A skill router tested on production chatbot traffic
Cover is generated by this site (not the creator's media).
WHAT IT DOES
Rather than pasting every available skill into the prompt, a router asks JEV which one fits and loads only that one.
The author tested it against the routing logic ChatFrom already runs in production, and argues that a decision model returning a choice, probabilities and a confidence score is a natural fit for intent routing.
Reported by the creator on X.
Summary written by this site
FROM THE ORIGINAL POST
It's a decision model that returns a choice, probabilities and a confidence score, which makes it a natural fit for tasks like chatbot intent routing. So I tested it using ChatFrom's production routing logic — Rouzbeh · Original post
JEV ROLE
Routing
Choice
#routing#context-window#agent
WHERE IT SITS
HOW IT WORKS
INPUTan incoming user request + a catalog of skills
JEVRouting
OUTPUTthe skill to load and run
WHAT THE POST SHOWED
No observable metrics recorded. Metrics are only published when they can be tied to a source link.
SOURCE
↗ Original postSource checked
Evidence is a status, not a ranking. It says how the claim can be checked — not whether the case is good.
AD
Reserved ad slot
Ad units are wired but not filled yet.
RELATED CASES