Docs
OfficialJev Guides & Articles
Cookbooks Index
The index of TypeSafe's worked examples, from parallel questions and reranking to guardrails, date extraction, and self-consistency, each with datasets and measured results.
- Format
- Docs
- Reading time
- 2 min
- Published by
- TypeSafe AI
- Last verified
- Sep 2026
Highlights
- Parallel questions cookbook: a 13-question GDPR briefing in one call, 12.2x cheaper and 10.0x faster.
- Reranking 30-passage BM25 shortlists over 40 legal queries moved top-1 from 5% to 18%.
- Other recipes cover skill suggestion over 182 skills and SEC reports into 75 industry groups.
Watch out
Vendor-authored examples rather than independent evaluations; each links to its own subpage.
Questions about this entry
Short answers drawn from the linked project or page.
Worked examples from parallel questions and reranking to guardrails, date extraction, and self-consistency, each with datasets and measured results: for example the 13-question GDPR briefing batched 12.2x cheaper and 10.0x faster.
No. The caveat calls them vendor-authored examples rather than independent evaluations, and each links to its own subpage with its own measurements and caveats.
The primitives and the confidence page. The index says it assumes you already know the TypeSafe primitives and understand how confidence works.
On the 13-question regulatory briefing over the GDPR article, batching every question into one call was 12.2x cheaper and 10.0x faster with no change in answers.
It built 30-passage BM25 shortlists for 40 CLERC legal queries and used one question per query-candidate pair to raise top-1 accuracy from 5% to 18% and top-10 from 38% to 62%.
Into Self-consistency, Batching, How-to, Extraction and Classification sections, each recipe labelled Beginner, Intermediate or Advanced.
It classifies SEC annual reports into 75 industry groups with one Choice each, then reads the answer's own confidence to decide whether to report that group or the broader division above it.
More Jev resources like this
A browsable atlas of 1,018 AI papers from August 2025 to August 2026, sorted into 24 topic collections with labs, citations, and code links, plus a reproducible cost benchmark for summarizing 1,000 papers.
Jev Guides & ArticlesArticle#community#directory#benchmarks
Community
TypeSafe's 11 September 2026 essay against benchmaxxing: a public eval can select the model even when nobody trains on that test.
Jev Guides & ArticlesArticle#official#benchmarks#evaluation
Official
The hub for TypeSafe's legal and policy documents, plus the data commitments attached to the API.
Jev Guides & ArticlesDocs#official#docs#privacy
Official
TypeSafe AI's product site for Jev, its first System One Model: typed decisions with calibrated confidence, performance and pricing claims, a FAQ, and links to the docs, console, workflow evals, and launch post.
Jev Guides & ArticlesDocs#official#docs#models
Official
The idea behind Jev: models that return typed decisions and probabilities instead of generated text, named after Kahneman's fast-thinking System 1, with confidence to route around uncertainty.
Jev Guides & ArticlesDocs#official#docs#architecture
Official
Why TypeSafe trains decision models with RLCD instead of RLHF: calibrated probabilities where 0.2 outcomes happen about 20% of the time, and the case for machine-to-machine automation.
Jev Guides & ArticlesDocs#official#docs#evaluation
Official
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.