Submit a project
Smart Home Assistant Demo
TypeSafe AIOfficial
An official walkthrough of batching home-control questions and using only the relevant answers.
Field notes
Short, practical guides with sources and clear limits.
Field notes & references
Review a research paper with Jev: a reproducible clarity check
A controlled edit, two reports, and a human verification checklist.
Read guide
Route support tickets
Four queues, a missing-details check and code-owned review thresholds.
Read guideRerank search results
Score a shortlist with a four-level rubric; handle ties and no-answer cases.
Read guideWhat Jev does well
A practical introduction to Choice, Score, and Noul.
Read guideJev in a real browser loop
A small control experiment, with timings and limits.
Read guideWrite better decision questions
Keep questions small, options clear, and uncertainty visible.
Read guideOfficial reading and references
TypeSafe Quick Start
TypeSafe AIOfficial
Start with the playground, make an HTTP request, and translate a first evaluation into Python.
Choice, Score & Noul
TypeSafe AIOfficial
Understand the three question types, the answers they return, and when to use each.
System One Workflow Patterns
TypeSafe AIOfficial
Explore fan-out, confidence-based routing, composite scoring, and intent routing.
System One HTTP API
TypeSafe AIOfficial
The request and response contract for calling Jev directly over HTTP.
Jev 1.13: Known Limitations
TypeSafe AIOfficial
TypeSafe's model-specific notes on failure modes and how to structure questions around them.
TypeSafe Workflow Evals
TypeSafe AIOfficial
TypeSafe's published comparison of structured workflows and single-prompt approaches.