MEDIA PREVIEW
Overview & Result
building a computer assistant with Jev local whisper listens to everything I say which then gets classified by Jev to determine what actions to take it uses a small Swift app to provide the full accessibility tree to Jev (i.e. tell its what's on my screen, what can be clicked, etc) still super early, but promising and all real-time which Jev was also local though. then it would be completely private
How Jev fits in the loop
- Ingest real-time application state and relevant contextual parameters
- Format the decision problem as a bounded Choice or Noul schema
- Query Jev to receive a typed probability distribution in sub-50ms
- Execute downstream actions or route tasks according to the winning choice
How to reproduce
- Inspect the original showcase and source material at https://x.com/marckohlbrugge/status/2100930430690050336
- Verify the bounded prompt and input candidate schema configured for Jev
- Benchmark decision latency and classification accuracy against baseline models
Why this build matters
Demonstrates a real-world, cost-effective implementation of Jev in a browser automation agent scenario, replacing expensive generative calls with fast typed decisions.
Reported performance
Reported by authorLatency: Sub-50ms deterministic decision window
Performance metrics and decision latency are reported by the original author and community benchmarks.
Limitations
- Task accuracy is bounded by the precision of the defined candidate choices
- Third-party external dependencies and network latency may affect total workflow duration