Independent · unofficial
Typesafe Jev, indexed and measured
Jev is a model that answers typed questions instead of writing text. This site does two things with it: it groups public builds by the kind of decision they make, and it publishes latency and cost numbers we measured on the same task.
Case index
336
public builds, grouped by the kind of decision they make
Benchmarks
396 calls
same-task latency and cost, raw responses published · Jev warm p50 312.7 ms
What this site is
Two parts, and they support each other. The case index collects public builds and groups them by decision type, so you can find the one that looks like your problem rather than the one with the most views. The benchmark page runs Jev and two chat models on an identical task set and publishes every raw response, so you can recompute the numbers instead of trusting them.
The grouping is the useful part of the index. “Someone used it to sort files” and “someone used it to drive a browser” are not the same kind of fact; what transfers between projects is the shape of the decision, not the domain.
What this site is not
It is not affiliated with TypeSafe, and it is not a mirror of anyone’s posts. Every case links to its original post, keeps only a short excerpt, and rehosts no media and no threads. Where a claim comes from an author we say so and quote their figure as reported rather than verified.
It is also not a tutorial library. The concepts of the model — what the three primitives are, how confidence thresholds work, when not to use it — are already documented well elsewhere, and we link out instead of writing them again.
Start here
If you want to know whether it is worth it, read the benchmark page first and run the scripts from your own region. If you already know what you want to build, start with the case index or the hub closest to your problem: browsers, games and realtime control, or document classification.
Start here
- Jev latency and cost, measured on the same taskSame-task latency and cost measurements for TypeSafe Jev against chat models, with the full method, warm and cold reported separately, and raw JSON published.
- Jev case indexAn indexed, searchable collection of public TypeSafe Jev builds — each one linked to its original post, grouped by the kind of decision it makes.
- Jev browser agentHow teams wire TypeSafe Jev into browser and computer-use agents: the observe → type questions → act loop, reported latency and cost, and the failure modes.
- Jev for games and realtime controlUsing TypeSafe Jev as the decision layer for Jev game AI decisions: legal-move enumeration, per-frame latency budgets, and why a schema prevents illegal moves.
- Jev document classificationClassifying documents, rows and records with TypeSafe Jev: batching, label sets, per-page economics, and the accuracy figures teams actually reported.