Building an agent with model router powered by Jev.
Patterns
Re-ranking
Score each query-candidate pair with one question and reorder a shortlist; the CLERC example lifts top-1 accuracy from 5% to 18%.
- Category
- Patterns
- Also known as
- —
- Related terms
- 4
- Directory entries
- 12
- Docs
- docs.typesafe.ai
- Added
- 2026-09-24
Definition
The re-ranking cookbook builds 30-passage BM25 shortlists for 40 CLERC legal queries, then asks one question per query-candidate pair. Top-1 accuracy rises from 5% to 18% and top-10 from 38% to 62%.
Pairwise questions give the model a narrow comparison instead of a whole-document judgment, and the resulting probabilities can be sorted directly — a natural fit for search and retrieval pipelines.
Tagspatternssearchreranking
Related terms
Definitions that connect to this one.
Line-by-line searchRank every line of a document in one request with a Choice, while a Noul checks whether the document contains an answer at all.PatternsRAG passage classificationScore each retrieved passage with four Noul questions, then decide in code which passages reach the answering model.PatternsParallel beam searchKeep the top-k branches at each taxonomy level instead of only the winner, so a wrong first choice can still be recovered.PatternsScoreRate the state against 2 to 10 ordered levels; returns a probability-weighted position, per-level probabilities, and confidence.Primitives
From the directory
One question per query-candidate pair raises top-1 accuracy from 5% to 18% and top-10 accuracy from 38% to 62% on 40 CLERC legal queries.
Cookbooks & DemosDocs#official#cookbook#reranking
Official
Rank 182 agent skills in one request and re-read the top three in a second: over 488 requests, wrong skill loads fell from 16.8% to 7.3% and needless loads from 9.8% to 4.0%.
Cookbooks & DemosDocs#official#cookbook#agents
Official
An independent evaluation of Jev in three retrieval stacks, with recalculated recall, latency, and cost against DeepSeek, GPT-4o-mini, and GPT-5-mini baselines.
Practices & PatternsArticle#community#search#reranking
Community
8GitHub stars
Reranking benchmark that gave Jev, Cohere Rerank 4 Pro, ZeroEntropy zerank-2, and DeepSeek the same thirty BM25 candidates across eight English datasets, publishing saved responses, scoring code, and paired-bootstrap intervals. Jev's rubric scored 0.692 nDCG@10 against Cohere Pro's 0.691.
Practices & Patterns#community#python#search
Community
anessbelbati/jev-rerank-benchPython
anessbelbati/jev-rerank-benchPython7GitHub stars
Unofficial LlamaIndex reranker and router built on the official Python SDK: JevRerank scores retrieved passages and JevSingleSelector chooses which tool handles a query.
Repos & SDKs#community#python#sdk
Community
WiktorB2004/llama-index-jevPython
WiktorB2004/llama-index-jevPython3GitHub stars
A CLI that reranks, filters, or extractively compresses JSON retrieval results by asking Jev separate Noul questions, then lets Rust apply the order and thresholds, reading stdin and writing stdout.
Tools & Integrations#community#rust#cli
Community
shinpr/jev-rerankerRust
shinpr/jev-rerankerRust6 more matching entries in the full directory.
From the community
Posts from builders shipping with Jev right now.
An agent with a Jev model router
Fraud detection with Jev and Kimi K3
Jev + Kimi K3 for fraud detection! TLDR: Jev classified 100 emails in 1.42 seconds, then I routed the uncertain cases to Kimi K3. The full pipeline got 96/100 correct for only ~$0.07. Video is not sped up, check out the live run! Here was my process: I gave Jev 100 emails to Show more
Jev Detector scans ~10,000 words for slop in ~2 s
Announcing Jev Detector The world's fastest AI slop detector, built on jev from @typesafeai ~10,000 words scanned for slop in ~2 seconds Best part, its free, no sign up required, enjoy! jevdetector.com
Computer use without screenshots
Okay so Jev can actually do computer use really well Without any screenshots, or LLMs and no Pixels leave my mac I dont even read the Dom elements A local CoreML model segments every button and UI element on screen. On-device OCR reads the labels. That text is all Jev gets. 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
Jev plays Subway Surfers
jev is insane 🤯 Here is Jev playing subway surfers at super human speed, and also playing 50 games at once. cost less than a cent to do this run. Jev does not replace llms like astra or fable, but opens up an entirely new world of capabilities.
Agentic browsing in Chrome
I built a Chrome extension for agentic browsing using Jev by @typesafeai, fx.sh including AI Gateway by @vercel. Now agents can browse, click, and interact with websites directly in your browser. Cost effective and fassst. Decision-making by Jev.
@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