> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.rubrichq.io/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.rubrichq.io/_mcp/server.

# 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