A voice agent makes a dozen small decisions every turn: is this a card number, do they want a human, is my draft safe to say? jevelin takes them off the critical path with a System One classifier, either Jev or the Apache-2.0 Laya on hardware you already own, and schedules every turn as a dependency graph. Move the sliders. The Python engine is running in your browser.
Assumptions: drag to change them
When does the agent start speaking?
Share of turns that have started speaking by each moment after the caller stops. Further left is faster. Dots mark each median. Hover to read values.
Baseline vs fast path
Time zero is the moment the caller stops talking. Everything left of it happened while they were still speaking.
The design rule
Raise the drawbridge. Never lower it.
A classifier can make a turn more cautious. It can never make it less cautious. Every output leads to a stricter, pre-approved path: a protective script, a transfer, a blocked draft, a hold. None of them unlocks anything.
How the fast path works
What's simulated: LLMs, speech and the classifier's answers, with latencies and prices from a JSON profile you can replace. What's real: the scheduling, routing, rules and fail-closed logic. It's the same code as the repo, with tests.