changelog, Versions and timeline (models, SDKs, API, company)
- reliability: Jev 1.13 jaggedness: known failure modes
- replicas: Community repos: what people built and how they use Jev, Field reports: independent evaluations, critiques, open replicas, Measurements, access routes and open replicas, Repos: data, documents, judging, real-time, markets, business apps, replicas
- repos: typesafe-ai GitHub organisation and repos, Community repos: what people built and how they use Jev, Repos: coding agents, orchestration, memory, browser and computer use, integrations, Repos: data, documents, judging, real-time, markets, business apps, replicas
- rerank: Cookbook: Re-ranking
- research-philosophy: Blog: The Bitterest Lesson
- responses: Python SDK responses, answers, usage, models
- retries: JavaScript SDK error classes, RetryPolicy, RequestOptions, Python SDK retries, exceptions, constants, HTTP status codes, rate limits, retry semantics
- retrieval: Cookbook: Classifying RAG passages, Cookbook: Re-ranking
- rlcd: AI primer: why calibrated decision models, System One Models
- rlhf: AI primer: why calibrated decision models, Blog: The Bitterest Lesson, Blog: AI: too good to be true, too bad to be useful (2026-06-19)
- rlvr: AI primer: why calibrated decision models
- routing: Confidence vs probability, Ideas section overview, Confidence-gated routing, Intent routing, Patterns overview
- rubric: Score questions
- safety: Cookbook: Guardrails for LLMs, Confidence-gated routing
- scaling: Blog: The Bitterest Lesson
- schemas: OpenAPI component schemas
- score: Primitives: Choice, Score, Noul, Score questions, Cookbook: Autoresearch feature discovery, Cookbook: Knowledge graph entity alignment, Cookbook: Guardrails for LLMs, Choosing between Choice, Score, Noul, Composite scoring, Python SDK question types (Noul, Choice, Score)
- scoring: Patterns overview
- sdk: typesafe-ai GitHub organisation and repos, JavaScript SDK changelog, JavaScript SDK error classes, RetryPolicy, RequestOptions, JavaScript SDK interfaces and type aliases, JavaScript/TypeScript SDK: install, client, choice/score/noul, Python SDK changelog, Python SDK question types (Noul, Choice, Score), Python SDK responses, answers, usage, models, Python SDK retries, exceptions, constants, Python SDK: install, clients, system_one()
- search: Cookbook: Line-by-line search, Patterns: judging, search, documents, real-time and markets
- skills: The typesafe-ai agent skill and Claude Code plugin
- smart-home: Smart home assistant demo walkthrough
- speculative: Smart home assistant demo walkthrough, Speculative fan-out
- state: State: what you send Jev
- structure: Structured instructions, options, levels, criteria
- structured-outputs: Jev vs LLM JSON mode / structured outputs
- stub: Blog: AI: too good to be true, too bad to be useful (2026-06-19)
- support: Patterns: marketing, sales, GTM, content, support and ops
- system-one: System One Models, Jev (model), Python SDK: install, clients, system_one()
- systemone: HTTP API: POST /v1/systemone and GET /v1/models
- taxonomy: Structured instructions, options, levels, criteria, Cookbook: Classification using confidence, Cookbook: Hierarchical classification
- team: Founders and team
- terminology: Glossary
- testing: Testing and evaluating a Jev workflow
- third-party: Press and third-party coverage
- thresholds: Confidence vs probability, Noul (yes/no) questions, Cookbook: Line-by-line search, Testing and evaluating a Jev workflow, Confidence-gated routing
- timeline: Versions and timeline (models, SDKs, API, company)
- timeouts: Python SDK retries, exceptions, constants
- token-budget: Consult guide: could Jev help this project?
- training: AI primer: why calibrated decision models
- troubleshooting: FAQ for agents and developers
- trust: Blog: Lies, Damned Lies, and Benchmarks
- types: JavaScript SDK interfaces and type aliases
- typesafe-ai: TypeSafe AI (company)
- typescript: JavaScript SDK error classes, RetryPolicy, RequestOptions, JavaScript SDK interfaces and type aliases, JavaScript/TypeScript SDK: install, client, choice/score/noul
- ui: Patterns: browser, computer use, voice and product UI
- uncertainty: Cookbook: Self-consistency — choices, Cookbook: Self-consistency — nouls
- usage: Python SDK responses, answers, usage, models
- use-cases: Use-case map by industry
- v1: Migrating from /preview/evaluation to /v1/systemone
- validation: OpenAPI component schemas
- verification: Cookbook: Double-checking citations, Cookbook: SDE cascade
- versions: JavaScript SDK changelog, Python SDK changelog, Versions and timeline (models, SDKs, API, company)
- weights: Composite scoring
- workflow: How to build software with System One
- workflows: Workflow evals: how TypeSafe measures Jev
- yes-no: Noul (yes/no) questions