All JEV cases
Each use case has its own page with every JEV case we have for it.
01
EN
▶ VIDEO
Pushing a Replit project's 18,360 outcomes down to 57
A Replit project had 18,360 possible branch outcomes and months of manual fixes barely dented the list. JEV was pointed at the project and, per the author, resolved all but 57.
A
Aaron Horne
@ahorne
Source checked
02
EN
▶ VIDEO
Routing multi-agent requests with JEV: 96/97
In a multi-agent workspace something has to decide which teammate takes a request. Fez ran that decision on JEV and scored 96/97 on their own routing battery, 184 ms median, $0.0018 a run.
F
Fez
@fez_chat
Source checked
03
EN
A DuckDB extension that classifies rows with JEV
A DuckDB extension that calls JEV directly on any CSV, Parquet file or table — about ten seconds for a thousand rows, no export step and no classifier service to maintain.
H
Hamilton Ulmer
@hamiltonulmer
Source checked
04
EN
▶ VIDEO
Agent step selection in a tenth of a second
Agentcard wired JEV into a shopping agent so it picks each browser step, while a vault fills in the card at checkout — neither the agent nor the browser ever sees it.
A
Agentcard
@agentcardhq
Source checked
05
EN
▶ VIDEO
Outfit picking as the last JEV check
In the aesty closet app JEV is the final layer before an outfit ships: it caught toe shoes planted in a party look and rebuilt the outfit from clothes the user already owns — 3 s, $0.0015.
N
Nadia Zueva
@nestymee
Source checked
06
EN
▶ VIDEO
A Polymarket trading agent built on JEV
An open-source agent that places predictions on Polymarket's five-minute BTC up/down market, with JEV making the call.
g
gabidev
@GabiDev98
Source checked
07
EN
▶ VIDEO
Smart mail search and one-click unsubscribe
magic-mail adds natural-language search and automatic classification to the Omamail client, plus one-click unsubscribe.
J
Jason Bales
@BalesTJason
Source checked
08
EN
▶ VIDEO
JEV as a Macaly skill for content checks
JEV is now a Macaly skill: ask that app builder for AI classification and it wires JEV in. The demo scores each paragraph for AI slop and flags the writing issues.
T
Tomas Rychlik
@rychlis
Source checked
09
EN
▶ VIDEO
jevselector: dropping unused skills from the prompt
A CLI tool that scores an agent's installed skills and drops the ones a project never uses — cutting the system prompt by roughly half, while respecting per-agent and pinned skills.
S
Sam
@universamlang
Source checked
10
EN
▶ VIDEO
Finding old coding-agent chats by description
An open-source VS Code tool: describe what an old Claude Code or Codex session was about and it finds the session in milliseconds.
F
Florian S
@airesearch12
Source checked
11
EN
▶ VIDEO
Replacing the LLM guardrail with a probabilistic judge
Running Vercel's safety classifier through JEV instead of a frontier LLM came out 5–18× faster, and a probability cannot hallucinate the way prose can.
I
IdeaBosque
@ideabosque
Source checked
12
EN
▶ VIDEO
JEVBOT rebuilt its trade filters after a 33% win rate
A live trading bot published its first 45 closed trades, found a 33% win rate, opened the book, audited the failures and rebuilt its entry filters around JEV.
J
JEVBOT
@JevBotApp
Source checked
13
EN
Hooking a deterministic classifier into V8's JIT
An experiment that put a JEV-style classifier inside V8 to help the JIT decide when to promote code. The author's verdict: as dumb as it sounds.
K
Kapeka
@kapeka0
Source checked
14
EN
▶ VIDEO
Talking your day into coloured decisions
A small app transcribes a spoken diary, then JEV reads cues across twelve emotion-linked colours and turns the entry into something structured.
S
Soumya
@soumyadesign
Source checked
15
EN
A skill router tested on production chatbot traffic
JEV picks which installed skill answers an incoming request, so the whole catalog stays out of the context window. The author tested it against the routing logic their product already runs.
R
Rouzbeh
@JustRouzbeh
Source checked
16
EN
▶ VIDEO
Support chats: JEV scores, humans label, code decides
A test harness where JEV turns a support conversation into sentiment probabilities, compares them with human labels, and picks where the human-review threshold should sit.
A
Aman
@amanunreal
Source checked
17
EN
▶ VIDEO
Reranking Pinecone results with plain-language criteria
Pinecone's own walkthrough: use JEV to rerank search results against criteria written in natural language instead of training a reranker.
P
Pinecone
@pinecone
Source checked
18
EN
▶ VIDEO
Signal Lab: crypto cohorts scored by JEV
A public page where JEV analysed two crypto cohorts — coins nearing a Top 10 flip, and names reclaiming their SMA50/200 — with setup, ATH potential and narrative per name.
M
Market Scanner
@marketscan_360
Source checked
19
EN
▶ VIDEO
Removing information until the decisions break
A deliberately rigged hiking game: strip away the information JEV gets, step by step, and watch how long its decisions hold up. The author calls it a probe, not a benchmark.
V
Vivek Karmarkar
@vivekkmkpinn
Source checked
20
EN
▶ VIDEO
50,000 Airtable validations for about $30
Validation rules written in language instead of formulas, applied to Airtable: roughly 50,000 checks for about $30, surviving tables being added and removed.
M
Martin
@martinmalindacz
Source checked
21
EN
Gens, Instinct 与 Meta 的 Crunch 能力实测
用 JEV 跑通了带 Instinct、Ways、Town、Office 的 Crunch 流程……Inworld 的 popularity 场景下需要管理超过 500 人的 NPC 对话。
Y
Yohei
@yoheinakajima
Creator reported
22
EN
12 秒给 100 个视频打上销售意向分
用 JEV 对某个 YouTuber 最近 100 个视频做分类：判断每个视频「有多想卖我东西」，并给出销售意向分（1-5）……
E
EP
@epxits
Creator reported
23
EN
税务文件自动分类器
用 JEV 构建了一个税务文件分类器。我们导入成千上万份税务文件，使用我上一季度搭建的 LLM pipeline……
N
Nakshatra Saxena
@newize
Creator reported
24
EN
▶ VIDEO
不到一小时用 JEV 复刻 Tesla FSD 界面
I rebuilt Tesla Full Self Driving with Jev in less than an hour. This model is a total unlock.
J
Justin Schroeder
@jpschroeder
Creator reported