Introduction

RubricHQ is a conversational AI testing platform for QA-testing voice-based AI agents — call center bots, customer service AI, and more.

What you can do

• Create AI agents — configure voice agents with custom instructions, LLM models, and voice providers
• Define test scenarios — write realistic caller personas and conversation goals
• Run batch tests — simulate hundreds of calls in parallel
• Evaluate with metrics — score transcripts automatically with custom or standard metrics
• Optimize prompts — compare prompt versions and track improvements over time

How it works

1. Create an Agent — the AI system you want to test
2. Define Scenarios — what a caller will say and what outcome you expect
3. Run a Batch — launch multiple simulated calls at once
4. Review Transcripts and Metrics — see where the agent passed or failed
5. Use the Prompt Optimizer — iterate on the agent’s instructions and measure impact