Turn messy text into typed fields, scores, and labels that downstream systems and models can use directly.
Asking for one overall rating hides the reasoning inside a single number. Score each dimension as its own question instead, normalise each answer to a 0 to 1 range, and combine them with weights your code owns, so a ranking can be explained and retuned without new model calls.
A tabular model needs numbers, and a written note is not one. Ask Jev a set of questions about each row, keep the probability distribution rather than the winning answer, and you get numeric columns that a gradient-boosting model can train on alongside your existing features.
A taxonomy with thousands of leaves will not fit in one question. Ask one choice question per node instead, walking down the tree, and use the probability on each edge to decide whether to follow the single best path or keep several candidates alive.
Jev is not trained to generate text, so it cannot write a value out for you. Extraction works the other way round: a regex or a parser finds candidate spans, a choice question picks the one the question asks for, and code copies that span unchanged.
Things people have built and written that match one of the use cases above.
Makes one AI trade decision every Monad block on the Kuru MON-USDC market using Jev. Live at jev-trader.vercel.app.
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.
The 1,863-point, 490-comment launch thread. Top comments argue the frontier-model framing is misleading, dispute the cannot-hallucinate claim on the grounds that type safety is not factual correctness, and note grammar-constrained decoding on ordinary LLMs already covers much of the interface.
Declares typed input/output Signatures for LLM modules and optimizes the underlying prompts and weights against a metric. Its Signature abstraction is the closest widely-used open equivalent of Jev's typed-question interface. Star count is GitHub's rounded display figure.
Guarantees valid structured output during generation by constraining decoding to a grammar or schema. The mechanism HN commenters repeatedly cited as already covering Jev's cannot-produce-a-type-error guarantee on ordinary LLMs. Star count is GitHub's rounded display figure.
Pydantic-based library that extracts typed, validated structured data from LLMs across providers with automatic retries. The established way teams get Jev-style typed answers today, at LLM latency and cost. Star count is GitHub's rounded display figure.
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.
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.
Vercel Labs CLI for generating from the terminal. Its evaluate command takes a state plus typed questions and defaults its evaluation model to typesafe-ai/jev on the AI Gateway, with -m jev as the shorthand and an --input flag for text or JSON state.
Generative engine optimization platform that tracks brand mentions across ChatGPT, Claude, Gemini and Perplexity. Its NOTRA_JEV_CLASSIFIERS setting moves the chat router, the GEO judge and the feedback classifier off their LLMs and onto typesafe-ai/jev, and routes the eve agent's model choice the same way.
A TypeScript classifier that sends each PDF page's text to Jev as a choice over 261 IRS forms and 7 page kinds, with a second call only for five corporate forms and their schedules. Its eval reports 0 wrong pages on 314 filled TaxCalcBench forms at about $0.001 per page, 34x cheaper and 6x faster than the Sonnet pipeline it replaced.
Local-first MCP plugin giving Claude Code, Codex, Cursor and OpenCode structured code-quality scores (correctness, complexity, modularity, security) while they work. Sends focused diffs to Jev and keeps keys and code local.