Zod validates data you already understand. Jev judges data you don't. jod is the seam: your state validates locally and for free, every question goes out in one parallel request, and typed answers come back. github.com/mateonunez/jod
Patterns
Hierarchical classification
Walk a deep taxonomy level by level, using each Choice answer to pick the next level's options, keeping several paths alive.
- Category
- Patterns
- Also known as
- —
- Related terms
- 4
- Directory entries
- 2
- Docs
- docs.typesafe.ai
- Added
- 2026-09-24
Definition
The cookbook classifies documents through deep patent, retail product, biomedical, and source-code hierarchies. Instead of flattening a taxonomy into one 255-option Choice, each level is its own question and the winner's children become the next request's options.
The trade-off is round trips versus option count: a level-by-level walk keeps every candidate path available in one call per level, which is why it is paired with beam search to avoid committing too early.
Tagspatternsclassification
Related terms
Definitions that connect to this one.
Parallel beam searchKeep the top-k branches at each taxonomy level instead of only the winner, so a wrong first choice can still be recovered.PatternsChoicePick one option from a set you define; returns the selected option, a probability for every option, and confidence.PrimitivesSecond requestA follow-up call that is only justified when code cannot build the second request until it has the first answer.PatternsLine-by-line searchRank every line of a document in one request with a Choice, while a Noul checks whether the document contains an answer at all.Patterns
From the directory
Classify documents through deep patent, retail product, biomedical, and source-code hierarchies using parallel beam search over Choice probabilities.
Cookbooks & DemosDocs#official#cookbook#classification
Official
The three TypeSafe question types, the typed answers they return, how to choose between them, and how to ask several in a single call.
Practices & PatternsDocs#official#primitives#choice
Official
From the community
Posts from builders shipping with Jev right now.
jod: Zod validates data, Jev judges it
Loki: a self-improving harness with a Jev companion
You can run Jev at home with Loki as well! It’s a full agent harness github.com/wundercorp/loki
Jev as an LLM guardrail inside Agentgateway
TypeSafe’s new Jev model is fast 🔥 and Agentgateway keeps up! In minutes, I had Jev running as a prompt guard through Agentgateway, with distributed tracing and cost tracking. Check out the example below Example: github.com/agentgateway/a… Intro to Jev: typesafe.ai/blog/introduci…
Jev reranks station suggestions in TrainLCD
提案駅のリランク判定と実測スパイクを追加する by TinyKitten · Pull Request #33 · TrainLCD/Functions github.com/TrainLCD/Funct… AIチャット機能の一部にもJevを潜ませてみるゾ
Vercel's fx safety reviewer, measured at 18× faster
@vercel 's fx uses Jev to review every command. @rauchg says it's up to 18x faster than GPT Luna and more accurate. @JoshARosen built Foreman, where Jev watches coding agents for drift, missed tests and getting stuck. @shantanugoel's Hermes agent installed an "ask Jev" skill on Show more
A game where you race Jev at spotting slop
A small game to show how fast TypeSafe's Jev actually is. Try to beat it at detecting a spam message beatjev2it.jlamberts86.workers.dev
