Email Triage with a Judgment-Only Model
Updated 2026-09-20
The scenario
A shared inbox — support@, sales@, founders' personal mail — receives far more than anyone can read. Most messages need a quick route, not a thoughtful reply: newsletters, notifications, cold pitches, auto-generated reports. A minority need a human or a carefully drafted response today.
Why Jev fits
Triage is a routing decision repeated thousands of times a day. The outputs are closed: reply or don't, which lane, how urgent. That is precisely the yes/no + choice + score triad a judgment-only model emits — fast enough to run on every incoming message at arrival time, cheap enough that the inbox stays sorted in real time instead of in batches.
Judgment design example
Structured input per message:
| Field | Example |
|---|---|
subject | "Invoice discrepancy — March" |
sender_domain | acme-corp.com |
is_existing_customer | true |
body_excerpt | first ~500 characters |
thread_length | 4 |
Judgments to define:
- Binary: "Does this need a reply from a human or a drafted response?" → no → archive with label.
- Choice: "Which lane?" →
billing/support/sales/legal/personal/noise. - Score: "Urgency 0–100" → sorts today's queue; anything above threshold pings immediately.
Where the LLM sits
Downstream of the verdict. For messages Jev routes as needs-reply, an LLM drafts the response using full thread context — the expensive read happens only where a reply will actually be sent. Noise never touches the generation budget.
This mirrors the voice-controlled-browser demo from early coverage in spirit: Jev decides what an incoming signal is and where it goes; other components do the acting. See the front-filter recipe.
Watch-outs
- VIP override. A hard-coded allowlist (boss, key accounts, legal) should bypass the noise verdict entirely.
- Excerpt limits. Judging on a truncated body can miss "by the way, we're cancelling" at the bottom of a long newsletter forward — include a tail excerpt or a full-body flag for long threads.
- Drafts, not sends. LLM-drafted replies should land as drafts for human approval until your error rate earns more autonomy.
Sources
- "Jev: The New AI Model That's Breaking The Internet (Full Tutorial)" — Moritz (~43K views, 2 days) — includes the voice-controlled-browser demo: judgment as the routing layer.
- "Jev is HERE. How to use it" — Greg Isenberg (~293K views, 1 day).
- AI with Surya — early-access coverage of the judgment (not generation) model concept.
Unofficial fan-made handbook. Not affiliated with TypeSafe AI or jev.com.
Related Guides
Content Moderation with a Judgment-Only Model
Use Jev-style judgment calls to screen high-volume UGC: spam, toxicity, and policy flags — cheaply, at full throughput, with LLMs reserved for borderline cases.
Data Filtering with a Judgment-Only Model
Use Jev-style judgments as a data-quality gate: relevance filtering, dedup signals, retrieval scoring, and training-data curation — before expensive downstream stages ever see the data.
Lead Scoring with a Judgment-Only Model
Score and route inbound leads with Jev-style judgments: ICP fit yes/no, tier classification, and 0–100 scoring — so sales and LLM-written outreach only touch leads worth the effort.
Sentiment Analysis with a Judgment-Only Model
Classify sentiment at scale with Jev-style judgments: polarity labels, aspect tagging, and intensity scores — cheap enough to cover every mention, with LLMs reserved for ambiguous cases.