How to shape what Jev evaluates: a string, a named object, or an array of messages. Every question in a request sees the same state and is evaluated independently.
Practices & Patterns·#official#docs#state
Official
A maintained list of jev-1.13's known failure modes, literal reading, unreliable counting, dates as text, indirection, context rot, and contradictory criteria, each with a guardrail.
Practices & Patterns·#official#docs#evaluation
Official
Pick one option from a set you define. Returns the option, the full probability distribution, and 0-1 confidence, with up to 255 options and parallel questions that barely add latency.
Practices & Patterns·#official#primitives#choice
Official
Rate content against 2 to 10 ordered levels. Returns a probability-weighted score that can land between levels, per-level probabilities, and confidence, with the arithmetic left to code.
Practices & Patterns·#official#primitives#score
Official
The yes/no primitive: one probability from 0 to 1, where the value is the answer and no separate confidence is needed. True and false criteria pin down subtle boundaries.
Practices & Patterns·#official#primitives#noul
Official
Instructions, option descriptions, score levels, and noul criteria all accept JSON, so you can label question parts, pass schemas and taxonomies, and keep candidate paths alive.
Practices & Patterns·#official#primitives#architecture
Official
Break a judgment into atomic Score questions, normalize each by its top level, and combine them with weights you control in code, as in the resume example's four scored dimensions.
Practices & Patterns·#official#patterns#score
Official
Use the answer to decide what to do and confidence to decide whether to act: the voice-banking example routes below 0.6 to a human and needs 0.85 or more to auto-approve a transfer.
Practices & Patterns·#official#patterns#confidence
Official
Ask everything the system might need in one request, then let code throw away what it does not use. The ticket-triage example sends a category plus four speculative questions in parallel.
Practices & Patterns·#official#patterns#batching
Official
Classify intent with a Choice and complexity with a Score, then send each branch to deterministic code, a specialist model, or a person, with a 0.5 intent-confidence floor.
Practices & Patterns·#official#patterns#routing
Official
An agent skill for writing and improving programs that call Jev: question design, state structure, answer composition, confidence thresholds, and how to diagnose a question that keeps coming back wrong.
Practices & Patterns·#community#skills#claude-code
A map of documented Jev use cases, routing, guardrail verification, citation checking, reranking, rubric scoring, bulk classification, and semantic linting in CI, each with a confidence policy.
Practices & Patterns·#community#routing#evaluation
Community
An engineering note that places Jev as a typed micro-decision layer inside an agent harness rather than a planner, with preconditions for confidence gates and fan-out and a runtime split into five parts.
Practices & Patterns·#community#agents#routing
Community
A comparative review of Jev and the open-source Laya encoder: interfaces, deployment, disclosed internals, calibration claims, and the limits of agreement-based workflow evals.
Practices & Patterns·#community#evaluation#calibration
Community
Yuchen Jin's take on Jev for LLM-as-a-judge work: 20-200x faster and 40-400x cheaper, with a screenshot of the model picking which candidate is AGI after a prompt sweep under $0.10.
Practices & Patterns·#community#x#evaluation
Community
Vercel CTO Malte Ubl reports that Jev beat an existing classifier eval previously run on Gemini 2.5 Flash Lite, saturating the eval on quality and running 6x faster.
Practices & Patterns·#community#x#evaluation
Community
A widely read counterpoint to Jev-based context compaction: compaction is reconstruction, not filtering, and scoring tool calls to drop history misunderstands context management.
Practices & Patterns·#community#x#compaction
Community
The WebMCP benchmark author reports that Jev paired with the small Mercury 2.5 model solved 100% of tasks at roughly 112x lower model cost than GPT-6 Astra with computer use.
Practices & Patterns·#community#x#benchmark
Community
The three TypeSafe question types, the typed answers they return, how to choose between them, and how to ask several in a single call.
Practices & Patterns·#official#primitives#choice
Official
How TypeSafe reports certainty, how it differs from probability, and how to use it architecturally to gate and route decisions.
Practices & Patterns·#official#confidence#routing
Official
Architectural patterns for System One systems: speculative fan-out, confidence-gated routing, composite scoring, and intent routing.
Practices & Patterns·#official#patterns#architecture
Official
Design AI-powered software by keeping code in control and giving System One narrow, structured decisions to make.
Practices & Patterns·#official#patterns#architecture
Official
Explore TypeSafe use cases by industry and turn promising ideas into concrete software workflows.
Practices & Patterns·#official#use-cases
Official
