Use case · Mixed
Phishing and email security classification with Jev
Jev's single raw verdict lost on accuracy to a cheap LLM in an independent test — but combining five cheap signal questions from the same call beat it decisively.
The problem
Phishing classification is high volume and latency-sensitive, which makes the speed and cost profile attractive. But security is exactly where you should not take a vendor's accuracy claim on faith.
How Jev handles it
Rather than asking one "is this phishing?" question, ask several orthogonal signal questions in the same call — sender plausibility, urgency pressure, credential solicitation, link/domain mismatch — and combine them in your own classifier.
def signal(instructions, yes, no):
return Noul(instructions=instructions,
criteria=NoulCriteria(true=yes, false=no))
response = client.system_one(
model="jev-latest",
state=email_text,
questions={
"urgency": signal("Does this create artificial time pressure?",
"Deadlines or threats of loss", "No time pressure"),
"credentials": signal("Does this ask for credentials?",
"Requests login, password or MFA code", "No credential request"),
"sender_odd": signal("Is the sender identity inconsistent?",
"Display name conflicts with address", "Sender looks coherent"),
"link_mismatch": signal("Does link text disagree with its destination?",
"Anchor text and href point elsewhere", "Links are consistent"),
"unusual_ask": signal("Is an unusual financial action requested?",
"Wire transfer, gift cards, payment change", "No financial request"),
},
)
# Five probabilities in, your own classifier decides
features = [response.answers[k].noul for k in
("urgency", "credentials", "sender_odd", "link_mismatch", "unusual_ask")]
is_phishing = my_logistic_model.predict_proba([features])[0][1]Does it actually work?
Independent evidence
Across 2,000 phishing emails, Jev's own verdict was statistically worse than Claude Haiku 4.5 (McNemar p < 0.0001) while winning on speed and cost. A cross-validated logistic regression over five signal questions asked in the same call reached 95.1% accuracy, AUROC 0.988, ECE 0.027. Latency was measured wall-clock from France against US-hosted services.
Notes from the field
- This is the most important lesson on the whole site: many cheap questions beat one big question, and the cost of asking more is close to zero.
- Never ship a security classifier on vendor numbers alone — build a labelled set from your own traffic.
- Jev is a signal generator here, not the final authority.