Built a live tool using @typesafeai JEV ! See live comparison btwn GPT & JEV at gptvsjev.vercel.app Get benchmarks like Money Spent ! Time Taken ! Tokens Used!
Patterns
Inbox triage
One Jev call per message, with a threshold and an action per label, so code moves or flags mail the model only scores.
- Category
- Patterns
- Also known as
- —
- Related terms
- 4
- Directory entries
- 3
- Docs
- —
- Added
- 2026-09-28
Definition
jev-mail-classifier turns each configured category into a Noul inside a single call, so one message can match several labels. Actions — tag, move, flag, mark read, webhook — run only when that category's probability clears its threshold. Processed mail is marked with an IMAP keyword, and a dry run changes nothing.
Jevmail keeps the same judgment and drops the writes: Gmail is read-only, and trays live in local SQLite. A threshold of 0.7 for urgent and 0.9 for spam is policy. It belongs beside the action.
Tagspatternsclassification
Related terms
Definitions that connect to this one.
Document splittingAsking Jev where one packet becomes the next document, then letting code export the page ranges.PatternsNoulThe yes/no primitive: one probability from 0 to 1, where the value is the answer and no separate confidence is returned.PrimitivesThresholdThe value your code compares against a score, a Noul probability, or a confidence to turn an answer into an action.Answers & ConfidenceConfidence gateA threshold on confidence that decides whether code acts, confirms first, or escalates to a person or a bigger model.Answers & Confidence
From the directory
19GitHub stars
An IMAP client that turns each inbox category into a Noul, then tags, moves, flags, or calls a webhook when the probability clears that category's threshold.
Tools & CLIs#community#python#email
Community
parth-kp/jev-mail-classifierPython
parth-kp/jev-mail-classifierPython86GitHub stars
A local, read-only Gmail triage app that sorts mail into five trays with Jev: each message becomes one experimental_evaluate call answering tray, urgency, and human-written questions, and 1,000 emails sort in about a minute for around 3 cents.
Cookbooks#community#typescript#privacy
Community
fazlerocks/jevmailTypeScript
fazlerocks/jevmailTypeScriptvogel ran Jev over 1,500 of his own emails to test classification quality and posted the results as a video, calling it the most impressive model he has tried for the task.
CookbooksVideo#community#x#video
Community
From the community
Posts from builders shipping with Jev right now.
GPT and Jev compared live
LitJev: Jev-style decisions on any local LLM
开源了 LitJev：我们对 Jev 类型化决策 API 实现方式的猜想，可接入任意现成 LLM。 小测试：Qwen3.8-27B，10 道 MMLU-Pro 一次完成，0.3 s。比让模型只生成答案快 2.9x；比生成完整 schema JSON 快更多（显然）。更多测试马上来。 非官方，基于公开信息。
Secret detection with Jev, tested
Built a quick Secret Detection Test with Jev by @typesafeai Results seem promising so far, ran it a few times and it's pretty consistent as well. github.com/teyhouse/jev-s…
Jev Driving Lab: a playground for System One models
@typesafeai (and System One models in general) have a lot of uses, and fun to play with. New paradigm open to public now. This is a self-driving sim I spun up to test Jev today. Structured sensor state in, typed driving decisions out, steer, brake, overtake, pedestrians, speed Show more
200 rows, 32 template families, and traps, judged in one call
First test with Jev (TypeSafe System One): 200 rows, 32 template families, traps — 'yes' rows with "we'll pass", 'no' rows with 'absolutely, happy to meet'. The single Jev question scored 100%. My 12 dimensions scored 98%. I had designed a task my own question could ace.
jev(): Postgres WHERE clauses in plain language
I think I just cooked something 🔥 jev(): a PostgreSQL extension that searches your whole database in natural language. No index, no embeddings, just one function. WHERE jev(people, 'could work from home') or WHERE jev(people, 'name sounds european') 129 rows judged in ~1s Show more
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x