Guides
Use Cases
Where a judgment-only model fits: moderation, scoring, triage, and filtering patterns.
Document Triage: Type and Urgency on Two Axes
Sort inbound documents — contracts, invoices, resumes, tickets — by type with Choice and by urgency with Score, so each document class gets its own downstream pipeline and deadline.
Intent Classification: The Front Door of a Chatbot
Classify user messages into intents (and urgency) before any LLM touches them — so simple requests get cheap handlers and only genuinely open-ended messages reach the expensive model.
RAG Reranking: Filtering Retrieval Results by Relevance
Use Jev-style Noul judgments to batch-score retrieved chunks for relevance and keep only the top-k — so the LLM answers from signal, not from whatever the vector search coughed up.
Validating Structured Extraction: Code First, Judgment Second
Pair deterministic code validation (schema, types, ranges) with a Jev-style semantic review pass — catch the extraction errors that parse fine but mean the wrong thing.
Support Ticket Routing with a Judgment-Only Model
Route support tickets to billing, technical, account, or sales with Jev-style Choice judgments — plus spam filtering and urgency scoring so humans only see what matters.
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.
Email Triage with a Judgment-Only Model
Triage inbound email with Jev-style judgments: needs-reply yes/no, lane classification, and urgency scoring — so LLM-drafted responses are only generated for mail that deserves one.
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.