II.
LibraryAgent overview
Reference · livelib-agent:ai-agents-conversational--llm-judge
llm-judge overview
Implements LLM-as-judge evaluation patterns
Attributes
displayName
llm-judge
description
Implements LLM-as-judge evaluation patterns
libraryPath
library/specializations/ai-agents-conversational/agents/llm-judge/AGENT.md
specialization
ai-agents-conversational
role
Safety and Evaluation Specialist
expertise
- LLM-as-judge design
- Evaluation prompts
- Scoring rubrics
- Judge calibration
- Agreement analysis
Outgoing edges
lib_applies_to_domain1
- domain:software-engineering·DomainSoftware Engineering
lib_belongs_to_specialization1
- specialization:ai-agents-conversational·Specialization
lib_implements_workflow2
- workflow:ml-model-lifecycle·WorkflowML Model Lifecycle
- workflow:feature-development·Workflow
lib_involves_role2
- role:ml-engineer·RoleMachine Learning Engineer
- role:backend-engineer·RoleBackend Engineer
lib_requires_skill_area2
- skill-area:eval-driven-development·SkillAreaEval-Driven LLM Development
- skill-area:agent-simulation-testing·SkillAreaAgent Simulation and Testing
Incoming edges
uses_agent1
- lib-process:ai-agents-conversational--conversation-quality-testing·LibraryProcessconversation-quality-testing