Glossary · Term

Progent

← all terms

Definition

A baseline approach for using a strong LLM as a safety judge over proposed agent actions.

A schema-aware LLM-as-judge safety architecture for agentic systems, used as the primary neural baseline in evidence-carrying agent comparisons.

Mentioned in 1 episode

  1. 062
    Treating Hallucinations as Exploits: A Gate-Based Architecture for Agent Safety