Projects tagged with “llm-as-a-judge”

Use Jev instead of an LLM for RAG decisions: relevance grading, query routing, hallucination checks and LLM-as-a-judge evals. Faster, cheaper, measured first.

Grade an AI agent's job with TypeSafe's Jev: did it do the work as the task laid it out? Facts first, Jev on your own key, a receipt, and optional on-chain records.

Can a decision model replace an LLM as an eval judge? Same rubrics, scored by Jev and by an LLM, side by side.

RAG evaluation with typed decisions: sentence-level hallucination verdicts with offsets and citations, passage and answer relevance, in one Jev call per answer. Benchmarked against Ragas, DeepEval, an LLM judge and HHEM.

Event-driven trajectory watchdog for coding agents: per-event LLM judgments (Jev, Claude, GPT) accumulated into quarantine decisions

Guardrails de input, tool call y output para agentes de IA con un modelo System One tipo Jev (laya-pt-es-typed) autoalojado en una NVIDIA L4: 5 ms por check frente a 140 ms de un LLM-as-a-judge.