Guides — field manual for System One.
Conceptual ladder first, then hands-on recipes. Use Cases stay on their own index.
- 4 foundation pages
- 35 recipe pages
- Compare + local checklist
- Paraphrased from public TypeSafe docs
Foundations
What Jev is → vs chat/code → Choice / Score / Noul → first small task.
01
What is Jev?
Jev is TypeSafe’s System One decision model: send state + typed questions, get structured answers your code can branch on—illustrated with a support email, not a chat.
- Paraphrased from public TypeSafe docs
- See Sources below
02
Jev, chat models, and code — who owns what
Code owns control flow and side effects; Jev owns narrow semantic judgments; LLMs write prose when you need text. Prefer workflows + gates over open agent loops.
- Paraphrased from TypeSafe how-to-build guidance
- See Sources below
03
Choice, Score, or Noul — how to pick
Choice selects from a closed set; Score rates ordered levels; Noul returns P(yes). Mix them in one call; each question runs in parallel against the same state.
- Paraphrased from public primitives docs
- See Sources below
04
Pick a small first task
Shrink “AI handles support” to a reviewable label on desensitized mail. Define input, options, success checks, and what you refuse to automate.
- Field-manual template; not an official mandate
- Cite TypeSafe use-case map for patterns
Recipes
Prepare materials → support routing → RAG filtering → n8n → extract and validate.
Step 01
Prepare materials
API key, SDK or HTTP, optional Gateway; decide atomic judgments, state fields, thresholds, and escalate paths before you code.
Step 02
Hands-on: support email routing
Route desensitized mail into shipping/refund/billing/other for human review—never refund or send mail from the model path.
Step 03
RAG passage filtering
Retrieve candidates with your search stack; ask Jev which snippets are relevant enough to keep—code enforces the cut.
Step 04
n8n automation
Call Jev from n8n via community node or HTTP; gate side effects on confidence — community node ≠ TypeSafe product.
Step 05
Extract and validate
Let Jev propose or select candidate field values; deterministic validators own schema, ranges, and rejects.
Step 06
Local deployment checklist
Hosted Jev stays on TypeSafe’s API. This checklist covers calling that API from your machine, then independent local runtimes with a System One–shaped HTTP API.
Step 07
First System One API call (LearnJev)
External walkthrough: curl/Python/TS Noul, response shape, usage notes; pin model version.
Step 08
Jev in Node.js (Flavio Copes)
External Node.js recipe for calling Jev; sibling of the Flavio Copes Jev deep-dive — verify against current TypeSafe docs.
Step 09
Jev course hub (jev-tutorial.org)
External course hub of Jev tutorials and guides; start from the tutorials index and the API quickstart outbound.
Step 10
Build a fact checker with Jev + SerpApi
External walkthrough: SerpApi Google results → Jev Choice verdict (supported/contradicted/mixed/insufficient).
Step 11
How to use Jev — practical System One guide (Valyu)
External DEV guide: setup, Choice/Score/Noul, cascade & retrieve-then-judge patterns, failure modes.
Step 12
AI that doesn't talk — plain-English Jev guide (ZipLyne)
External plain-English intro: typed answers, confidence branches, where Jev fits beside chat models.
Step 13
Gate agent tool calls with Jev (OpenRouter)
External OpenRouter cookbook — per-call Noul checks → approve/block/review thresholds instead of blanket HITL.
Step 14
Verified cascade with Jev (OpenRouter)
External OpenRouter cookbook — check a cheaper draft with Jev before accept or escalate.
Step 15
Jev API tutorial: a typed ticket router (DataCamp)
External DataCamp tutorial by Tom Farnschläder — call the Jev API and build a typed ticket router with closed answers.
Step 16
Classify text with Jev (Flavio Copes)
External Flavio Copes recipe for text classification with Jev; sibling of his Node.js call-Jev post — verify against current TypeSafe docs.
Step 17
What Is Jev? Explained for PMs (Product Compass)
External Product Compass issue by Paweł Huryn: Jev's three question types, how he uses one Choice question to moderate AskOne, and quick wins for PMs. Later sections are paid.
Step 18
Two Jevs, One Dungeon Crawl (Altered Craft)
External post by Sam Keen: running Open Jev locally on a MacBook with MLX, then pointing a Godot text adventure built for the TypeSafe Jev API at both models and comparing answers and confidence.
Step 19
How QuizPilot Uses Jev to Answer Quiz Questions (90-question benchmark)
External post by the QuizPilot developer: how single-choice, true/false and multi-select questions map onto Jev, and a small self-written benchmark against two LLMs, with confidence used to pick answers for re-checking.
Step 20
Jev in Quote-to-Cash: Deal Desk, Disputes, Collections (RevExOS)
External post from RevExOS: four quote-to-cash decision points mapped to Jev Noul, Choice and Score questions, with raw requests and responses, and a clear list of what Jev should not do in finance workflows.
