Jev tools for real jobs
Each tool is one Jev question set built for a specific job. Open one to run it on your own text, see what Jev returned on a real example, and learn how to turn it into a step in your pipeline.
Have a whole file instead of one text? Run it as a CSV batch. See spreadsheet tasks
- Jev as a judgeCheck an LLM answer against reference facts and get a ship / revise / reject verdict with probabilities.Open tool
- LLM routerClassify a prompt’s difficulty and pick a small, medium or frontier model before you spend on the completion.Open tool
- Prompt injection detectorFlag instruction overrides and data-exfiltration requests in LLM inputs and get a pass / sanitize / block decision.Open tool
- Support ticket triageRoute a support ticket to the right team, rate its urgency and flag churn risk, each with a probability.Open tool
- Context compactionScore transcript excerpts for keep or drop, so compaction deletes what is stale and keeps the rest verbatim.Open tool
- Content moderationSort user comments into allow / review / remove, with separate harassment and spam probabilities.Open tool
- Lead qualificationScore an inbound lead’s fit, place it in a buying stage and check for a timeline, each with a probability.Open tool
- RAG evaluationCheck a RAG answer for groundedness and tell a retrieval failure from a generation failure, with probabilities.Open tool
- Tool call guardScore a proposed agent tool call for intent match and risk, and get an execute / confirm / block decision.Open tool
- Resume screeningMatch a candidate to a role, check seniority and suggest a next step, with probabilities for a human reviewer.Open tool
- Citation checkVerify one claim against one source: supported, partially supported or unsupported, and whether it is overstated.Open tool
- Review sentimentClassify a product review as positive, mixed or negative, estimate its star rating and flag refund requests.Open tool
- Zero-shot classificationClassify text into labels you define in plain English, with a probability for each label and no training data.Open tool
- Intent classificationDetect the intent of a customer or chatbot message from intents you define, with a probability for each.Open tool
- Model pricingMonthly cost of five decision models for your volume, text length and question count, from measured token counts.Open tool
Run it on a whole spreadsheet
Prefer to skip the code? These tasks take a CSV and return every row labeled, scored and sorted, paid in credits.
- Review analyzerSentiment, star rating, main topic and refund requests for every customer review.Open tool
- Lead scorerRank inbound messages by buying intent and fit, and filter out spam and job seekers.Open tool
- Ticket triageRoute support tickets to the right team and flag the urgent and at-risk ones.Open tool
- Keyword intent sorterClassify search keywords by intent, best page type and commercial value.Open tool
Getting started
- Decision modelsJev, Clef, Clef-flash, Perplexity Decider and OpenAI Luna Decisions on the same inputs: accuracy, calibration, cost and latency.Open tool
- Jev 시작하기Jev를 이용하는 방법(무료 체험, API 키, TypeSafe 직접 이용)을 요금, 절차, 코드와 함께 소개합니다.Open tool
- Clef playgroundTry Clef-flash free in the browser and compare Jev, Clef and Clef-flash side by side on your own input.Open tool
- How to get ClefEvery way to use Cloudflare’s Clef: free trial, JevStation API, Workers AI direct, self-hosted — with prices and code.Open tool
Integrations
Connect Jev to Claude Code, Cursor and other MCP clients.
- Jev MCP serverThe JevStation MCP server: its seven tools, client configuration, authentication, billing and troubleshooting.Open tool
- Jev in Claude CodeAdd the Jev MCP server and skills to Claude Code, then use Copy for AI to integrate Jev into your code.Open tool
- Jev in CursorConfigure JevStation’s remote MCP server in Cursor’s mcp.json and use the Jev tools from the agent.Open tool
Comparisons
How Jev stacks up against the other ways to get the same answer.
- Jev vs LLM classificationJev against a prompted GPT- or Claude-class model for classification: cost, latency, output shape, consistency and calibration.Open tool
- LLM router comparisonLiteLLM, OpenRouter, RouteLLM, Portkey and Jev compared by the decision each one makes, what it costs to run and where it fits.Open tool
- Jev vs open modelsopen-jev, jev-on-a-laptop, GLiNER and fine-tuned classifiers against hosted Jev: what each is, and what has been measured.Open tool
- Jev vs ClefCloudflare’s open-weight Clef against Jev: price, context, latency, benchmarks and when to pick each.Open tool
- Jev vs DeciderPerplexity Decider against Jev: same contract, measured accuracy, calibration, latency, and per-question billing.Open tool
- Jev vs Decision-1Microsoft-Decision-1 against Jev: same contract and price, measured accuracy, calibration, latency and tokens.Open tool
- Decisions API alternativesOpenAI Decisions API without the waitlist, plus Jev, Clef and Perplexity Decider: measured accuracy, cost, and how to port a request.Open tool