Parallel questions
TypeSafe cookbook showing how to evaluate many typed questions over one shared state in a single Jev request.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
This is an official TypeSafe documentation cookbook on parallel questions: evaluating many questions over shared state in one request. The list summaries describe it as a worked example alongside other reproducible recipes covering reranking, guardrails, citation checks, extraction and hierarchical classification.
Other projects cite this cookbook as the basis for batching independent questions into one call; one n8n node README reports TypeSafe measuring batching as 12.2x cheaper and 10x faster than separate calls with identical answers. The cookbook text itself was not fetched here.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Other | Multiple independent Choice, Score and Noul questions over one state | — |
How it works
- Build one shared state.
- Add many independent typed questions.
- Send them in a single request.
- Use each answer independently.
Strengths
- Fewer requests and lower cost than one call per question.
- Answers do not depend on other questions in the request.
Caveats
- Content not reviewed directly; summarised from list and other READMEs.
Getting started
Read https://docs.typesafe.ai/cookbooks/parallel_questions.At a glance
- Type
- Article
- Status
- production
- Runtime
- hosted API docs
- Has code
- no
- Has tests
- no
Use cases and integrations
How curated lists describe it
Official worked example of evaluating many questions over shared state in one request.
cobanov/awesome-jevReproducible recipes: parallel questions, reranking, guardrails, citation checks, extraction, hierarchical classification.
hellogumbo/awesome-jev
Frequently asked questions
What does the cookbook teach?
How to ask many typed questions about one state in a single request.
Why batch questions?
TypeSafe reports it is much cheaper and faster than separate calls.
Are there other recipes?
Yes, including reranking, guardrails, citation checks, extraction and hierarchical classification.
Related projects
PostgreSQL toolkit with 41 Jev-powered semantic operators and natural-language-to-SQL, leaving joins and arithmetic to SQL.
ProjectbetaPythonAgent skill that teaches coding agents to hand bulk semantic judgments to Jev and to find where a product could use Jev decisions.
Agent skillbetaWorked Jev examples for ticket triage and reranking, runnable through OpenRouter without an early-access key, with offline tests.
ProjectprototypePythonNext.js community playground extending the 110-example TypeSafe library with A/B comparisons, routing, extraction, games and simulations.
ServicebetaTypeScriptOfficial TypeSafe cookbook recipes for guardrails, re-ranking, RAG passage classification, citation checks and more with Jev.
ArticleproductionJSON-in/JSON-out CLI that reranks, filters or compresses search results with independent Jev Noul checks, keeping metadata intact.
CLIbetaRust