ORIENTATION
Start here: official and explainers
The launch material, the docs and the best explainers of the typed-decision contract.
CURATED VIEWS OF THE INDEX
Collections
Hand-picked groups of entries by use case. Membership is editorial; evidence labels stay attached to each entry.
MEASUREMENTS
Benchmarks & independent tests
Every public measurement of Jev found so far: TypeSafe's evals dashboard, independent benchmark repositories, and vendor and builder tests on their own data.
ACTION SELECTION
Browser & computer use
Jev choosing the next click, key or app action from a bounded action space built out of the DOM, OCR or an accessibility tree.
ROUTING, GATING, VERIFYING
Agent harnesses
Where a typed decision sits inside a larger loop: model routing, tool-risk gates, context compaction, rollout rules.
MANY ITEMS, FEW DECISIONS
Search, ranking & queues
Thousands of pages, mentions, emails, ads or candidates screened by parallel yes/no and score questions before anything expensive runs.
PR GATES AND ROUTERS
Coding workflows
Jev inside coding agents: reviewing diffs against fixed checks, choosing models per turn, deciding what stays in context.
FAST LOOPS ON STRUCTURED STATE
Games & simulations
Real-time loops where the model picks an action many times a second from a small, fixed set.
OPEN REPLICAS
Local & replica models
Independent projects that reproduce the typed-decision interface on open weights or tiny specialists.
UPSTREAM DISCOVERY
Directories & roundups
Community lists and threads used as upstream sources for this index.
APPLICATIONS
Interfaces & creative workflows
Typed decisions in voice interfaces, reading tools, reference search and interactive controls. Each entry describes which part the model judges and which part ordinary code executes.