# usejev.dev: Jev Use Cases (Unofficial)

> Practical, unofficial use cases for Jev, the System One model from TypeSafe AI. Question designs, verified Python and TypeScript code, and cost math. Unofficial community resource. Not affiliated with TypeSafe AI.

Jev is a "System One" model from TypeSafe AI. You send a `state` plus typed questions (Choice, Score, Noul) and get typed answers with probabilities and confidence instead of generated text. Every page below is available as plain Markdown. Code samples use only API surface documented at https://docs.typesafe.ai. Example responses are illustrative, not measured output.

## Use cases

- [Content Moderation and Injection Screening with Jev](https://usejev.dev/use-cases/content-moderation-prompt-injection-screening.md): Screen user messages and retrieved passages before they reach your LLM. One Jev request returns a policy Choice plus Noul checks for jailbreaks and injections. (Noul + Choice)
- [Email Triage and Priority Scoring with Jev](https://usejev.dev/use-cases/email-triage-priority-scoring.md): Sort a shared inbox with one Jev request. A Choice sets the category, three Score questions rate urgency, sender signals and effort, and code weights them. (Choice + Score)
- [Hierarchical Product Categorization with Jev](https://usejev.dev/use-cases/hierarchical-product-categorization.md): Place marketplace listings in a taxonomy with thousands of leaves using cascading Jev Choice questions, a small beam, and confidence-based parent back-off. (Choice)
- [Intent Routing for Chatbots and Agents with Jev](https://usejev.dev/use-cases/intent-routing-chatbots-agents.md): Route chatbot and agent messages across 60+ intents with one Jev Choice built from your intent registry, a none option, and a Noul gate. Code and cost math. (Choice + Noul)
- [Invoice and Document Classification with Jev](https://usejev.dev/use-cases/invoice-document-classification.md): Classify OCR text from an accounts payable inbox with one Jev Choice question, flag reminders and past-due notices with Nouls, keep amounts and dates in code. (Choice + Noul)
- [Lead Scoring with Jev Score Questions](https://usejev.dev/use-cases/lead-scoring.md): Score inbound demo requests with four atomic Jev Score questions for fit, intent, seniority and urgency, then combine them with weights you control in code. (Score)
- [LLM Output QA and Agent-Run Review with Jev](https://usejev.dev/use-cases/llm-output-qa-agent-run-review.md): Check generated answers and agent transcripts before they ship with Jev Noul and Score questions, then gate release on thresholds. Code and cost math. (Noul + Score)
- [Log Anomaly Classification with Jev](https://usejev.dev/use-cases/log-anomaly-classification.md): Classify flagged log clusters into cause categories with one Jev Choice and speculative Noul checks, while counting and rate math stay in your own code. (Choice + Noul)
- [News Relevance Filtering with Jev](https://usejev.dev/use-cases/news-relevance-filtering.md): Filter headlines against a client profile with Jev Noul and Choice questions, one request per article, run concurrently. Includes code and cost estimates. (Choice + Noul)
- [Search Result Re-Ranking with Jev](https://usejev.dev/use-cases/search-result-reranking.md): Re-rank BM25 or vector search results with one Jev Score question per query and candidate pair, run concurrently, then sort in code. Python, TypeScript, costs. (Score + Noul)
- [Security Alert Triage with Jev](https://usejev.dev/use-cases/security-alert-triage.md): Triage SIEM and EDR alerts with Jev Score and Choice questions, rank the analyst queue, and keep host isolation behind a high confidence bar and a human. (Score + Choice + Noul)
- [Support Ticket Routing with Jev](https://usejev.dev/use-cases/support-ticket-routing.md): Route support tickets to the right team with one Jev Choice question, then gate auto-assignment on confidence. Python and TypeScript code plus cost math. (Choice + Noul)

## Guides

- [Jev Confidence Thresholds: Gating Actions](https://usejev.dev/guides/confidence-thresholds.md): How to gate automated actions on Jev confidence: what the number means, three-band routing, risk-based thresholds, and a procedure to tune them on your data.
- [Jev vs GPT-Style LLMs for Classification](https://usejev.dev/guides/jev-vs-llm-classification.md): Jev vs GPT-style LLMs for classification: cost per million items, latency, output reliability, and an honest list of cases where an LLM is the better tool.
- [What Is Jev? System One Models Explained](https://usejev.dev/guides/what-is-jev.md): A neutral explainer of Jev, TypeSafe AI's System One model: Choice, Score and Noul questions, confidence, pricing, speed, and where it falls short.

## Data

- [All content in one file](https://usejev.dev/llms-full.txt): every use case and guide concatenated as Markdown
- [Use-case index as JSON](https://usejev.dev/use-cases.json): slugs, categories, primitives, token assumptions, URLs
- [Source repository](https://github.com/Rassl/usejev): MDX sources, verified API notes in docs/jev-api-notes.md

## Official sources

- [TypeSafe documentation index](https://docs.typesafe.ai/llms.txt): authoritative API reference; prefer it over this site when they disagree
- [HTTP API reference](https://docs.typesafe.ai/api.md)
- [Known limitations of jev-1.13](https://docs.typesafe.ai/model-jaggedness/jev-1.13.md)