Step 21
Nine Ways to Use Jev in AI Apps and Agent Workflows (To Data & Beyond)
External post from To Data & Beyond: nine Jev decision patterns, from model routing to confidence gating, with Python examples and small live comparisons against GPT-4.1 mini with structured outputs. The full post is for paid subscribers.
Step 22
GraphRAG with TypeSafe Jev (Towards Data Science)
External TDS article by Partha Sarkar (2026-09-27): use Jev Noul, Choice and Score for high-frequency GraphRAG micro-decisions—entity resolution, schema mapping, subgraph pruning—while LLMs keep synthesis.
Step 23
JevEval: Jev-as-a-Judge in DeepEval
External DeepEval blog and docs: define Noul, Score and Choice questions yourself; TypeSafe Jev answers them with calibrated probabilities; DeepEval turns the answers into a fixed, inspectable metric score with no evaluation LLM.
Step 24
How to Use Jev AI: a detective-game tutorial (Analytics Vidhya)
External Analytics Vidhya tutorial by Riya Bansal (2026-10-15): build a Python interrogation game where TypeSafe Jev answers seven Choice/Score/Noul questions per turn and your code owns the story.
Step 24
Jev 1.14: What's New and How to Upgrade
Jev 1.14.0 brings small gains everywhere and the biggest gain in multilingual support. Same price as 1.13. Experimental images, box type and long context.
Step 25
Jev Meets the Trolley Problem (Zach Landes)
External essay by Zach Landes (2026-10-14): put TypeSafe Jev and other decision models on the classic trolley dilemma, then read calibrated Choice answers — not chat.
Step 26
Benchmarking Jev's Box Tool on ScreenSpot (Arthur Katcher)
External benchmark write-up by Arthur Katcher (2026-10-17): Jev 1.14 box on ScreenSpot-v2 and ScreenSpot-Pro with official scoring, plus a zoomed second look and five harness rules for click agents.
Step 27
Can Jev Replace Hand-Written Routing Rules? (Mo Al Mamun)
External experiment by Mo Al Mamun on DEV (2026-10-17): rules, Jev, an LLM and a rules+Jev hybrid route 3,080 Banking77 messages to 77 backend actions, with accuracy, latency, cost and referral trade-offs.
Step 28
A Jev Gate in Front of Your LLM (Stas Slutsker)
External write-up by Stas Slutsker on DEV (2026-10-20): one Jev call with a choice and a noul question decides whether a Hebrew stock-review RAG assistant runs its expensive generation, tested on 134 questions in Hebrew and English.
Step 29
Decision Models for Evals: Tune the Threshold (Hamel Husain)
External write-up by Hamel Husain and Antaripa Saha (2026-10-20): use decision models such as Jev as eval judges, tune each model's threshold instead of trusting 0.50, compare cost and performance, and check calibration before reading scores as confidence.
Step 30
Jev Guardrails on AWS: Allow, Ask or Block a Tool Call (Rasik Rahman S)
External build write-up by Rasik Rahman S (2026-10-21): a Lambda guardrail asks Jev three typed questions about each proposed agent tool call (risk, intent match, exfiltration), applies a threshold policy in code, logs to DynamoDB and returns allow, ask or block.
Step 30
Clairic and Jev on 100 Return Emails (UnlockJapan)
External write-up by Takuma Yoshida at UnlockJapan (2026-10-26): four layouts that combine Cloudflare Clairic, TypeSafe Jev 1.14 and Claude Haiku 5.5 on 100 return/refund emails, with accuracy, cost and confidence-split results.
Step 31
Jev in Cloud Operations with PowerShell (Olivier Miossec)
External DEV write-up by Olivier Miossec (2026-10-01): use Doug Finke's Jev PowerShell module to gate Bicep What-If changes, review NSG rules, and triage Azure Policy linter findings with hosted TypeSafe Choice / Noul / Score questions.
Step 32
Jev Gives You Probabilities, Not Decisions (Olivier Miossec)
External DEV write-up by Olivier Miossec (posted 2026-10-09, edited 2026-10-25): the mental model behind hosted TypeSafe Jev—state vs questions, Score / Noul / Choice, confidence thresholds, and writing atomic questions—with PowerShell examples that apply in any language.
Step 33
Atomic questions beat crammed principles (Takuma Yoshida)
External note.com write-up by Takuma Yoshida (2026-10-29): on Kaggle Game Arena Bargaining, splitting negotiation principles into many small hosted TypeSafe Jev questions (then optionally moving calculable parts to Python) beat stuffing seven principles into one prompt.
Compare
Hosted Jev versus independently published System One–style tools. Official sources only.