Live radar · scored by Jev
What people are building with Jev.
119 signals · last crawl
Jev Bookkeeping Automation
Jev is an independent index that automates bookkeeping by performing actions on a desktop accounting application based on a decision log and a dynamically rewritten playbook.
Open Source Jev Clone
This project is an open-source clone of the Jev API, designed to outperform the original in its core function by offering offline execution, zero cost, and open weights, while achieving competitive accuracy and significantly lower latency.
TypeSafe Jev Index
TypeSafe's Jev is an independent index that filters data based on specified criteria, returning a probability or score without extraneous text.
JevSQL: Natural Language Predicates for SQL
JevSQL enables asking questions in natural language within SQL queries using a typed control plane, avoiding direct LLM interaction with data.
Jev by TypeSafe AI
Jev is an AI model that rapidly processes news articles, assesses their relevance to a given portfolio, and extracts key information for further use.
AI Triage for Healthcare Intake
This project moves the decision-making step in AI triage for healthcare intake from an LLM to Jev, utilizing 25 typed questions to process decisions quickly and affordably.
Live Sales Call Analyzer
This project uses Jev, an AI model that makes decisions and classifies things, to analyze live sales calls by dissecting conversations, identifying key deal signals, and triggering actions to assist sellers.
Jev Performance on Ruka Workload
Jev processed 500 products with 801 possible master supplies in 8 seconds, achieving approximately 62 products/sec, a significant improvement over the current LLM pipeline's 2 products/sec.
Support-Ticket Triage Simulation
This project simulates support-ticket triage using Jev, performing five parallel typed judgments for department, frustration, urgency, human request, and refund intent.
Jev: Frontier Model for Decisions
Jev is a frontier model optimized for decision-making, processing state and typed questions to return booleans with probabilities, enums, and scores in a single pass, eliminating the need for output parsing or schema management.
Jev Resume Screener
This project uses Jev to build a resume screener that provides typed probabilities for answers to small questions, flags unsure answers, and ensures every score is traceable for consistent results.
Jev Team Calendar
Jev returns typed skill judgments per resume, not generated text, to form a project team.
Real-time Support Triage and Response Bot
This project is a bot that triages support tickets, routes them to the appropriate specialist agent, and determines if human intervention is needed, with Cerebras drafting the reply.
Jev vs. LLMs on Support Tickets
This project compares the performance of Jev, GPT-5.6 Luna, and Claude Sonnet 5 in handling 30 support tickets, evaluating speed, cost, and accuracy.
We aren't running Jev through our formal benchmarks because many of our evaluations involve open
I gave Jev some proprietary data alongside OHLCV over the last 2 years and a few actions it could choose from (long/flat/short).
Jev Playground Support Ticket Analysis
Jev Playground analyzes support tickets to extract structured data like assigned teams, refund requests, and urgency scores.
Jev Expense Categorization
This project uses Jev to automatically categorize expenses within an open-source application.
End of radar









