/start-evals

Start AI evals without overengineering - create your first 20 test cases in a spreadsheet

# Start Evals Command

Launch your AI evaluation process using the **PM-Friendly Evals approach** (Aman Khan + Hamel Husain).

**Works with:**
- **Linear MCP / GitHub MCP** - Optional: Can create eval project with test case issues
- **Manual** - Generate test cases as markdown/spreadsheet (recommended for quick start)

## What This Does

Helps PMs start testing AI quality **without overengineering**. Generates your first 20 test cases and sets up a lightweight eval process.

**Philosophy:** Start with 20 test cases in a spreadsheet. Scale when ready. Error analysis > automation.

## Usage

...