Email triage at scale
Fast, calibrated routing decisions across an overflowing inbox.
Crawled from X, GitHub, blogs, and docs. Jev classifies, de-duplicates, and ranks. Every row links back to the original source.
Jev scores relevance and originality, then we mix in public traction.
Fast, calibrated routing decisions across an overflowing inbox.
Speculative decisions first, LLM fallback only when needed.
I built a CLI that sorts a folder by what each file actually says, using Jev from @typesafeai.
been playing with Jev from @typesafeai and built unsaidbrief the idea: we give AI builders vague prompts, then spend hours fixing decisions we never actually made paste your brief
JevNoiseGate filters unwanted notifications and SMS on Android.
Apply OS — Personal career decision engine powered by TypeSafe AI (Jev).

Proof of concept using Jev by @typesafeai to analyze image metadata and estimate how likely an image is to be AI-generated.

shipped: jev by @typesafeai now gates tryeve's builds.
A natural-language dispatcher for MCP tools that makes zero general-purpose LLM calls — not to pick the tool, not to read out an argument's value, nothing. It runs entirely on @typ
Been seeing a lot of people get ghosted or scammed by fake job posts.
Measured on 19 documents / 155 pages, mistral-ocr-latest through a @LiteLLM gateway: OCR-only vs Jev-router 155 pages billed down to → 87 19 API requests down to → 13 35.6s → 20.7s
got early access to @TypeSafeAI (Jev). in my last post on autoresearch vs dream-rsi, the quiet bottleneck was: how do you score 28+ dreamt tree branches offline without waiting mi
Built a support-ticket triage simulation with @typesafeai #Jev ⚡ 5 typed judgments in parallel: • Department • Frustration • Urgency • Human request • Refund intent ~126ms avg |
jev でメモリコンパクションを実装する例。ログが今の作業と関係ある/ないを分類してフィルタするっぽい。 https://t.co/fe7idXMu95
Doc-OCR router using Jev @typesafeai A Jev-powered router that looks at a PDF page by page, decides which pages actually need OCR, extracts the rest locally. Result: save cost o
n8n community node for TypeSafe Jev structured AI decisions
🆕@typesafeai dropped Jev this week, a new frontier model optimized for decisions. We put it to work on an incident triage workflow in Box. Jev doesn't generate text. You send it
3 days ago ... Jev, TypeSafe claims, is well-suited for AI automation software, real-time applications that need quick decisions, AI map reduce jobs for classifying large ...
@hov8a @typesafeai Yep this is one I’m building: https://t.co/ZBWc616ww6 JEV does the fast semantic judgments, deterministic code handles ALLOW / REVIEW / HOLD.