Active Product Hunt campaign vs. three editorial page visits
Rules for the obvious.
Jev for the ambiguous.
Eight labeled visitor journeys. One transparent baseline. Expected answers are withheld from Jev until scoring.
Run live with your own key ↗5 of 8 matched the labeled rubric
8 of 8 matched the labeled rubric
cases handled by function without Jev
4 judgments · 254 ms totalEvery answer is inspectable.
The baseline always prioritizes page-count first, then UTM/referrer, then default. The hybrid uses functions for clear cases and sends only conflicts to Jev.
Deep history normally means returning, but every signal is technical
No acquisition signal and repeated commercial exploration
UTM exists, but it marks internal navigation—not acquisition
Strong acquisition signal and no meaningful history
No evidence for a specialized experience
A UTM-tagged link that is still clearly developer traffic
Fresh email click vs. an established pricing and security journey
The function is the frame.
Jev fills the gap.
Function extracts facts
Normalize referrer, classify UTM, count meaningful paths, and detect obvious cases.
Jev resolves conflict
Only ambiguous combinations become typed, three-way Jev choices.
Function enforces safety
Validate the answer, restrict it to three variants, and fall back on failure.
Recorded live Jev run from September 20, 2026. Expected labels were used only for scoring after the response and were not included in Jev state or questions. This proves behavior on the labeled MVP set, not conversion lift.
Verify it on your machine.
Clone the repository, add your own TypeSafe key locally, and rerun every case.