Specialized AI evaluators and agents that power CXMind's intelligent testing
Judge Agents
Specialized evaluators that assess bot responses
Custom Judges
Create your own judges with custom prompts and LLM configurations
No Custom Judges Yet
Create custom judges with your own evaluation prompts and LLM configurations
Describe what to evaluate and how to score. JSON output formatting is automatically appended — just focus on your evaluation criteria.
LLM Configuration
No LLM providers configured. Add one in LLM Providers
Test cases with these tags will automatically use this judge
Which quality dimension does this judge primarily evaluate?
Retrieve relevant document chunks to enhance evaluation accuracy
Allow this judge to call tools from connected MCP servers during evaluation
Upload ground-truth documents specific to this judge's evaluation scope
Utility Agents
Agents for test generation, driving, and summarization