Judge whether retrieved text is relevant, ranked correctly, or actually supports the claim it is cited for.
An answer with citations is only as good as the citations. Match each quote against the source in code to catch fabrications, then ask Jev one Choice question about how the surrounding section relates to the claim. Confidence decides which verdicts a human reviews.
Two catalogues describe overlapping sets of the same products, and a rough first pass hands you candidate pairs. One Jev Score question with a level per outcome decides each pair, and yes/no questions about individual fields tell a curator where the two sources disagree.
Retrieval returns whatever looks similar, including noise and hostile text. Put a Jev call between retrieval and generation: four yes/no questions per passage return probabilities, and your code decides which passages become evidence, which get flagged as conflicts, and which never reach the prompt.
Keyword or vector search narrows thousands of documents to a shortlist but rarely puts the right one first. Ask Jev one yes/no question about each query and candidate pair, take the probability it returns as the score, and sort the shortlist by it, highest first.
Things people have built and written that match one of the use cases above.
AI News daily roundup leading with the Jev launch, summarising RLCD and TypeSafe's 20-200x speed and 40-400x cost claims. Frames Jev as part of a broader move toward task-specialised models.
Compact encoder model that takes the label set as input at inference time and extracts arbitrary entity types zero-shot on CPU. Same classifier-that-takes-its-categories-as-input shape, for extraction rather than decisions. Star count is GitHub's rounded display figure.
Modernized BERT encoder used as the backbone for fast fine-tuned classifiers and rerankers. The non-generative baseline Jev's cost and latency claims are usually measured against. Star count is GitHub's rounded display figure.
Web search in plain language where Jev chooses sources, time ranges and search terms, then scores each result for relevance, with retrieval through Search1API. Returns links and snippets with visible relevance scores and editable filters, and writes no answers.
Codebase search that finds files matching a natural-language request through repeated Jev-guided passes over a directory tree.
Fish-style autosuggestions for zsh ranked by Jev. As you type, the plugin sends your last 100 distinct history entries and asks which one you are most likely completing, then shows the best match in grey with its score for you to accept.
Independent reimplementation inspired by jevlike that scores pre-written options in one batched forward pass by log-probability over a local Gemma 3 4B, shipping an HTTP server, CLI and a TypeSafe System One API implementation.
Agent-ergonomic CLI for Jev with pick, rate, check, rank, triage and guard subcommands, meant for agents offloading snap judgments from the shell.
Recursive tournament engine that ranks texts such as poems, startup pitches and cold emails using Jev for pairwise judgments, Elo rating mechanics and Swiss matchmaking, with real-time WebSocket streaming.
Command line search that asks a yes/no question of every function in a codebase and ranks the answers by the probability that the answer is yes. It is grep whose pattern is a question, not embedding search, and the author measured 1,302 functions of gin-gonic/gin in 3.7 seconds for $0.018.
Claude Code mod that routes decisions to Jev: it ranks installed skills against each prompt and answers the agent's own this-or-that questions when confidence is high enough, otherwise falling back to asking the user.
Rust and Python dataset sifter that streams Parquet and JSONL rows past Jev typed decisions at 1,500+ records per second, writing passed and rejected rows to disk. Uses speculative fan-out and calibrated post-training rubrics.