Date extraction
Official TypeSafe cookbook pattern: extract dates with typed questions and do validation and arithmetic in code.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
This is a recipe in TypeSafe's Jev documentation. According to the list summary, it shows a pattern that separates typed extraction from date validation and arithmetic: the model identifies date components as typed answers, while ordinary code checks validity and computes differences.
The pattern reflects a general rule for decision models: let the model make the judgment it is good at and keep deterministic calculations in code. It is useful for anyone pulling deadlines, effective dates or durations out of documents.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Extract | Which date does the text refer to (as typed components)?(inferred) | — |
How it works
- Ask typed questions to identify date parts in text
- Validate the resulting date in code
- Do any date arithmetic in code
Strengths
- Deterministic validation and arithmetic
- Clear separation between judgment and calculation
Caveats
- List-only entry; recipe details not reviewed
Getting started
See https://docs.typesafe.ai/cookbooks/date_extraction_cookbook.At a glance
- Type
- Article
- Status
- production
- Has code
- yes
Use cases and integrations
How curated lists describe it
Official pattern separating typed extraction from date validation and arithmetic in code.
cobanov/awesome-jev
Frequently asked questions
What does the recipe show?
How to extract dates with typed questions while keeping validation and arithmetic in code.
Why not let the model compute dates?
Arithmetic is deterministic and more reliable in code.
Who publishes it?
TypeSafe, in the official docs.
Related projects
Eight zero-dependency examples applying Jev to mechanical and electrical engineering: CAD routing, FEM triage, DFM, BOM alignment.
ProjectprototypePythonNext.js community playground extending the 110-example TypeSafe library with A/B comparisons, routing, extraction, games and simulations.
ServicebetaTypeScriptTypeSafe cookbook showing how to evaluate many typed questions over one shared state in a single Jev request.
ArticleproductionAwesome list and guide to System One models (Jev, Laya and others) organized around a five-stage agent lifecycle, with comparison tables.
ProjectproductionOpinionated catalog of 84 Jev projects in 11 categories, each with a hand-written reason it is worth looking at.
ProjectproductionUnofficial collection of Jev state formats, question patterns, cookbook index and case studies, plus a ranked Top 30 of community builds.
Projectproduction