Cookbook: Classification using confidence
Uses the confidence value returned with Choice and Score answers to decide when to act automatically and when to escalate.
More like this
jev-trader
Makes one AI trade decision every Monad block on the Kuru MON-USDC market using Jev. The public deployment runs in dry-run mode with a mock model.
jarrodwattsOpenjev-trader on github.com2.2k starsLoop, mock model p50 100 msDecision window ~300 ms/block
jkudish/jev-mcp
MCP server that gives Claude Code, Codex, Amp, OpenCode and other agents ten Jev judgment tools, each returning typed probabilities they can branch on. The author calls it early software.
320 starsPer call 150-500 ms
Ran Jev against an existing classifier eval that previously used Gemini 2.5 Flash Lite
Vercel CTO reports Jev saturated an existing classifier eval that had used Gemini 2.5 Flash Lite and ran about 6x faster. Original post; TypeSafe's quote-tweet is a separate item.
Malte Ubl (@cramforce)OpenRan Jev against an existing classifier eval that previously used Gemini 2.5 Flash Lite on x.com220k viewsSpeed vs Gemini 6x faster
SetFit: efficient few-shot text classification
Fine-tunes Sentence Transformer embeddings plus a lightweight head for high-accuracy classification from a handful of labeled examples, with no prompting. The standard cheap alternative to an LLM classification call when the label set is fixed. Star count is GitHub's rounded display figure.
AnyJev: Jev-style decisions from any open LLM
Python library from Nokia researchers that reads typed Choice, Noul and Score answers with probabilities from an open LLM's logits or hidden states, without fine-tuning. Its zero-label level reduces option-order bias, and a head fit on 100 to 300 labels can run behind vLLM.
AlternativeConfidence-gated actionsForeman
Places Jev as a fast supervisor above slower Codex coding agents. Codex workers do the engineering while Foreman independently assesses whether the work is complete, requirements are met, tests suffice, or human input is needed.
