TAG
Probe RL environment verifiers for false passes and false fails
A realistic fictional small business for testing AI agents: synthetic data generator, mock CRM/inbox/calendar/invoicing MCP servers, and verified workflow tasks.
A deterministic first-pass filter for unsupported claims in LLM output, computed without calling another LLM. Not a standalone hallucination detector. A spec plus reference implementation, shipped as touchstone-mcp.
